Browse content similar to The Secret Science of Pop. Check below for episodes and series from the same categories and more!
Line | From | To | |
---|---|---|---|
# Oh, baby, baby, the reason I breathe is you | 0:00:05 | 0:00:11 | |
# Boy, you've got me blinded... # | 0:00:13 | 0:00:17 | |
We're told that ours is an age of data, | 0:00:17 | 0:00:20 | |
an age in which practically everything we do, | 0:00:20 | 0:00:23 | |
say and make can be reduced to flows of information by algorithms | 0:00:23 | 0:00:28 | |
spinning away on server farms in remote locations. | 0:00:28 | 0:00:32 | |
Data science already tells us where to go, how to get there, | 0:00:37 | 0:00:41 | |
who to date and what to buy them. | 0:00:41 | 0:00:44 | |
But all that's rather trivial stuff. | 0:00:44 | 0:00:46 | |
I think that even the most glorious, ephemeral and marvellous | 0:00:46 | 0:00:52 | |
products of the human mind | 0:00:52 | 0:00:54 | |
can in fact be measured by science. | 0:00:54 | 0:00:58 | |
And by that, I mean pop. | 0:00:58 | 0:01:01 | |
MUSIC: I Really Like You by Carly Rae Jepsen | 0:01:01 | 0:01:05 | |
Armed with just a few algorithms, | 0:01:05 | 0:01:07 | |
I intend to change the way we understand pop. | 0:01:07 | 0:01:10 | |
This is based upon the music - | 0:01:10 | 0:01:13 | |
the wave forms, the numbers. | 0:01:13 | 0:01:15 | |
I'm gathering a team of data scientists to analyse | 0:01:17 | 0:01:21 | |
five decades of the UK's Top 40 hits. | 0:01:21 | 0:01:23 | |
Together, we'll show the artists what science can do. | 0:01:24 | 0:01:27 | |
# Doo, doo! Doo-doo-doo-doo! # | 0:01:30 | 0:01:32 | |
We're teaming up with pop legend Trevor Horn. | 0:01:32 | 0:01:36 | |
So, this is a thing called M Harmony PCA 4. | 0:01:36 | 0:01:38 | |
Right. | 0:01:39 | 0:01:40 | |
# Into the ocean with me... # | 0:01:40 | 0:01:44 | |
We're going to try to do something never tried before - | 0:01:44 | 0:01:48 | |
use data to give an unsigned artist a potential hit. | 0:01:48 | 0:01:52 | |
I like the end. That was good. | 0:01:52 | 0:01:54 | |
I can't even imagine, like, | 0:01:54 | 0:01:56 | |
what the science is going to say or do to the song. | 0:01:56 | 0:01:59 | |
MUSIC: Hey Ya! by OutKast | 0:01:59 | 0:02:01 | |
I'll also be using my analysis to map the turning points | 0:02:01 | 0:02:05 | |
of pop history. | 0:02:05 | 0:02:06 | |
Love Me Do, right on the average. | 0:02:06 | 0:02:08 | |
Yellow Submarine, right on the average. | 0:02:08 | 0:02:11 | |
Lennon and McCartney are writing ditties for prepubescent girls. | 0:02:11 | 0:02:14 | |
We don't know what the answers will be. | 0:02:14 | 0:02:17 | |
Yeah, it's not exactly an advertisement for machine learning, is it? | 0:02:17 | 0:02:19 | |
-No. -THEY LAUGH | 0:02:19 | 0:02:22 | |
But that's what happens when science... | 0:02:22 | 0:02:24 | |
-Thank you, sir. -Thank you for exposing me on national television | 0:02:24 | 0:02:27 | |
-in getting it wrong! -THEY LAUGH | 0:02:27 | 0:02:28 | |
Hey. | 0:02:28 | 0:02:29 | |
..meets culture. | 0:02:29 | 0:02:31 | |
What exactly are your qualifications? | 0:02:31 | 0:02:33 | |
My PhD was on fruit flies, | 0:02:33 | 0:02:35 | |
I've spent most of my professional life studying worms. | 0:02:35 | 0:02:38 | |
MUSIC: You're Gonna Miss Me by 13th Floor Elevators | 0:02:48 | 0:02:53 | |
Let me begin with a confession. | 0:02:56 | 0:02:58 | |
I'm not much of a music fan. | 0:02:58 | 0:03:01 | |
Worse, as an immigrant that's citizen of nowhere, | 0:03:01 | 0:03:04 | |
what I know about British pop history is distinctly second-hand. | 0:03:04 | 0:03:09 | |
It's not that I don't like the stuff, it's just that I don't | 0:03:09 | 0:03:12 | |
have stacks of vinyl at home. | 0:03:12 | 0:03:14 | |
And if you spent your youth | 0:03:14 | 0:03:17 | |
throwing up on the King's Road or off your head in a field outside of | 0:03:17 | 0:03:19 | |
Reading, then you know more about British popular music than I do. | 0:03:19 | 0:03:23 | |
But to do what I want to do I don't have to be a fan. | 0:03:23 | 0:03:27 | |
That's because what I want to do is science. | 0:03:27 | 0:03:31 | |
You may wonder why an evolutionary biologist should | 0:03:31 | 0:03:34 | |
decide to study the charts, but just as fruit flies and finches evolve, | 0:03:34 | 0:03:39 | |
so too, I believe, does pop. | 0:03:39 | 0:03:42 | |
Every new song comes with its own burden of mutations. | 0:03:44 | 0:03:48 | |
Some of them bad, but a few of them flourish | 0:03:48 | 0:03:53 | |
and get passed on to future generations. | 0:03:53 | 0:03:55 | |
Listen carefully and you can hear the music evolve. | 0:03:57 | 0:04:01 | |
There are countless examples, but one clear primordial ancestor | 0:04:01 | 0:04:06 | |
is Kraftwerk's Autobahn. | 0:04:06 | 0:04:08 | |
Bit of honking, bit of synthesiser. | 0:04:11 | 0:04:13 | |
The weirdness begins right from the start. | 0:04:16 | 0:04:19 | |
# Fahren, fahren, fahren auf der Autobahn... # | 0:04:19 | 0:04:22 | |
"Bahn, bahn, bahn, autobahn?" | 0:04:22 | 0:04:24 | |
I mean, really. | 0:04:24 | 0:04:26 | |
It must've been the weirdest thing possible when people first heard it. | 0:04:26 | 0:04:30 | |
# Fahren, fahren, fahren auf der Autobahn... # | 0:04:30 | 0:04:33 | |
Think of its glorious weirdness as a musical mutation. | 0:04:33 | 0:04:37 | |
Remember, this was 1974. | 0:04:37 | 0:04:40 | |
Bizarre though it may have been, | 0:04:43 | 0:04:44 | |
Kraftwerk's mutation changed the course of pop evolution. | 0:04:44 | 0:04:49 | |
Three years later, record producer Giorgio Moroder heard it, | 0:04:49 | 0:04:53 | |
absorbed it and put it into a song | 0:04:53 | 0:04:55 | |
that he made for disco's ultimate diva. | 0:04:55 | 0:04:58 | |
It begins very Kraftwerk-like. | 0:04:58 | 0:05:01 | |
MUSIC: I Feel Love by Donna Summer | 0:05:01 | 0:05:03 | |
Driving drum machine. | 0:05:03 | 0:05:04 | |
Synthesisers coming in. | 0:05:06 | 0:05:07 | |
But it's got a different feel, this is dance music. | 0:05:10 | 0:05:12 | |
And then. | 0:05:15 | 0:05:16 | |
# Ooh | 0:05:16 | 0:05:20 | |
# Heaven knows, heaven knows... # | 0:05:20 | 0:05:21 | |
Donna Summer having an orgasm, or at least faking one. | 0:05:21 | 0:05:24 | |
I Feel Love was a glorious synthesis of disco, | 0:05:26 | 0:05:30 | |
early electronica and pure sex. | 0:05:30 | 0:05:33 | |
It was the future. | 0:05:33 | 0:05:35 | |
Moroder's formula would become the basis of electronic dance music | 0:05:36 | 0:05:40 | |
and its innumerable subgenres - | 0:05:40 | 0:05:42 | |
house, techno, | 0:05:42 | 0:05:43 | |
not to mention neurofunk, speedcore and cybergrind. | 0:05:43 | 0:05:47 | |
I have no idea what I'm saying | 0:05:49 | 0:05:52 | |
but I do believe that all genres only exist because musical mutations | 0:05:52 | 0:05:56 | |
are passed from one generation to the next. | 0:05:56 | 0:06:00 | |
And it's that inheritance, that lineage, | 0:06:00 | 0:06:05 | |
which is then transmitted and recombined with other elements. | 0:06:05 | 0:06:10 | |
That is the essence of evolution. | 0:06:10 | 0:06:14 | |
That is how pop music evolves. | 0:06:14 | 0:06:17 | |
MUSIC: Hey Ya! by OutKast | 0:06:17 | 0:06:19 | |
MUSIC: Back In Black by AC/DC | 0:06:19 | 0:06:21 | |
MUSIC: Fame by David Bowie | 0:06:21 | 0:06:24 | |
To me, pop should be a science of diversity and change, | 0:06:24 | 0:06:27 | |
competition and conflict. | 0:06:27 | 0:06:30 | |
MUSIC: Heartbreak Hotel by Elvis Presley | 0:06:30 | 0:06:31 | |
MUSIC: Losing My Religion BY R.E.M. | 0:06:31 | 0:06:33 | |
MUSIC: Toxic by Britney Spears | 0:06:33 | 0:06:36 | |
MUSIC: Royals by Lorde | 0:06:36 | 0:06:41 | |
But if we're going to make it a science, | 0:06:41 | 0:06:43 | |
a Darwinian science, we need to do what scientists do - | 0:06:43 | 0:06:46 | |
experiments. | 0:06:46 | 0:06:48 | |
MUSIC: Blue Monday by New Order | 0:06:48 | 0:06:50 | |
And in my first experiment, | 0:06:51 | 0:06:53 | |
I want to find the musical adaptations that define | 0:06:53 | 0:06:55 | |
pop success today and put all of them into just one song. | 0:06:55 | 0:07:01 | |
But to do that, I'll need a music producer who'll let science | 0:07:01 | 0:07:04 | |
into his studio. | 0:07:04 | 0:07:06 | |
# They took the credit for your second symphony | 0:07:06 | 0:07:09 | |
# Rewritten by machine on new technology | 0:07:09 | 0:07:13 | |
# And now I understand the problems you can see | 0:07:13 | 0:07:16 | |
# Oh, oh... # | 0:07:16 | 0:07:18 | |
Trevor Horn is the man behind some of the catchiest tunes in pop. | 0:07:18 | 0:07:22 | |
