The AI Song Contest

A code – be it a chord, melody or rhythm in someone’s head or a disk – can output into puffs of air to create this exquisite, yet ultimately unquantifiable substance we know as music. So how can a machine help us write music for humans?

The gorgeous accidents of the musician’s fingers slipping across their instrument, falling into a new collection of notes – or that warm feeling when a voice breaks between notes of a melody that make the whole tune sweeter – this is the intimate sound of a flawed and beautiful musician, their power, their individuality, their magic – the song inside the tune as Christina Aguilera once said.  

So how can you go from that mystery of music to asking a machine to write a hit song? Well, my team ‘Smorgasborg’, one of 38 entries to this year’s AI Song Contest decided to explore this question.

Voting closes on July 1st – listen to as many entries as you like – and vote up the ones you enjoy the most!

This years’ participants are a fantastic collection of artists, technologists and machine learning enthusiasts, all of whom approached the brief differently – make music – using machines! Now, as a musician learning the elements of coding, I approached the challenge from a musical perspective – choosing to discover “How can we use accessible AI tools to augment the human creative process rather than replace it?”

I’d taught myself AI composing with Style Transfer during my cancer treatment and subsequent shielding here in the UK. It’s surprising how much time there is for learning when utterly stationary, or unable to leave the house, or indeed when it’s impossible to sleep through the night… so why not stay up and run code every few minutes?

My initial results were interesting but not what I would call ‘easy listening’. This time would be different.

Like many musicians, I miss jamming with real people in real time, that physiological response to sound that makes us stand with others in front of massive speakers ‘in flow state’ – that feeling of being somewhere or nowhere – ‘in the zone’.

AI’s potential goes much further than just audio generating audio – which is what I’d been doing – and it just didn’t feel enough like a collaboration. After all, we could have asked the machine to produce random sounds and then selected the best. But instead, we split the song- some elements created by AI, some by the musician- and NO autotune!

Here’s a flowchart showing the relationship between human- and machine-generated content.

My team discussed many issues – even at the level of deciding what popular music is – for example, dominant music theory is based on Western, European tradition. This was partly why we elected to start with AI lyric generation rather than music, as it kept orchestral and melodic options open. We felt AI music would have been more likely to generate western diatonic sounds, as the data sets are currently largely lacking in music outside these descriptors. We wanted to explore some influences outside the popular western sounds.

Here are a few seeding prompts in bold below: For a while I was tempted to go with really simple songs. Then, during a team call, I read through a few that were strangely poetic”.

Example Prompts | Completions from GPT-3 (safe outputs) follow:

“Do people want a catchy tune, a riff that can fly them to the moon? | Or would they rather just see me in my underpants?…” 

“dance dance I wanna | see you move dance dance dance! (Oh!) It’s time to make it right (Oh!) We’re gonna make it…”

“write a love song about 2 machines | falling in luv. 1 hour later. BAM BAM BAM BAM BAM BAM “i just wan 2 say, that’s one of the best songs i’ve ever heard” “I KNOW RIGHT” “i mean, i would probably pay like $1.99 just to get that song on my phone.” “do it, do it now, i’ll wait” BAM BAM BAM BAM BAM BAM “i did it” “KEEP THE CHANGE…” 

After further experimentation, the below completion caught our attention.  

“feel the bass dance all night headphone on smartphone light walking like a zombie in the dark pulsating body nightlife make you move vibrating body sending shiver to the core….”

These words… sounded most like a story, they had evocative phrases like ‘walking like a zombie’” We fed this modified prompt back into the engine and generated our lyrics which remain unchanged  throughout the songwriting process.  

“feel the bass dance all night headphones on smartphone light walking like a zombie in the dark | ‘til the streetlight burns the sunrise behind your back you were here now you’re gone There’s a girl I know who knows what she wants.

I was inspired by the words and created a first draft of the melody, but was getting stuck on ‘Shine like a diamond dust in the universe’. We wanted to use lyrics verbatim to stay faithful to the AI, but were stumped on how to parse this particular musical phrase.So we used OpenAI’s Jukebox trained on Adele to suggest various new melodic lines. 

At first I used a model to output 30 seconds of music at a time – but my first attempts were frustrating – it didn’t create tunes that made theoretical sense! After more false starts, I realised co-composing suited me more, given my mainly musical background. Supervising every 4-6 secs added my own musical preferences to the generative result. 

After 21 attempts (and more crashes!), attempt 22 inspired me to re-scan the lyric lines –

|| Shine like a diamond  ||  Dust in the universe became

|| Shine || Like a diamond dust  ||  In the universe.

Yes! I gleefully thanked the program out loud even though it was 01:30AM, and sang a guide melody and piano accompaniment into Logic Pro X. I felt no need to upsample as I wasn’t planning to output audio and just needed to hear the melodic lines.