From writing songs with The Buggles... | 0:07:22 | 0:07:24 | |
# Video killed the radio star... # | 0:07:24 | 0:07:27 | |
..to producing Seal and Frankie Goes To Hollywood, | 0:07:27 | 0:07:30 | |
he certainly knows how to make a hit, | 0:07:30 | 0:07:33 | |
even if he isn't clear as to how he does it. | 0:07:33 | 0:07:35 | |
Well, it's like those little puzzles, you know, | 0:07:37 | 0:07:39 | |
where you've got to get, like, five balls into a hole. | 0:07:39 | 0:07:43 | |
And you kind of manoeuvre it and you get one into | 0:07:43 | 0:07:45 | |
a hole and then you get a second one in and then you're trying to | 0:07:45 | 0:07:48 | |
get the third one in and the first two pop out. | 0:07:48 | 0:07:51 | |
You know? Trying to get a hit record's a bit like that. | 0:07:51 | 0:07:54 | |
Every time I've ever tried to analyse it and get any sort | 0:07:54 | 0:07:57 | |
of hard and fast rule, it always changes and... | 0:07:57 | 0:08:00 | |
# If I couldn't read you... # | 0:08:00 | 0:08:04 | |
Trevor and I will be working with Nike Jemiyo, | 0:08:04 | 0:08:07 | |
an unsigned singer. | 0:08:07 | 0:08:09 | |
We're going to take one of her songs and try to turn it into a hit. | 0:08:09 | 0:08:13 | |
She seems unconvinced. | 0:08:13 | 0:08:15 | |
I think there's a reason why some songs last for decades. | 0:08:16 | 0:08:21 | |
And I think that's more to do with heart, maybe, than science. Maybe. | 0:08:21 | 0:08:28 | |
Imagine if you had a formula and all you had to do was adhere to | 0:08:30 | 0:08:33 | |
this formula and you could churn out hit records, that would be so funny. | 0:08:33 | 0:08:37 | |
I just can't see it, though. | 0:08:37 | 0:08:38 | |
# Relax don't do it | 0:08:38 | 0:08:41 | |
# When you want to suck it to it | 0:08:41 | 0:08:43 | |
# Relax don't do it | 0:08:43 | 0:08:45 | |
# When you want to come. # | 0:08:46 | 0:08:49 | |
But I intend to bring some analytical firepower to bear | 0:08:49 | 0:08:52 | |
on this problem. | 0:08:52 | 0:08:54 | |
I've put together a team of analysts from the BBC R&D | 0:08:54 | 0:08:58 | |
and from Queen Mary and Oxford universities | 0:08:58 | 0:09:01 | |
and brought them to where I work, | 0:09:01 | 0:09:03 | |
the Data Science Institute at Imperial College London. | 0:09:03 | 0:09:07 | |
So if you look through, I've got, erm... Is there anything in there | 0:09:07 | 0:09:10 | |
we recognise? Oh, there's Saturdays. I've heard of The Saturdays. | 0:09:10 | 0:09:12 | |
We're beginning our analysis with the last six years of chart music. | 0:09:12 | 0:09:16 | |
Who else is in there? Kanye West. | 0:09:16 | 0:09:19 | |
Got some Katy Perry. | 0:09:19 | 0:09:20 | |
So once we've got all the songs together, | 0:09:21 | 0:09:23 | |
what we need to do is to extract the information from them. | 0:09:23 | 0:09:27 | |
In effect, you're asking computers to listen to music. | 0:09:27 | 0:09:30 | |
Erm... | 0:09:30 | 0:09:32 | |
Tim Cowlishaw and Mi Tian | 0:09:32 | 0:09:34 | |
have the job of reducing our songs to numbers. | 0:09:34 | 0:09:37 | |
The basic idea is to turn the music, as something humans can hear, into | 0:09:37 | 0:09:42 | |
machine-understandable data with meaningful information stored in it. | 0:09:42 | 0:09:48 | |
MUSIC: Baby by Justin Bieber | 0:09:48 | 0:09:50 | |
We're recording tempos, what instruments are present | 0:09:50 | 0:09:53 | |
and what pitches are being played and when. | 0:09:53 | 0:09:56 | |
We're even measuring the length and structure of each song. | 0:09:57 | 0:10:01 | |
By the end, we've turned sound waves into this. | 0:10:01 | 0:10:04 | |
These are the raw data of a single song, | 0:10:07 | 0:10:10 | |
the information that makes it - | 0:10:10 | 0:10:13 | |
the DNA of that song, if you will. | 0:10:13 | 0:10:17 | |
We start with more than a million numbers per song | 0:10:18 | 0:10:21 | |
and then distil them down to quantify its essence. | 0:10:21 | 0:10:27 | |
I can't pretend that these numbers mean anything to me. | 0:10:27 | 0:10:31 | |
Most of the features we've measured are hard for humans to interpret. | 0:10:31 | 0:10:35 | |
To a scientist, numbers on this scale, on this magnitude, | 0:10:35 | 0:10:40 | |
are beautiful. | 0:10:40 | 0:10:42 | |
The difficulty comes in knowing what they mean. | 0:10:42 | 0:10:44 | |
MUSIC: Ice Ice Baby by Vanilla Ice | 0:10:44 | 0:10:47 | |
But, in truth, I don't have to know what these numbers mean or | 0:10:47 | 0:10:50 | |
how they relate to what makes a song great. | 0:10:50 | 0:10:52 | |
That's because we live in the age of machine learning. | 0:10:52 | 0:10:56 | |
In the old way of doing science, the kind of science | 0:10:56 | 0:10:59 | |
that I've done all my life, | 0:10:59 | 0:11:02 | |
you look for causal associations between variables, | 0:11:02 | 0:11:07 | |
the way in which one thing that you've measured in the world affects | 0:11:07 | 0:11:11 | |
another, and you've got an explicit hypothesis about how that works. | 0:11:11 | 0:11:16 | |
Machine learning doesn't go like that. | 0:11:16 | 0:11:19 | |
Our computers know a track's success. | 0:11:20 | 0:11:23 | |
They know which songs topped the charts for weeks... | 0:11:23 | 0:11:26 | |
..and which scraped in at number 40. | 0:11:29 | 0:11:32 | |
The machines then sift through our millions of data points. | 0:11:33 | 0:11:37 | |
They're looking for those features that tend to be present in hits | 0:11:37 | 0:11:41 | |
but absent in flops. | 0:11:41 | 0:11:43 | |
The machine learning approach is to measure everything that you | 0:11:45 | 0:11:48 | |
can possibly measure about a song and throw it into the pot | 0:11:48 | 0:11:54 | |
and let the algorithm figure out what makes a hit. | 0:11:54 | 0:11:58 | |
# Shake it off | 0:11:58 | 0:11:59 | |
# Shake it off | 0:11:59 | 0:12:01 | |
# Shake it off | 0:12:01 | 0:12:02 | |
# Shake it off | 0:12:02 | 0:12:04 | |
# Shake it off | 0:12:04 | 0:12:05 | |
# Shake it off | 0:12:05 | 0:12:07 | |
# Shake it off | 0:12:07 | 0:12:08 | |
# Shake it off Oh-oh | 0:12:08 | 0:12:10 | |
# Shake it off... # | 0:12:10 | 0:12:11 | |
It'll take a lot of data-bashing to get any results, | 0:12:11 | 0:12:15 | |
so it's a good time to introduce Trevor to my way of making music. | 0:12:15 | 0:12:18 | |
For all the time that I've spent analysing pop music, | 0:12:19 | 0:12:23 | |
I've never actually met a real live producer, | 0:12:23 | 0:12:25 | |
never mind the man who made the '80s. | 0:12:25 | 0:12:28 | |
# They send the heart police to put you under | 0:12:28 | 0:12:33 | |
# Cardiac arrest... # | 0:12:33 | 0:12:35 | |
-Ah, Armand. -You must be Trevor. | 0:12:35 | 0:12:38 | |
I am. Come in. | 0:12:38 | 0:12:40 | |
-Lovely to meet you. -Nice to meet you. | 0:12:40 | 0:12:42 | |
Come through. | 0:12:43 | 0:12:44 | |
The reason that this kind of study hasn't been done before is | 0:12:46 | 0:12:50 | |
simply because up till now you've not been able to analyse that | 0:12:50 | 0:12:55 | |
-number of songs... -Yeah. -..in a quantitative, scientific way. | 0:12:55 | 0:12:59 | |
-Right. -And I would claim that I, an evolutionary biologist, | 0:12:59 | 0:13:04 | |
know more about popular music... | 0:13:04 | 0:13:06 | |
-Right. -..than anybody up till now. | 0:13:06 | 0:13:08 | |
Well, what exactly are your qualifications... | 0:13:08 | 0:13:10 | |
to be the person that knows the most about pop music? | 0:13:10 | 0:13:13 | |
My PhD was on fruit flies, | 0:13:13 | 0:13:15 | |
I've spent most of my professional life studying worms. | 0:13:15 | 0:13:20 | |
Very important worms, as it so happens. | 0:13:20 | 0:13:22 | |
The reason I claim that I think that I know more is because, | 0:13:22 | 0:13:26 | |
in some ways, precisely because I am ignorant. | 0:13:26 | 0:13:29 | |
-Right. -And because that means that I can just let the numbers talk to me. | 0:13:29 | 0:13:33 | |
'But Trevor's not convinced that the high road to pop stardom | 0:13:33 | 0:13:36 | |
'is paved with data.' | 0:13:36 | 0:13:38 | |
Can I tell you, I have five things that I look at, right? | 0:13:38 | 0:13:42 | |
If you want to be a successful artist, right? | 0:13:42 | 0:13:45 | |
You have to be able to write | 0:13:46 | 0:13:48 | |
or have access to the best material, | 0:13:48 | 0:13:52 | |
you must have a really great voice, two octaves, | 0:13:52 | 0:13:58 | |
you have to have personal charm and charisma... | 0:13:58 | 0:14:04 | |
Computers can't measure personal charm and charisma. | 0:14:04 | 0:14:07 | |
..you have to be physically and mentally strong. OK? | 0:14:07 | 0:14:10 | |
The fifth one is you've got to want it. | 0:14:10 | 0:14:12 | |
OK, forget about making her a star. THEY LAUGH | 0:14:17 | 0:14:20 | |
-But that's what you're up against. -She may well have the qualities. | 0:14:20 | 0:14:23 | |
-Make her a decent record. -Produce her, yeah... | 0:14:23 | 0:14:25 | |
-Yeah. -..a song that could feasibly, plausibly, | 0:14:25 | 0:14:30 | |
be released and not disappear into the void of... | 0:14:30 | 0:14:34 | |
-The void, the black hole of... -The black hole of YouTube. | 0:14:34 | 0:14:37 | |
And if it works, we're going to go in business as a production company. | 0:14:37 | 0:14:41 | |
-Right! -TREVOR LAUGHS | 0:14:41 | 0:14:43 | |
And become...just a hit factory. | 0:14:43 | 0:14:46 | |
MUSIC: Mrs Robinson by Simon & Garfunkel | 0:14:46 | 0:14:49 | |
But we haven't just gathered modern music. | 0:14:49 | 0:14:52 | |
I think we can use my techniques to see how pop | 0:14:52 | 0:14:55 | |
has evolved over the years. | 0:14:55 | 0:14:57 | |
The thing that I love about pop music is that it comes with its | 0:15:00 | 0:15:03 | |
own meticulously-documented fossil record, the UK Official Charts. | 0:15:03 | 0:15:08 | |
We've got the songs for about 50 years and we can study them all. | 0:15:09 | 0:15:13 | |
Just like the modern tracks, | 0:15:16 | 0:15:18 | |
these historic songs have been converted into numbers. | 0:15:18 | 0:15:22 | |
But here we're looking at how the music changed over the years. | 0:15:22 | 0:15:26 | |
Take 50 years of music, 17,916 songs, | 0:15:26 | 0:15:31 | |
turn them into millions of numbers, | 0:15:31 | 0:15:33 | |
boil those numbers down into a single variable | 0:15:33 | 0:15:37 | |
and this is what you get. | 0:15:37 | 0:15:38 | |
This is the rate of evolution of the UK charts | 0:15:40 | 0:15:43 | |
over the last 50 years. | 0:15:43 | 0:15:46 | |
This is what actually happened. | 0:15:47 | 0:15:50 | |
When the red line is high, the music is evolving quickly. | 0:15:50 | 0:15:54 | |
When low, slow. | 0:15:54 | 0:15:55 | |
And when it crosses the yellow line, | 0:15:55 | 0:15:58 | |
that's when the UK charts had a revolution. | 0:15:58 | 0:16:00 | |
And it begins on a high, with a revolution. | 0:16:01 | 0:16:05 | |
Our first revolution is centred around 1964, | 0:16:07 | 0:16:10 | |
the year that gave us a new TV channel... | 0:16:10 | 0:16:13 | |
-ARCHIVE: -BBC Two opening night. | 0:16:13 | 0:16:15 | |
MUSIC: Rockin' Robin by The Hollies | 0:16:15 | 0:16:19 | |
-..pirate radio... -My name's Simon Dee, | 0:16:19 | 0:16:21 | |
with you for the next two hours. | 0:16:21 | 0:16:22 | |
First one off the top of the pile, The Hollies - Rockin' Robin. | 0:16:22 | 0:16:25 | |
..and a pop chart in which musical evolution was in overdrive. | 0:16:26 | 0:16:30 | |
We've forgotten what the sound of the early 1960s was. | 0:16:32 | 0:16:36 | |
It was big, smooth orchestral numbers. | 0:16:36 | 0:16:39 | |
People like Frank Sinatra, Ella Fitzgerald, Connie Francis | 0:16:39 | 0:16:44 | |
were in the charts. | 0:16:44 | 0:16:47 | |
It's like contemplating an age of dinosaurs | 0:16:47 | 0:16:51 | |
before a mass extinction event. | 0:16:51 | 0:16:53 | |
MUSIC: You Really Got Me by The Kinks | 0:16:53 | 0:16:56 | |
It was music for grown-ups | 0:16:56 | 0:16:59 | |
and it was doomed. | 0:16:59 | 0:17:00 | |
# Girl, you really got me goin'... # | 0:17:00 | 0:17:03 | |
And this is the sort of music that swept it away. | 0:17:03 | 0:17:05 | |
This is The Kinks - You Really Got Me. | 0:17:06 | 0:17:10 | |
Dave Davies is the man behind that crunching guitar. | 0:17:10 | 0:17:14 | |
HE PLAYS GUITAR | 0:17:14 | 0:17:15 | |
It's just G and F, you know. | 0:17:15 | 0:17:19 | |
All the different things you can do with G and F. | 0:17:19 | 0:17:21 | |
# You really got me now... # | 0:17:21 | 0:17:24 | |
This was British rock and roll. | 0:17:24 | 0:17:26 | |
# Oh yeah, you really got me now... # | 0:17:26 | 0:17:30 | |
It was loud and sexy, | 0:17:30 | 0:17:32 | |
nothing like the pretty orchestral stuff it replaced. | 0:17:32 | 0:17:35 | |
# You really got me... # | 0:17:35 | 0:17:37 | |
But if you play just the three bottom of notes on guitar... | 0:17:39 | 0:17:42 | |
..sounds bigger | 0:17:46 | 0:17:48 | |
than if it was played like a full chord, which would be... | 0:17:48 | 0:17:52 | |
prettier but... | 0:17:52 | 0:17:53 | |
When you really dig in... | 0:17:56 | 0:17:58 | |
sounds more powerful, sexier. | 0:17:58 | 0:18:01 | |
More aggressive, I guess. | 0:18:03 | 0:18:04 | |
The word aggressive is key. | 0:18:06 | 0:18:08 | |
These songs tend to have fewer harmonies, | 0:18:10 | 0:18:12 | |
stronger rhythms and more thrashing guitars. | 0:18:12 | 0:18:16 | |
So by combining these features into a single variable - | 0:18:18 | 0:18:21 | |
aggression - we can see how the charts have changed. | 0:18:21 | 0:18:24 | |
Aggression rises rapidly in '63, '64, | 0:18:26 | 0:18:31 | |
moving through to '65, | 0:18:31 | 0:18:33 | |
and we can go and look at the artists | 0:18:33 | 0:18:36 | |
that are actually coming in here. | 0:18:36 | 0:18:37 | |
Pretty Things, The Rolling Stones and, of course, The Who. | 0:18:37 | 0:18:40 | |
# You say I've been in prison | 0:18:40 | 0:18:42 | |
# You say I've got a wife... # | 0:18:42 | 0:18:45 | |
The data shows the birth of British beat music, | 0:18:45 | 0:18:48 | |
a musical mutation that swept all before it. | 0:18:48 | 0:18:51 | |
Now, you will surely not be amazed to hear that there was | 0:18:53 | 0:18:56 | |
a pop revolution around '64. | 0:18:56 | 0:18:59 | |
But we've found it just by feeding the songs to a computer. | 0:18:59 | 0:19:04 | |
The thing to remember is that none of this is based upon | 0:19:04 | 0:19:07 | |
the standard cultural mythologies of pop, | 0:19:07 | 0:19:10 | |
the hazy recollections of journalists and rock stars. | 0:19:10 | 0:19:14 | |
This is based upon the music - | 0:19:14 | 0:19:17 | |
the wave forms, the numbers. | 0:19:17 | 0:19:20 | |
MUSIC: Love Me Do by The Beatles | 0:19:20 | 0:19:24 | |
But the numbers conceal a surprise. | 0:19:24 | 0:19:26 | |
# Love, love me do | 0:19:26 | 0:19:29 | |
# You know I love you... # | 0:19:29 | 0:19:31 | |
You may have noticed that I've not mentioned | 0:19:31 | 0:19:33 | |
a certain four-piece that did quite well. | 0:19:33 | 0:19:36 | |
'64 may have been the peak of Beatlemania | 0:19:38 | 0:19:41 | |
but the data suggests that musically they weren't that important. | 0:19:41 | 0:19:46 | |
And none of their charting singles sit high on our plot of aggression. | 0:19:47 | 0:19:52 | |
Love Me Do, right on the average. | 0:19:52 | 0:19:54 | |
Yellow Submarine, right on the average. | 0:19:54 | 0:19:56 | |
Hey Jude, right on the average. | 0:19:56 | 0:19:59 | |
Penny Lane...ah, a little bit below. | 0:19:59 | 0:20:01 | |
It's the hallmark of The Beatles - average. | 0:20:02 | 0:20:05 | |
Who isn't average? | 0:20:06 | 0:20:08 | |
The Kinks aren't average, The Who aren't average, | 0:20:08 | 0:20:11 | |
The Pretty Things aren't average, The Dave Clark Five aren't average, | 0:20:11 | 0:20:14 | |
The Rolling Stones - they're certainly not average. | 0:20:14 | 0:20:18 | |
The London bands are dragging mean aggression up | 0:20:18 | 0:20:22 | |
and transforming the musical landscape. | 0:20:22 | 0:20:25 | |
Meanwhile, Lennon and McCartney | 0:20:25 | 0:20:27 | |
are writing ditties for prepubescent girls. | 0:20:27 | 0:20:29 | |
Now, before you write into Points Of View, | 0:20:31 | 0:20:33 | |
let me be clear. | 0:20:33 | 0:20:35 | |
I'm not saying that the Fab Four weren't culturally important, | 0:20:35 | 0:20:38 | |
that they didn't have winsome personalities and great haircuts. | 0:20:38 | 0:20:42 | |
And I'll even concede that Sgt Pepper may well be the most | 0:20:46 | 0:20:48 | |
influential album of all time. | 0:20:48 | 0:20:51 | |
Or not. | 0:20:51 | 0:20:52 | |
But the fact remains - | 0:20:52 | 0:20:53 | |
The Beatles sat out the British revolution of 1964. | 0:20:53 | 0:20:58 | |
My team are still searching for the numerical ingredients | 0:21:00 | 0:21:03 | |
of a modern pop hit. | 0:21:03 | 0:21:04 | |
PIANO PLAYS | 0:21:04 | 0:21:07 | |
Meanwhile, Trevor's getting his first listen to the song | 0:21:10 | 0:21:13 | |
we'll be working on. | 0:21:13 | 0:21:14 | |
# If I couldn't read you | 0:21:20 | 0:21:22 | |
# The signs say you've moved on | 0:21:23 | 0:21:26 | |
# Cos when we talk and we walk | 0:21:28 | 0:21:30 | |
# Down the lane of memories | 0:21:30 | 0:21:34 | |
# Dive into the ocean with me | 0:21:36 | 0:21:42 | |
# Cos if you stand still... # | 0:21:42 | 0:21:45 | |
The song's called Dive. | 0:21:45 | 0:21:47 | |