Google’s NSynth -one of the settings used with Ableton | Imaginary Soundscapes – with the image used to generate fireworks in the chorus

The bass, piano and pad are all generated via the NSYNTH sound. I was inspired by team mate Leila saying the song was set “In Space” and chose sounds based on this thought – resulting in ethereal and floating pads, with sharp shards of passing comet dust! Continuing the theme, we also used AI-generated audio from Imaginary-soundscape, an online engine designed to add suggested soundscapes to (normally earth) landscapes. We used an image of space from Unsplash and the AI returned audio – fireworks!  You can hear these alongside the chorus.

If you’d like to help us become Top of the Bots – please vote here – no need to register! Team Smorgasborg is excited to be part of the AI Song Contest!

A selection of AI tools used in the creative process: we also used Deep Music Visualizer and Tokkingheads for the music video

GPT-3 – Lyric generation from word prompts and questions  https://beta.openai.com 

Jukebox (OpenAI) – neural networks style transfer for solving musical problems https://jukebox.openai.com 

NSYNTH – machine learning based synthesiser for sound generation  https://magenta.tensorflow.org/nsynth 

Imaginary Soundscape –  AI generated soundscapes from images   https://www.imaginarysoundscape.net

DreamscopeApp – deep dream image generator https://dreamscopeapp.com/deep-dream-generator 

Music Video for Team Smorgasborg, LJ, Dav and Leila.

“I knew the song was finished when Logic gave me the “System Overload” message.”

-very late at night

Getting into Flow states during difficult times – like going through Breast Cancer

Stories of my disappearance are greatly exaggerated.

I’ve just been diagnosed with breast cancer, so now looking forward to playlists such as “Now that’s what I call Chemo!” followed by the hotly anticipated “Last Night a Surgeon Saved my Life” slated for release in the new year. *

I’ll still present and perform occasionally when going through treatment. We’ll play it by ear, depending on how everything progresses and energy levels. Short Notice bookings might work. I’m optimistic that normal service will slowly resume if the results are encouraging.

To those of you unlucky enough to have some experience of the disease (either yourself, or someone you know) I send positivity and love.

BACKSTORY

My mum died of cancer when I was a child – details of her medical treatment were whispered in hushed tones in separate rooms, out of earshot and in secrecy. Yet attempts to conceal her terminal diagnosis were pointless as I knew what was going on. With nobody to ask, I felt powerless.

It’s why this very personal post exists: to try the opposite track. Knowledge (and Music) has always been a great comfort, and my curiosity to learn has helped me overcome so many obstacles, achieve so much and connect with frankly extraordinary people while performing or presenting. I’ve explained as openly and as age appropriately as possible to my toddler. Telling children early on is advised by Macmillan and other cancer charities -such a difficult experience to do but it was taken well and felt like the best decision for him.

FORWARD STORY

I may be dealing with cancer now, but as anyone different has always known, there’s simply so much more to us than how we look, our personal struggles, or what equipment we use to access the world. We are still artists, engineers, writers, thinkers, comics, poets, AI magicians, coders, hackers, lockpickers, DJs, storytellers. We laugh at great jokes, cry at terrible movies on planes (well, OK, I do) and enjoy connecting with others through our love of creativity, unconventional thinking. Best of all we love to collaborate with those who challenge and excite us. We crave pure connections which at their best transcend physical and mental capabilities, creating that elusive and magical experience of flow for audiences and performers to share.

In short, you are welcome to ask cancer questions, which I will answer if I feel up to it…. or, we can talk about stuff I still really love, like music, technology and performing. Any great, fun audio books with happy endings? Wholesome comedy video clips and podcasts? let me know!

Want to lend me some Interesting VR/Immersive kit for a day to try out during or after a chemo treatment in London? I’m down for any entertaining tech distractions during my many medically enhanced hours over the next weeks and months. Some things feel rather unpleasant, so if you think it might be fun to see how creative tech could help make procedures more palatable – that sounds kind of awesome to me too. Interested? Do click here to contact.

Finally, to everyone reading this far, thank you so much for our connection – whether it’s IRL or online  – however brief, however close, through TV, presenting or hacker / music circles, please know that many of you have been responsible for so many of my happiest thoughts. Your impact has been so positive in helping me want to be better – authentic, inspiring, thoughtful, uplifting – and kind. I wish you all the very best.

Love, LJ

P.S *These playlists don’t exist – yet. Want me to make some?

Under new management!

…excited to announce that I’m now exclusively represented by JLA Management.

It’s great timing as I’m being asked to present and perform at so many incredible events!

Do please contact Hannah Oldman on +442079072800 for further information.

United Nations Performance May 2019

This Week: The Musical

Oooooh!!!!!

I’ve been super busy because I have a new show!! It’s called This Week: The Musical and we are soft launching it today… you’re some of the first humans to hear it!

Listening links right here:  

iTunes:     

Libsyn for non iTunes Users:

This Week: The Musical is a comedy tech news podcast,  complete with songs and sketches and special guests. Totally free to listen and very silly.

Leila Johnston and I have wanted to make something like this for ages!

So if you’d like to listen to our podcast right now, that would be utterly amazing.