Nike wrote it about taking risks to achieve your dreams. | 0:21:47 | 0:21:50 | |
# What we could be. # | 0:21:50 | 0:21:55 | |
Good. | 0:22:06 | 0:22:08 | |
I was going to say, you probably started singing in church, right? | 0:22:08 | 0:22:12 | |
-Yes, I did. -Yeah, I can tell from the sound of the way you're singing. | 0:22:12 | 0:22:15 | |
But, I mean, there's nothing wrong with that, | 0:22:15 | 0:22:17 | |
that's where Dionne Warwick started to sing, church. | 0:22:17 | 0:22:19 | |
You know? It's a great place to learn. | 0:22:19 | 0:22:22 | |
I mean, great place to learn music, anyway. | 0:22:22 | 0:22:25 | |
Yeah, it's a pleasant song, so... | 0:22:25 | 0:22:27 | |
There's loads of people with pleasant songs, | 0:22:27 | 0:22:31 | |
you've got to find some way of getting through all of them, | 0:22:31 | 0:22:33 | |
-you know? But there's a couple of things that we can try. -OK. | 0:22:33 | 0:22:37 | |
And the first thing would be to get the song out of you | 0:22:37 | 0:22:39 | |
with a piano and a click. | 0:22:39 | 0:22:41 | |
OK. | 0:22:41 | 0:22:42 | |
METRONOME CLICKS | 0:22:42 | 0:22:45 | |
PIANO PLAYS | 0:22:45 | 0:22:48 | |
Science can't yet direct a singer to produce a perfect vocal, | 0:22:48 | 0:22:52 | |
so I'm leaving this to Trevor. | 0:22:52 | 0:22:54 | |
# If I couldn't read you | 0:22:54 | 0:22:56 | |
# The signs say you've moved on... # | 0:22:58 | 0:23:01 | |
Stop there. Just one more time. | 0:23:01 | 0:23:04 | |
I think a teeny bit more edge than that, if you can do it. | 0:23:04 | 0:23:07 | |
# Packed your past in a box on a ship | 0:23:07 | 0:23:10 | |
# Sail till dawn. # | 0:23:10 | 0:23:13 | |
Sorry to be a pain, to keep you doing it, but just try... | 0:23:13 | 0:23:15 | |
Can you try it at 65? | 0:23:15 | 0:23:17 | |
# Now you've had your freedom | 0:23:20 | 0:23:22 | |
# You want to stay out in the cold | 0:23:23 | 0:23:27 | |
# You think it's easier | 0:23:27 | 0:23:29 | |
# When you're given much to hold... # | 0:23:29 | 0:23:32 | |
That's good. That's what I meant. | 0:23:34 | 0:23:36 | |
I can't even imagine, like, what the science is going to say | 0:23:38 | 0:23:41 | |
or do to the song but it will definitely be interesting. | 0:23:41 | 0:23:44 | |
# Into the ocean with me | 0:23:44 | 0:23:49 | |
# Cos if you stand still... # | 0:23:49 | 0:23:53 | |
I can't wait to hear what happens when I come back | 0:23:53 | 0:23:55 | |
and what they've done with it. | 0:23:55 | 0:23:57 | |
# What we could be. # | 0:23:57 | 0:24:02 | |
I like the end. That was good. | 0:24:02 | 0:24:05 | |
That was kind of a bit of Minnie Riperton there. | 0:24:05 | 0:24:08 | |
Good. You got through it. | 0:24:08 | 0:24:10 | |
Come here and take five. | 0:24:10 | 0:24:11 | |
Yeah, I think you slowed it down. | 0:24:13 | 0:24:15 | |
Oh, did I? Where do I start to slow down? | 0:24:15 | 0:24:18 | |
At the top. | 0:24:18 | 0:24:19 | |
THEY LAUGH | 0:24:19 | 0:24:21 | |
MUSIC: Can't Get You Out Of My Head by Kylie Minogue | 0:24:21 | 0:24:25 | |
The next job is to see if our analysis can turn Dive | 0:24:27 | 0:24:30 | |
into a chart-topper. | 0:24:30 | 0:24:32 | |
So, what we want to know is, what is the magic ingredient that | 0:24:36 | 0:24:40 | |
makes a pop song a hit, right? | 0:24:40 | 0:24:43 | |
As opposed to a non-hit. | 0:24:43 | 0:24:45 | |
Ben Lambert's been going through the data. | 0:24:46 | 0:24:49 | |
The hope was that through machine learning we'd find musical | 0:24:49 | 0:24:52 | |
features that help us distinguish hits from flops. | 0:24:52 | 0:24:55 | |
But the results are not very promising. | 0:24:56 | 0:24:59 | |
So, 50-50 would be just picking randomly. | 0:25:00 | 0:25:03 | |
And we get an accuracy of about 52% or 53%. | 0:25:03 | 0:25:08 | |
-Right. -So, slightly better than just randomly picking | 0:25:08 | 0:25:11 | |
but, basically, not. | 0:25:11 | 0:25:12 | |
Yeah, it's not exactly an advertisement for machine learning, is it? | 0:25:14 | 0:25:17 | |
-No. -THEY LAUGH | 0:25:17 | 0:25:19 | |
If we can't identify the features that predict the relative | 0:25:19 | 0:25:23 | |
success of a song, then it's really not clear what to tell Trevor. | 0:25:23 | 0:25:27 | |
We run all the models we can think of, we tweak them in all | 0:25:27 | 0:25:31 | |
the different ways we can, we subset the data... | 0:25:31 | 0:25:35 | |
in all kinds of ways... | 0:25:35 | 0:25:37 | |
..and we get nothing. | 0:25:38 | 0:25:40 | |
We can't predict it. | 0:25:40 | 0:25:41 | |
We just don't know what makes a hit. | 0:25:41 | 0:25:44 | |
But there's a faint glimmer of hope, | 0:25:44 | 0:25:47 | |
for we have identified one correlation. | 0:25:47 | 0:25:50 | |
The one thing which we did find, and it's not a very, | 0:25:50 | 0:25:53 | |
very strong signal, but it's a statistically significant signal, | 0:25:53 | 0:25:57 | |
so that's something, is that there's an association | 0:25:57 | 0:26:00 | |
between success in the charts and | 0:26:00 | 0:26:05 | |
how close a song is to the average. | 0:26:05 | 0:26:09 | |
MUSIC: Style by Taylor Swift | 0:26:09 | 0:26:13 | |
Imagine a perfectly average song, | 0:26:13 | 0:26:16 | |
one whose every feature sits at the centre of our distributions. | 0:26:16 | 0:26:20 | |
Our analysis shows that such a song should do better than most. | 0:26:22 | 0:26:26 | |
Of course, none of our songs actually hit that statistical | 0:26:27 | 0:26:31 | |
sweet spot, but we can measure how close they are to it, | 0:26:31 | 0:26:34 | |
and the closer a song gets, the better it seems to do. | 0:26:34 | 0:26:37 | |
Perhaps, then, what we have to tell Trevor | 0:26:41 | 0:26:43 | |
is to simply make Dive really average. | 0:26:43 | 0:26:46 | |
I guess I would say that in all my years as a scientist, | 0:26:47 | 0:26:52 | |
the discovery that the most average song tends to be the most successful | 0:26:52 | 0:27:00 | |
song is one of the more depressing results that I have ever found. | 0:27:00 | 0:27:05 | |
And I fear that Trevor won't like the news. | 0:27:07 | 0:27:11 | |
The thing that I've found that is predictive of success | 0:27:13 | 0:27:16 | |
is how average the music is. | 0:27:16 | 0:27:18 | |
This is a force which is sort of driving music at any given time | 0:27:18 | 0:27:25 | |
to some sort of... | 0:27:25 | 0:27:27 | |
I don't want to call it a lowest common denominator, but sort of | 0:27:27 | 0:27:30 | |
the centre of the distribution, a kind of a homogenising force. | 0:27:30 | 0:27:35 | |
Do you think that there's a certain inevitability about that? | 0:27:35 | 0:27:39 | |
Because we're in a unique position at the moment. | 0:27:39 | 0:27:41 | |
We're in a position that no-one's ever been in before, | 0:27:41 | 0:27:44 | |
where we have at least 50 years of, 60 years, | 0:27:44 | 0:27:49 | |
70 years of recorded music. | 0:27:49 | 0:27:52 | |
We can go back and we can listen to all of this music | 0:27:52 | 0:27:54 | |
-from the '60s, the '50s. -Yes. | 0:27:54 | 0:27:56 | |
Never been able to do that before. | 0:27:56 | 0:27:58 | |
I suspect that Trevor's right. | 0:28:00 | 0:28:02 | |
Today, in a few finger taps, you can hear almost any song | 0:28:02 | 0:28:06 | |
in recorded history. | 0:28:06 | 0:28:08 | |
Perhaps this explains why our algorithms have struggled here. | 0:28:08 | 0:28:12 | |
If modern artists are combining genres promiscuously, | 0:28:12 | 0:28:15 | |
the result will be the songs that are neither one thing nor the other. | 0:28:15 | 0:28:19 | |
But this hasn't always been the case. | 0:28:22 | 0:28:26 | |
Our pop history shows that the charts were once | 0:28:26 | 0:28:28 | |
a bloody battleground in which genres vied for supremacy. | 0:28:28 | 0:28:32 | |
We are back at our rate of evolution plot and you can | 0:28:32 | 0:28:36 | |
see that the rate at which the music is changing in the charts | 0:28:36 | 0:28:40 | |
begins to pick up in the 1970s. | 0:28:40 | 0:28:43 | |
Around 1975 it crosses the line, we are into a revolution. | 0:28:43 | 0:28:47 | |
It peaks in the late 1970s, | 0:28:47 | 0:28:51 | |
when the music is changing with maximum speed. | 0:28:51 | 0:28:54 | |
This revolution is going to become | 0:28:54 | 0:28:57 | |
one of the most important in the history of British pop. | 0:28:57 | 0:29:01 | |
When this revolution came, the country seemed half asleep. | 0:29:07 | 0:29:11 | |
The UK was a sea of brown, orange and mustard. | 0:29:11 | 0:29:14 | |
But something was stirring in the pop charts. | 0:29:15 | 0:29:18 | |
# I am an antichrist | 0:29:18 | 0:29:22 | |
# And I am an anarchist... # | 0:29:22 | 0:29:25 | |
Ask a Brit of a certain age what happened in the late 1970s | 0:29:25 | 0:29:29 | |
and chances are he'll say, "Well, mate, it was all about punk." | 0:29:29 | 0:29:34 | |
There's no doubt that punk rock's cultural impact was immense, | 0:29:35 | 0:29:41 | |
so much so that it's easy to forget just how tiny it all was. | 0:29:41 | 0:29:49 | |
MUSIC: No Future by Sex Pistols | 0:29:49 | 0:29:53 | |
Safety pins, spiky hair, spittle and swearing on national TV. | 0:29:53 | 0:29:59 | |
Punk grabbed all of the headlines. | 0:29:59 | 0:30:01 | |
Go on, you've got another five seconds, says something outrageous. | 0:30:01 | 0:30:04 | |
-You dirty -BLEEP. | 0:30:04 | 0:30:06 | |
-Go on, again. -You dirty -BLEEP. | 0:30:06 | 0:30:08 | |
-What a clever boy(!) -BLEEP. | 0:30:08 | 0:30:09 | |
But that's not the same as making music that mattered. | 0:30:09 | 0:30:12 | |
This is a network of musical relationships | 0:30:16 | 0:30:19 | |
between some 800 artists, | 0:30:19 | 0:30:22 | |
pretty much everybody who charted in the UK in the 1970s. | 0:30:22 | 0:30:26 | |
And it's based upon the music as measured by our computer | 0:30:26 | 0:30:31 | |
and you can see that the relationships it gives make sense. | 0:30:31 | 0:30:35 | |
The more songs of a particular genre, | 0:30:36 | 0:30:38 | |
the bigger the block of colour. | 0:30:38 | 0:30:40 | |
Up here, for example, we have funk and disco, | 0:30:40 | 0:30:44 | |
they are all grouping together. | 0:30:44 | 0:30:46 | |
Up here, we have vast swathes of soft pop. | 0:30:46 | 0:30:49 | |
James Taylor, Joan Baez, Gordon Lightfoot, people like that. | 0:30:49 | 0:30:54 | |
And down here, in yellow, we've got punk. | 0:30:54 | 0:30:59 | |
And there's not very much of it. | 0:30:59 | 0:31:02 | |
In the entire 1970s, only about 68 songs that could be called punk | 0:31:02 | 0:31:07 | |
by any reasonable definition charted. | 0:31:07 | 0:31:10 | |
MUSIC: Hersham Boys by Sham 69 | 0:31:10 | 0:31:12 | |
There just wasn't enough punk to have had a significant impact | 0:31:12 | 0:31:15 | |
upon the evolution of the UK charts. | 0:31:15 | 0:31:18 | |
So what was changing pop? | 0:31:18 | 0:31:20 | |
In the '70s, we see songs becoming faster. | 0:31:22 | 0:31:24 | |
MUSIC: We Are Family by Sister Sledge | 0:31:24 | 0:31:25 | |
And more percusso. | 0:31:25 | 0:31:27 | |
Again, by combining features | 0:31:27 | 0:31:29 | |
we create a new variable, rhythmic intensity. | 0:31:29 | 0:31:32 | |
It's the thing that changes in the 1970s. | 0:31:32 | 0:31:36 | |
It begins to increase in 1972, | 0:31:36 | 0:31:38 | |
climbs rapidly, peaks in 1979. | 0:31:38 | 0:31:42 | |
Whatever's changing in the 1970s isn't punk, it's not rock, | 0:31:42 | 0:31:48 | |
it's something else and it's coming from America. | 0:31:48 | 0:31:50 | |
# We are family | 0:31:50 | 0:31:54 | |
# I've got all my sisters with me... # | 0:31:54 | 0:31:56 | |
It started as a funk invasion | 0:31:56 | 0:31:58 | |
but quickly morphed into the music of glitter balls and flairs. | 0:31:58 | 0:32:02 | |
# Get up everybody and sing... # | 0:32:02 | 0:32:05 | |
Disco may have started in the black and gay clubs of New York City... | 0:32:05 | 0:32:08 | |
MUSIC: Stayin' Alive by Bee Gees | 0:32:08 | 0:32:11 | |
..but in the UK, it was Saturday Night Fever | 0:32:11 | 0:32:13 | |
that sent it stratospheric. | 0:32:13 | 0:32:16 | |
And the irresistible grooves of the Bee Gees ruled the charts. | 0:32:16 | 0:32:20 | |
You can hear, you can feel, you can see | 0:32:22 | 0:32:27 | |
and we can measure that rhythmic intensity, that driving beat. | 0:32:27 | 0:32:32 | |
The data are unambiguous - | 0:32:34 | 0:32:36 | |
a tidal wave of disco flooded the charts | 0:32:36 | 0:32:38 | |
with pulsating four-on-the-floor rhythms. | 0:32:38 | 0:32:42 | |
Punk arose, flourished and vanished in almost an instant. | 0:32:42 | 0:32:46 | |
So why does punk rock seem to matter so much? | 0:32:48 | 0:32:51 | |
I think it's a combination of British chauvinism, nostalgia, | 0:32:51 | 0:32:56 | |
Johnny Lydon's charisma and Vivienne Westwood's clothes. | 0:32:56 | 0:33:00 | |
But the fact of the matter is that as far as the music is concerned, | 0:33:00 | 0:33:06 | |
it was never that special. | 0:33:06 | 0:33:07 | |
# If I choose to believe... # | 0:33:07 | 0:33:10 | |
-MUSIC REWINDS -# If I choose to believe you... # | 0:33:10 | 0:33:12 | |
MUSIC REWINDS | 0:33:12 | 0:33:13 | |
# If I choose to believe... # | 0:33:13 | 0:33:15 | |
Trevor's working with arranger Julian Hinton. | 0:33:15 | 0:33:18 | |
# Dive into the ocean... # | 0:33:18 | 0:33:19 | |
Their first job is to produce Nike's song as they normally would. | 0:33:19 | 0:33:23 | |
This is more of an organic feel so, because of the nature of the song, | 0:33:23 | 0:33:28 | |
it's got a lot more emotion to it, | 0:33:28 | 0:33:30 | |
it needs to have an ebb and flow. | 0:33:30 | 0:33:32 | |
That's why I am being more painstaking. | 0:33:32 | 0:33:35 | |
I'm going into a lot more detail | 0:33:36 | 0:33:38 | |
so that hopefully it retains its performance | 0:33:38 | 0:33:41 | |
and be the best version of what is essentially there. | 0:33:41 | 0:33:44 | |
I'm not trying to... | 0:33:44 | 0:33:46 | |
fix or change the character of it. | 0:33:46 | 0:33:48 | |
The song is a ballad, so they're putting luscious strings | 0:33:50 | 0:33:53 | |
underneath it. | 0:33:53 | 0:33:54 | |
Whether they be from a keyboard or from an orchestra | 0:33:54 | 0:33:58 | |
they're a very, very warm and expressive sound, | 0:33:58 | 0:34:03 | |
probably one of the... | 0:34:03 | 0:34:04 | |
Strings are probably one of the most expressive things | 0:34:04 | 0:34:07 | |
other than the voice. | 0:34:07 | 0:34:08 | |
# Dive into the ocean with me | 0:34:14 | 0:34:20 | |
# I know there's danger | 0:34:20 | 0:34:23 | |
# But this time I'm braver | 0:34:23 | 0:34:27 | |
# Dive into the ocean with me... # | 0:34:29 | 0:34:34 | |
-See just that bit there? -MUSIC STOPS | 0:34:34 | 0:34:37 | |
-The dive, can you just make it dive at the right time? -Mm. | 0:34:37 | 0:34:40 | |
He's hitting the water too late. | 0:34:40 | 0:34:42 | |
# Dive into the ocean with me | 0:34:42 | 0:34:47 | |
# I know there's danger | 0:34:48 | 0:34:52 | |
# But this time I'm braver... # | 0:34:52 | 0:34:56 | |
'With Trevor happy, it's time for me to see if I can get | 0:34:57 | 0:35:00 | |
'Dive's features as close to the average as possible.' | 0:35:00 | 0:35:03 | |
-Hi, guys. -Hi. | 0:35:03 | 0:35:04 | |
'But to do that, we need a point of reference. | 0:35:04 | 0:35:07 | |
'We need to hear some songs that our data show really are average.' | 0:35:07 | 0:35:12 | |
-Oh, yeah, it's G-Eazy featuring... -Featuring Bebe Rexha. | 0:35:12 | 0:35:15 | |
-Featuring Bebe Rexha. -Yeah. | 0:35:15 | 0:35:17 | |
MUSIC: Me, Myself & I by G-Eazy and featuring Bebe Rexha | 0:35:17 | 0:35:20 | |
Yeah. | 0:35:20 | 0:35:22 | |
There's some sonic things going on, | 0:35:22 | 0:35:24 | |
-there's a very electronic percussion. -Yep. | 0:35:24 | 0:35:27 | |
And a very crisp electronic high-end as well, which is copied | 0:35:27 | 0:35:31 | |
from one track to the next and is a really classic pop structure. | 0:35:31 | 0:35:37 | |
MUSIC: You Don't Own Me by Grace | 0:35:37 | 0:35:39 | |
Next up, Grace's You Don't Own Me. | 0:35:39 | 0:35:42 | |
-Exactly. -Now here we've got a blossoming, | 0:35:42 | 0:35:44 | |
very overtly uplifting sonic here. | 0:35:44 | 0:35:49 | |
-It's got a '50s sound and it's got an '80s, '90s sound... -Yep. | 0:35:49 | 0:35:52 | |
..and all kinds of other things in between in terms of, | 0:35:52 | 0:35:55 | |
"Ooh, I can hear '70s influenced drums | 0:35:55 | 0:35:58 | |
"or some strings from the 1950s going on in there." | 0:35:58 | 0:36:01 | |
As Trevor predicted, our average songs seem to be a mix of everything | 0:36:01 | 0:36:05 | |
that's gone before. | 0:36:05 | 0:36:07 | |
In order for that track to become successful, | 0:36:07 | 0:36:10 | |
people have got to be OK with all those sounds and textures. | 0:36:10 | 0:36:13 | |
We come to a place of unbelievably... | 0:36:13 | 0:36:16 | |
believable open-mindedness, actually. | 0:36:16 | 0:36:18 | |
# Dive into the ocean with me... # | 0:36:18 | 0:36:22 | |
'The current charts are a homogenised blend of earlier genres. | 0:36:23 | 0:36:28 | |
'That suggests that we need to make Nike's song...' | 0:36:28 | 0:36:32 | |
Nice. | 0:36:32 | 0:36:33 | |
'..into a mishmash of them.' | 0:36:33 | 0:36:36 | |
If I take that down to the original... | 0:36:36 | 0:36:38 | |
-DRUMS PLAY -# Dive into the ocean with me... # | 0:36:38 | 0:36:43 | |
It doesn't work... | 0:36:43 | 0:36:46 | |
in that style. | 0:36:46 | 0:36:47 | |
Let's take it up even more. | 0:36:47 | 0:36:49 | |
-TRACK PLAYS FASTER -# This time I'm braver... # | 0:36:49 | 0:36:51 | |
Now we're into sort of... It feels more like a remix. | 0:36:51 | 0:36:54 | |
'But although we can estimate an average, | 0:36:54 | 0:36:57 | |
'it's quite hard to define it musically.' | 0:36:57 | 0:37:00 | |
TRACK PLAYS | 0:37:00 | 0:37:02 | |
So that's the other groove I have. | 0:37:02 | 0:37:04 | |
# Dive into the ocean with me... # | 0:37:04 | 0:37:06 | |
I'm hearing, sort of, mid-Madonna, a little bit there. | 0:37:06 | 0:37:10 | |
'The features themselves are hard to interpret, | 0:37:10 | 0:37:12 | |
'so to find the centre of the charts, we have to experiment.' | 0:37:12 | 0:37:16 | |
One of the things that a lot of the average tracks have, | 0:37:16 | 0:37:22 | |
and I think this is precisely why they're average, | 0:37:22 | 0:37:25 | |
is that they have this combination of a big melodic segment | 0:37:25 | 0:37:28 | |
and then you've got a... Let's say pop dude, sort of, who comes in, | 0:37:28 | 0:37:32 | |
does a bunch of rap. | 0:37:32 | 0:37:34 | |
Can you give Nike's song that? | 0:37:34 | 0:37:36 | |
In other words... | 0:37:36 | 0:37:37 | |
can we get a rap in there? | 0:37:37 | 0:37:38 | |
Jul? | 0:37:40 | 0:37:41 | |
HE LAUGHS | 0:37:41 | 0:37:43 | |
I'm sorry, | 0:37:43 | 0:37:44 | |
are you just googling "rap a cappella edify bmp"? | 0:37:44 | 0:37:47 | |
And I have 118,000 hits. | 0:37:47 | 0:37:51 | |
RAP PLAYS ON COMPUTER | 0:37:51 | 0:37:54 | |
Er... | 0:37:54 | 0:37:56 | |
-RAPS: -# So many people give their religion | 0:37:56 | 0:37:58 | |
# The music and church let you know how you're livin'... # | 0:37:58 | 0:38:01 | |
'Now this is Crash DDZ, a rapper from Kentucky.' | 0:38:01 | 0:38:06 | |
DRUMS PLAY | 0:38:07 | 0:38:09 | |
# Everything happens for a reason... # | 0:38:09 | 0:38:13 | |
HE LAUGHS | 0:38:13 | 0:38:15 | |
Who's controlling this, by the way? Is it you or you? | 0:38:17 | 0:38:20 | |
-That was a collaboration, actually. -That was a collaboration. | 0:38:20 | 0:38:23 | |
-Seriously? -A classic production collaboration. | 0:38:23 | 0:38:25 | |
# We can sense our defences come down so easily | 0:38:25 | 0:38:30 | |
-RAPS: -# Man would stand, guitar in his hand | 0:38:30 | 0:38:33 | |
# Recording artists, the history, tell us, travelling bands | 0:38:33 | 0:38:36 | |
# Travelling bands, Johnny Cash and clones... # | 0:38:36 | 0:38:39 | |
'In a few mouse clicks, and for 1, | 0:38:39 | 0:38:42 | |
'we had a rap to pair with Nike's vocals.' | 0:38:42 | 0:38:44 | |
This is going to be one happy rapper. | 0:38:46 | 0:38:49 | |
Until we measure Dive, we won't know how close we've got to our goal | 0:38:49 | 0:38:53 | |
of making its features average. | 0:38:53 | 0:38:56 | |
So it's not clear how useful my analysis will be. | 0:38:56 | 0:39:00 | |
# Dive into the ocean with me... # | 0:39:00 | 0:39:02 | |
'But what is clear is that music production | 0:39:02 | 0:39:04 | |
'is already very reliant upon technology.' | 0:39:04 | 0:39:07 | |
The tools that these guys are using, high-end computers, | 0:39:09 | 0:39:13 | |
various kinds of programmes, different kinds of algorithms, | 0:39:13 | 0:39:16 | |
they're utterly familiar to me and yet their product, | 0:39:16 | 0:39:19 | |
the things that come out of this stuff, it's... | 0:39:19 | 0:39:24 | |
Well, it's like magic. | 0:39:24 | 0:39:25 | |
And there's no doubt that the influence of technology | 0:39:27 | 0:39:30 | |
on the last three decades of the pop charts has been immense. | 0:39:30 | 0:39:34 | |
But it doesn't show up in our data where you might expect. | 0:39:34 | 0:39:38 | |
We've seen a revolution in the 1960s, British rock and roll. | 0:39:38 | 0:39:42 | |
We've seen another revolution in the 1970s, | 0:39:42 | 0:39:45 | |
the rise of disco and funk. But what about the 1980s? | 0:39:45 | 0:39:49 | |
The music's changing, it's always changing, | 0:39:49 | 0:39:53 | |
it's not just changing very fast | 0:39:53 | 0:39:55 | |
and there's nothing resembling a revolution. | 0:39:55 | 0:39:58 | |
MUSIC: Take On Me by A-ha | 0:39:58 | 0:40:01 | |
This may be a surprise - the 1980s was the decade of A-ha... | 0:40:01 | 0:40:05 | |
MUSIC: Karma Chameleon by Culture Club | 0:40:06 | 0:40:09 | |
..Culture Club... | 0:40:09 | 0:40:11 | |
MUSIC: Never Gonna Give You Up by Rick Astley | 0:40:11 | 0:40:15 | |
..and, of course, Rick Astley. | 0:40:15 | 0:40:18 | |
But while there was no pop revolution in the '80s, | 0:40:20 | 0:40:23 | |
I do think that it contained the seeds | 0:40:23 | 0:40:25 | |
of the greatest revolution of them all... | 0:40:25 | 0:40:28 | |
..the rise of the machines. | 0:40:30 | 0:40:32 | |
As soon as technology came along, you could dream something, | 0:40:35 | 0:40:38 | |
you could make it happen, you know? | 0:40:38 | 0:40:41 | |
If you sort of dreamt something | 0:40:41 | 0:40:43 | |
and you tried to make it happen in the '70s, it was harder | 0:40:43 | 0:40:46 | |
because you had to get people to play it. | 0:40:46 | 0:40:47 | |
In the wake of Kraftwerk's pioneering electronica, | 0:40:51 | 0:40:54 | |
the '80s and '90s brought the arrival of increasingly versatile | 0:40:54 | 0:40:58 | |
drum machines and synthesisers. | 0:40:58 | 0:41:00 | |
In a few clicks, producers could make any sound they wanted. | 0:41:02 | 0:41:05 | |
So where is tech's influence on the evolution of pop? | 0:41:06 | 0:41:09 | |
We just need to plot our data in a different way. | 0:41:11 | 0:41:16 | |
If we take 17,916 songs - all of the songs in our data | 0:41:16 | 0:41:21 | |
over the history of the UK charts - and plot them | 0:41:21 | 0:41:24 | |
on a single graph of rhythmic intensity, | 0:41:24 | 0:41:27 | |
what we see is something that looks like this. | 0:41:27 | 0:41:30 | |
The key to this plot is the vertical range of music | 0:41:30 | 0:41:33 | |
at any given point in time. | 0:41:33 | 0:41:35 | |
That tells us how much rhythmic variety is in the charts. | 0:41:36 | 0:41:39 | |
We begin in the 1960s. Down here we've got low-intensity stuff, | 0:41:39 | 0:41:44 | |
Shirley Bassey. | 0:41:44 | 0:41:45 | |
Up here, Chubby Checker. | 0:41:45 | 0:41:48 | |
They sound very different but the range is relatively small. | 0:41:48 | 0:41:53 | |
We move along. | 0:41:53 | 0:41:54 | |
The average is changing but that's not actually the big story here. | 0:41:54 | 0:41:59 | |
As we progress into the early '80s, | 0:41:59 | 0:42:03 | |
we start seeing a new world of high-intensity music. | 0:42:03 | 0:42:08 | |
This is electronica, Kraftwerk, | 0:42:08 | 0:42:10 | |
Cabaret Voltaire, Bam Bam, | 0:42:10 | 0:42:14 | |
dance music, house, techno, | 0:42:14 | 0:42:17 | |
all this stuff is coming in and it expands even further. | 0:42:17 | 0:42:21 | |
This expanding space is the third great story in our history of pop. | 0:42:25 | 0:42:29 | |
It's the relentless advance of electronic dance music. | 0:42:30 | 0:42:34 | |
DJ Annie Mac explains why she thinks it's so successful. | 0:42:35 | 0:42:39 | |
It's the collective experience of 100, | 0:42:40 | 0:42:44 | |
1,000 people standing on a floor... | 0:42:44 | 0:42:47 | |
# The weekend is coming up... # | 0:42:47 | 0:42:49 | |
..all experiencing the same thing. | 0:42:49 | 0:42:51 | |
That kind of physical collective experience | 0:42:51 | 0:42:55 | |
is a very beautiful thing. | 0:42:55 | 0:42:57 | |
If you say so. | 0:42:58 | 0:42:59 | |
But the most striking thing is how many sub genres dance has spawned. | 0:43:03 | 0:43:08 | |
House, techno, funky, grime, | 0:43:08 | 0:43:12 | |
drum and bass, jungle, hard-core, break beat, big beat. | 0:43:12 | 0:43:17 | |
Liquid drum and bass, progressive house. | 0:43:19 | 0:43:22 | |
And it's easy to see why this diversity flourished. | 0:43:22 | 0:43:25 | |
I would say technology is definitely a massive reason for | 0:43:25 | 0:43:29 | |
why dance music, electronic music has been so prone to expansion | 0:43:29 | 0:43:34 | |
and evolution and fragmentation. | 0:43:34 | 0:43:35 | |
It's one of the most exciting things, I think, | 0:43:35 | 0:43:38 | |
about electronic music. | 0:43:38 | 0:43:39 | |
# Dive into the ocean with me | 0:43:42 | 0:43:47 | |
# I know there's danger... # | 0:43:47 | 0:43:49 | |
Back in the studio and we're still trying to make Dive truly average, | 0:43:49 | 0:43:54 | |
a song that mashes everything together | 0:43:54 | 0:43:55 | |
to sit at the statistical centre of the charts. | 0:43:55 | 0:43:59 | |
And we think we need a fair chunk of dance intensity. | 0:43:59 | 0:44:02 | |
-How much bass have you guys put on this thing? -How much bass? | 0:44:04 | 0:44:07 | |
Yeah. | 0:44:07 | 0:44:09 | |
I mean... | 0:44:09 | 0:44:11 | |
is it the case that we can push this towards more of a dance song? | 0:44:11 | 0:44:15 | |
That's really the nub of the problem. | 0:44:15 | 0:44:17 | |
This is a ballad and ballads are a completely different thing and, | 0:44:17 | 0:44:22 | |
you know, if you think about the best dance songs of all time, | 0:44:22 | 0:44:26 | |
-say something like Boogie Wonderland by Earth, Wind & Fire... -Yep. | 0:44:26 | 0:44:30 | |
..the tune in the verse is all off the beat. | 0:44:30 | 0:44:33 | |
HE SINGS THE MELODY OF BOOGIE WONDERLAND | 0:44:33 | 0:44:36 | |
It's all off the beat and it dances on top of the track. | 0:44:36 | 0:44:40 | |
Most dance songs don't start out life as ballads, you know? | 0:44:40 | 0:44:44 | |
We're going to try one last push to make Nike's song really, | 0:44:44 | 0:44:48 | |
really average. | 0:44:48 | 0:44:50 | |
# Dive into the ocean with me... # | 0:44:50 | 0:44:54 | |
We've even brought her back to do a fresh, faster vocal. | 0:44:54 | 0:44:57 | |
# But this time I'm braver... # | 0:44:57 | 0:45:01 | |
-Given that you have a math degree from Imperial College... -Yes. | 0:45:01 | 0:45:07 | |
..can you imagine just... | 0:45:07 | 0:45:08 | |
..setting yourself up as a music analyst from now on? | 0:45:10 | 0:45:13 | |
You know, every song you write, it's just going to be, | 0:45:13 | 0:45:16 | |
"Hmm, a little standard deviation away from the mean, | 0:45:16 | 0:45:19 | |
"got to move in there." | 0:45:19 | 0:45:22 | |
Well, maybe we'll see how this works. | 0:45:22 | 0:45:24 | |
Yes, I think perhaps we should. | 0:45:24 | 0:45:27 | |
If it works then maybe. | 0:45:27 | 0:45:29 | |
DANCE VERSION OF DIVE PLAYS | 0:45:29 | 0:45:31 | |
'We've created a few versions of Dive in the hope | 0:45:31 | 0:45:34 | |
'that one will stick closely to the chart average, | 0:45:34 | 0:45:37 | |
'our key to pop success. | 0:45:37 | 0:45:39 | |
'But some versions just don't work.' | 0:45:39 | 0:45:42 | |
All right... | 0:45:42 | 0:45:43 | |
-MUSIC STOPS -Enough. | 0:45:43 | 0:45:45 | |
Yeah, we can only apologise to Nike, for doing that to her song. | 0:45:45 | 0:45:49 | |
No, but I would... | 0:45:49 | 0:45:51 | |
'Using data to make a hit is proving to be a challenge.' | 0:45:51 | 0:45:54 | |
But I've got another idea. | 0:45:56 | 0:45:57 | |
Thanks to the rise of technology, | 0:45:59 | 0:46:01 | |
we now live in a world of bedroom producers. | 0:46:01 | 0:46:04 | |
There's an ocean of undiscovered artists out there, | 0:46:04 | 0:46:07 | |
and some of them might even be competent. | 0:46:07 | 0:46:10 | |
Can algorithms find the stars of the future? | 0:46:15 | 0:46:18 | |
It's time for another experiment. | 0:46:18 | 0:46:20 | |
And to conduct it, I don't need to go far. | 0:46:20 | 0:46:22 | |
That's because the BBC is home to Introducing, | 0:46:23 | 0:46:26 | |
a website to which unsigned artists can upload their music, | 0:46:26 | 0:46:30 | |
music that we can analyse. | 0:46:30 | 0:46:32 | |
What I have here is a hard drive containing 1,786 songs. | 0:46:35 | 0:46:39 | |
This is the raw material of evolution, | 0:46:39 | 0:46:43 | |
unfiltered by any company or broadcaster | 0:46:43 | 0:46:47 | |
or any consideration of taste other than the musicians' own. | 0:46:47 | 0:46:50 | |
And what we want to know is, is any of it any good? | 0:46:51 | 0:46:56 | |
Normally each track is vetted by a human being | 0:46:56 | 0:46:59 | |
but I suspect that machines can do their job just as well. | 0:46:59 | 0:47:03 | |
What we do is we teach the computer, using a machine-learning algorithm, | 0:47:03 | 0:47:08 | |
what the charts are now | 0:47:08 | 0:47:11 | |
and then we apply that model to the Introducing data | 0:47:11 | 0:47:15 | |
and we ask which of the Introducing songs are most chart-like, | 0:47:15 | 0:47:20 | |
which does the computer think are most likely to go into the charts? | 0:47:20 | 0:47:24 | |
As before, our computers measure each song. | 0:47:27 | 0:47:30 | |
HE MUTTERS | 0:47:30 | 0:47:32 | |
'This is the same process we went through | 0:47:32 | 0:47:34 | |
'for all the chart music earlier on,' | 0:47:34 | 0:47:36 | |
it's just sort of MP3 files go in one end | 0:47:36 | 0:47:38 | |
and spreadsheets come out the other. | 0:47:38 | 0:47:41 | |
The result, a simple list with the most chart-like songs at the top. | 0:47:41 | 0:47:46 | |
Out of all those songs, our algorithm picked one. | 0:47:46 | 0:47:52 | |
And it's a song called Margarita by a group called The Modern Strangers. | 0:47:52 | 0:47:58 | |
The Modern Strangers were actually soon to play a gig in London. | 0:48:01 | 0:48:05 | |
So, two weeks later, | 0:48:06 | 0:48:07 | |
I found myself heading to a dingy club to hear them. | 0:48:07 | 0:48:11 | |
Margarita was the finale. | 0:48:13 | 0:48:16 | |
# Sit back, Margarita | 0:48:16 | 0:48:19 | |
# Nice and slow | 0:48:19 | 0:48:22 | |
# Oooh | 0:48:22 | 0:48:24 | |
# Baby, all I ever wanted was your love | 0:48:24 | 0:48:31 | |
# Ooh... # | 0:48:31 | 0:48:32 | |
Catchy. It certainly had people dancing. | 0:48:32 | 0:48:35 | |
# Sit back, Margarita... # | 0:48:43 | 0:48:47 | |
It's the first time I've really listened to the song. | 0:48:47 | 0:48:50 | |
The computer just gave us a name. | 0:48:50 | 0:48:53 | |
None of us had actually heard the thing. | 0:48:53 | 0:48:57 | |
And I've got to say, it's amazingly convincing. | 0:48:57 | 0:49:01 | |
Margarita is almost an old school disco track - | 0:49:07 | 0:49:11 | |
it comes straight in with a big beat and melodical. | 0:49:11 | 0:49:15 | |
The lyrics may be lacking but it's very, very danceable. | 0:49:20 | 0:49:25 | |
The computer is dumb. | 0:49:28 | 0:49:29 | |
It doesn't have a sophisticated model of beauty | 0:49:31 | 0:49:35 | |
or danceability. | 0:49:35 | 0:49:38 | |
But here's the thing - this song is great. | 0:49:38 | 0:49:41 | |
And people think it's great. | 0:49:41 | 0:49:44 | |
It seems to have bottled some musical magic. | 0:49:44 | 0:49:48 | |
And our computer algorithm has found that same magic, it's... | 0:49:49 | 0:49:56 | |
It shows that it can be bottled by math. | 0:49:58 | 0:50:01 | |
And that's rather amazing. | 0:50:01 | 0:50:03 | |
# Baby, all I ever wanted was your love | 0:50:03 | 0:50:09 | |
# Ooh. # | 0:50:09 | 0:50:13 | |
Thank you very much for having us! Have a good evening. | 0:50:13 | 0:50:16 | |
But every experiment needs a control. | 0:50:18 | 0:50:21 | |
BBC Music Introducing in Kent with Abbie McCarthy. | 0:50:21 | 0:50:26 | |
Good evening, it's after eight o'clock... | 0:50:26 | 0:50:28 | |
I want to pit my algorithm against some human competition. | 0:50:28 | 0:50:31 | |
..right here in Kent. | 0:50:31 | 0:50:33 | |
Abbie McCarthy is the Introducing DJ at BBC Radio Kent. | 0:50:34 | 0:50:39 | |
We get sent probably about 300 tracks a week, | 0:50:39 | 0:50:42 | |
so there's lots of music to listen through, | 0:50:42 | 0:50:44 | |
and then we're just looking for a song that really stands out, | 0:50:44 | 0:50:46 | |
whether that it's really well produced, | 0:50:46 | 0:50:48 | |
it's got a really good beat to it. | 0:50:48 | 0:50:50 | |
# I am scared... # | 0:50:50 | 0:50:51 | |
Then sometimes we have a moment where we're like, | 0:50:51 | 0:50:54 | |
"Wow, this song's really, really incredible." | 0:50:54 | 0:50:57 | |
# Oh-oh-oh... # | 0:50:57 | 0:51:00 | |
Abbie's also picked a song - Gold by singer-songwriter Shells. | 0:51:00 | 0:51:04 | |
I'm going to play both her choice and mine to Rhys Hughes, | 0:51:07 | 0:51:10 | |
the head of programming at Radio 1. | 0:51:10 | 0:51:13 | |
Now, it's not going to be a proper experiment, | 0:51:13 | 0:51:15 | |
but if I played you two songs, would you warrant that you could | 0:51:15 | 0:51:17 | |
pick out the one that Abbie picked and the one that the machine picked? | 0:51:17 | 0:51:21 | |
I've got a 50% chance, haven't I? | 0:51:21 | 0:51:23 | |
You do, that's why it's not a very good experiment but... | 0:51:23 | 0:51:25 | |
Song number one. | 0:51:25 | 0:51:27 | |
MUSIC: Margarita by The Modern Strangers | 0:51:27 | 0:51:30 | |
# Sit back, Margarita | 0:51:30 | 0:51:33 | |
# Nice and slow... # | 0:51:33 | 0:51:34 | |
Get the idea? | 0:51:34 | 0:51:36 | |
-Get the idea? -Yeah. | 0:51:36 | 0:51:38 | |
Next up, Abbie's song. | 0:51:38 | 0:51:39 | |
MUSIC: Gold by Shells | 0:51:39 | 0:51:43 | |
# Oh, oh, oh | 0:51:43 | 0:51:46 | |
# Oh, everybody's made of gold | 0:51:46 | 0:51:50 | |
# So put me in black and white... # | 0:51:50 | 0:51:53 | |
MUSIC STOPS | 0:51:53 | 0:51:54 | |
One of those two songs, Margarita and Shells, was chosen by computer, | 0:51:54 | 0:51:58 | |
the other one by DJ. | 0:51:58 | 0:52:01 | |
Which was which? | 0:52:01 | 0:52:02 | |
I would say the computer picked the second one you've played. | 0:52:04 | 0:52:10 | |
Wrong. The computer picked Modern Strangers, it picked the first one. | 0:52:10 | 0:52:13 | |
-Right, OK. -Yeah? | 0:52:13 | 0:52:15 | |
So you have to concede that at least our algorithm | 0:52:15 | 0:52:18 | |
is doing as well as a DJ. | 0:52:18 | 0:52:20 | |
What do you say to just ditching them all and replacing them | 0:52:20 | 0:52:23 | |
with a computer? | 0:52:23 | 0:52:24 | |
I don't think an algorithm would've picked out a Bob Dylan, | 0:52:24 | 0:52:27 | |
I don't think an algorithm would've picked out a David Bowie. | 0:52:27 | 0:52:30 | |
I don't think a computer can understand the emotional response | 0:52:30 | 0:52:35 | |
that you get to a record. | 0:52:35 | 0:52:37 | |
You know, we all have records that we know that make us happy, | 0:52:37 | 0:52:42 | |
records that make us incredibly sad, | 0:52:42 | 0:52:45 | |
records that make, you know, you want to jump around your bedroom | 0:52:45 | 0:52:48 | |
and, you know, throw shapes in the mirror. | 0:52:48 | 0:52:51 | |
And I don't think an algorithm can do that. | 0:52:51 | 0:52:53 | |
Isn't it really just a matter of time before | 0:52:53 | 0:52:56 | |
this rather romantic vision buckles? | 0:52:56 | 0:52:58 | |
-I think... -And you will have machine-learning algorithms | 0:52:58 | 0:53:01 | |
-and you are going to become as teched up as Google. -Yeah. | 0:53:01 | 0:53:05 | |
We are, I mean, but I'm an incurable romantic | 0:53:05 | 0:53:08 | |
and I think that... I think, you know, that the human voice | 0:53:08 | 0:53:13 | |
and the human passion will always, will always win through. | 0:53:13 | 0:53:18 | |
Thank you so much. | 0:53:18 | 0:53:19 | |
Oh, thank you for exposing me on national television | 0:53:19 | 0:53:21 | |
in getting it wrong! | 0:53:21 | 0:53:22 | |
I think I've shown that we can indeed pick fantastic songs | 0:53:24 | 0:53:27 | |
without listening to a note. | 0:53:27 | 0:53:29 | |
But it doesn't look as though I'll be selling my algorithms to Radio 1 | 0:53:29 | 0:53:33 | |
any time soon. | 0:53:33 | 0:53:35 | |
As for helping Trevor, well, my team have finished analysing | 0:53:35 | 0:53:39 | |
all the versions of Dive and the results are frankly unimpressive. | 0:53:39 | 0:53:44 | |
Here we've plotted the distance of every one of the songs | 0:53:44 | 0:53:49 | |
in the charts over the last year or so from the centre of the charts, | 0:53:49 | 0:53:54 | |
from their average. | 0:53:54 | 0:53:56 | |
Right at the centre is Taylor Swift's Style. | 0:53:56 | 0:54:00 | |
Maybe that's why she's so successful. | 0:54:00 | 0:54:02 | |
And here you can see the problem, | 0:54:02 | 0:54:04 | |
here we have ever-increasing distance from the centre. | 0:54:04 | 0:54:07 | |
Dive is out here at the edge of musical space, | 0:54:07 | 0:54:11 | |
and it's not as though we didn't try to push it down here somewhere - | 0:54:11 | 0:54:15 | |
we gave it a bit of oomph, we upped the tempo, | 0:54:15 | 0:54:19 | |
we thought, "Maybe it needs more bass," | 0:54:19 | 0:54:21 | |
so we gave it more of that. But whatever we tried, | 0:54:21 | 0:54:24 | |
it just pushed it further out into musical space. | 0:54:24 | 0:54:27 | |
We're not even getting near where we need to be. | 0:54:27 | 0:54:30 | |
And here's the thing, we can measure them, | 0:54:31 | 0:54:34 | |
we can plot them, but so far, | 0:54:34 | 0:54:38 | |
we don't know how to move them. | 0:54:38 | 0:54:39 | |
# If you stand still... # | 0:54:39 | 0:54:42 | |
All that's left is to break the news to the team. | 0:54:42 | 0:54:46 | |
-RAPS: -# So many people give to religion | 0:54:46 | 0:54:48 | |
# The music and church let you know how you're livin' | 0:54:48 | 0:54:50 | |
# Save a part of life and give till it hurts | 0:54:50 | 0:54:53 | |
# Creativity... # | 0:54:53 | 0:54:55 | |
Well, erm... | 0:54:55 | 0:54:57 | |
So, er... | 0:54:58 | 0:55:00 | |
I like the song. | 0:55:01 | 0:55:03 | |
It's really nice and, erm, the question that we've asked is, | 0:55:03 | 0:55:07 | |
how far are those songs from the centre of the charts? | 0:55:07 | 0:55:13 | |
And the answer is... | 0:55:13 | 0:55:15 | |
..that they're all really far away. | 0:55:20 | 0:55:23 | |
HE LAUGHS | 0:55:23 | 0:55:25 | |
-So my thinking is... -Yeah. | 0:55:25 | 0:55:27 | |
..that to the degree that we can tell you anything useful... | 0:55:27 | 0:55:32 | |
..it should be to ignore what we are saying. | 0:55:34 | 0:55:40 | |
'It seems that the recipe for pop success will remain hidden for now. | 0:55:40 | 0:55:45 | |
'Even hit-makers sometimes don't know it until they hear it.' | 0:55:45 | 0:55:49 | |
But sometimes when you're going through the process, things happen. | 0:55:49 | 0:55:53 | |
Just the way the singer sings that line | 0:55:53 | 0:55:55 | |
that you didn't think sounded that great, | 0:55:55 | 0:55:58 | |
but suddenly when this person sings it it just sounds amazing | 0:55:58 | 0:56:01 | |
and then suddenly, man, you have something, you know? | 0:56:01 | 0:56:04 | |
And you might have to work for days to get something really special. | 0:56:04 | 0:56:09 | |
It doesn't happen all that often, it's hard to find. | 0:56:09 | 0:56:12 | |
-We'd call it non-linear effect. -Non-linear effect, yeah. | 0:56:12 | 0:56:16 | |
And non-linear effects, | 0:56:16 | 0:56:19 | |
-they're the hardest for us to get at nowadays. -Yeah. | 0:56:19 | 0:56:23 | |
No, I can imagine. | 0:56:23 | 0:56:25 | |
We had hoped to show how science could help | 0:56:25 | 0:56:32 | |
a few really talented musicians how to make a great hit song. | 0:56:32 | 0:56:39 | |
And I have to say that we have singularly failed. | 0:56:39 | 0:56:42 | |
DANCE VERSION OF DIVE PLAYS | 0:56:42 | 0:56:44 | |
That's not to say that Dive isn't lovely, | 0:56:47 | 0:56:50 | |
and in exploring the musical space | 0:56:50 | 0:56:52 | |
I suppose that science did play a part, but only a modest one. | 0:56:52 | 0:56:57 | |
If Dive is any good, and I think it's great, | 0:57:00 | 0:57:04 | |
it's because Nike, Trevor and his team made it so. | 0:57:04 | 0:57:07 | |
# Defences come down so easily | 0:57:07 | 0:57:11 | |
# Dive into the ocean with me... # | 0:57:11 | 0:57:15 | |
Wow. | 0:57:15 | 0:57:16 | |
Wow. That's very different. | 0:57:18 | 0:57:20 | |
I'd never imagined as a dance track, no, but I like it, | 0:57:21 | 0:57:24 | |
I think it's good. I really liked the synths, I liked the rhythms, | 0:57:24 | 0:57:29 | |
I liked some of the chord changes. | 0:57:29 | 0:57:31 | |
My head was kind of bopping to it. | 0:57:31 | 0:57:34 | |
You may doubt that we can capture creativity, | 0:57:35 | 0:57:40 | |
that we can bottle art. And I have to agree, | 0:57:40 | 0:57:43 | |
it hasn't been very convincing. And yet, I still think we can. | 0:57:43 | 0:57:47 | |
After all, we've seen the power of data. | 0:57:48 | 0:57:51 | |
It's shown us how pop evolved... | 0:57:51 | 0:57:54 | |
..and how to find great new music. | 0:57:57 | 0:58:00 | |
There's nothing intrinsically mysterious about this, | 0:58:00 | 0:58:03 | |
it is after all just physics and neurobiology. | 0:58:03 | 0:58:08 | |
# Dive into the ocean with me... # | 0:58:08 | 0:58:10 | |
Given enough computational power, given enough data, | 0:58:10 | 0:58:14 | |
we will work it out. | 0:58:14 | 0:58:16 | |
When? | 0:58:16 | 0:58:17 | |
Not by the end of this programme, but we will. | 0:58:17 | 0:58:20 | |
# Dive into the ocean with me | 0:58:20 | 0:58:24 | |
-# I'm braver -Yes, I'm braver | 0:58:24 | 0:58:27 | |
-# Braver -Yes, I'm braver | 0:58:27 | 0:58:31 | |
# Dive into the ocean with me | 0:58:31 | 0:58:36 | |
# Cos if you stand still | 0:58:36 | 0:58:38 | |
# You'll never, ever, ever see what we could be | 0:58:38 | 0:58:42 | |
RAPPING | 0:58:42 | 0:58:46 | |
# What we could be | 0:58:46 | 0:58:48 | |
RAPPING | 0:58:48 | 0:58:53 | |
# What we could be. # | 0:58:53 | 0:58:55 |