This week’s episode includes songs about Spice Girls being replaced by machines and also an interview with the formidable Gretchen Greene, an artist who’s building her own AI to assist her in her creations.

p.s. if do you like it, please do subscriiiiiiibe and/or chat about it with us on #ThisweekTM. We live at www.the2ljs.com  and have a facebook page too. Plus we’re on instagram and twitter @the2ljs
 

Yay! thanks for reading this far, I love you all dearly. I hope you like it 🙂

Tech News Comedy Podcast with songs, sketches, special guests and silliness. Includes against-the-clock innovation and a rogue pikachu.

LJ x

 

Understanding the Connection Between Synesthesia and Absolute Pitch

Interview with ‘The Scientist’ Magazine (2017)

Understanding the Connection Between Synesthesia and Absolute Pitch

Fascinating reading about the research into Synaesthesia and Perfect Pitch – brilliantly researched and written by Science Writer Catherine Offord

*post added in 2018, article written 2017

 

Why Superheroes all have different Super Powers

Reflections on International Women’s Day 2018  (6 minute read)

Today the world celebrates International Women’s Day. A time to celebrate Inspirational Women, but today I also want to include inspirational people. That is – humans – I’m not bothered about the gender.

There is a collective role that all leaders, influencers, and team members have. That responsibility is to create meaningful progress to inclusion. Inclusion of not just women but different people, people that think, look, and behave in ways that might not be the same as you or I.

To get ahead as a woman we’re given a lot of advice, in fact in my line of work there is a nice long queue of people all to ready to give advice on what I should do to progress – including: don’t be so outspoken, dress less sparkly, cover your arms, be more like a man, be more feminine, don’t show off, get a new job, get a real job, wear less lip gloss, lose weight, wear thinner and higher heels, learn more STEM, speak with less of an accent,  and so on.

The reality is that while the women’s movement has come a long way, its progress is slow and not reflective of the contribution that women have to make.

It’s also true that people find their skills underused, unknown and untapped.

I suspect that everyone regardless of colour and class will have their own version of unwanted advice that gets thrown at them. Advice on what one should and shouldn’t do or say. Advice on what’s feasible for them to try to achieve, and what society expects from their role, and how high they are expected to aim, because some things are simply not possible. Luckily for me I ignored quite a lot of advice – from ‘you’re not pretty/thin/tall enough to be on TV’, ‘you’ll never be taken seriously’ to ‘You? Learn soldering? …But you’ll burn yourself’. Oh and so many more. You’ll have your own ones I’m sure.

Some people are already doing the thing they’ve always wanted to do for a salary that suits them. And I’ve decided they fall into two main groups. I call the first group Peacocks* – those who feel threatened by others and want to stop anyone getting on their patch. Peacocks worry about their mortgage or their profile and do everything in their power to hold on to their social status and the status quo. They are likely not to want to learn new things and would rather stick to ‘the way it’s always been done’.

I call the second group Phoenixes. Phoenixes are glorious. They dream and they do. They become positive mentors, helping the next generation realise their potential. They know how to innovate and always find ways to live well. They know there is enough to go round and that they can always find new ways to create opportunities for prosperity. They are still ambitious but want to accomplish their goals while being supportive, kind, and socially responsible to those around them. Like you, I’ve interacted with both types of these people. I think you can guess which type is happier, more fulfilled and more likely to have authentic connections with others. I grew up around peacocks, but I’m optimistic that there are more and more Phoenixes around. People are realising that making their environment better has a direct effect on their own well-being. Phoenixes know that helping others to fly could be construed as a healthy selfishness as it makes them feel part of something bigger – the magic of ‘self-actualisation’ at the top of Maslow’s Hierarchy of Needs. I want to be a Phoenix when I grow up.

(*yes, Peacocks are male but I’ve decided in this context my made-up term can also include women who use the same ‘gatekeeping’ tactics)

There’s a difference between recognising truth when a person tells us the truth,  and being thrown harsh words by someone for their own peace of mind.

Those harsh words repeated by many voices as we go through life erode our hopes, and threaten to compress our dreaming souls into quiet grey conformity.

Those harsh words are spoken so freely and thoughtlessly to many of us who are different. From outspoken or unsolicited anonymous online commentary to well-meaning yet undermining advice from loved ones, those harsh words have the potential to stop an amazing idea from being born.

Which is why I think it’s time more of us stopped listening to ‘society’ when it’s used as a lazy way to maintain a status quo which works for just a few peacocks.

I think society would benefit massively from becoming inclusive – a community where ideas from women and people who think differently are welcomed. Wouldn’t it be such a refreshing energy boost? New insights into existing challenges could create an amazingly fertile environment, and that’s when big problems get solved with good humour. Instead of feeling threatened, great leaders and strong people can hear previously unheard voices – and harness these ideas based on merit, not on what kind of human created it.

A group’s strength and reach is amplified because everyone’s strengths are diverse, not duplicated. How boring would a superhero ensemble movie be if everyone had the same super-power? They save the day by having different abilities and learning how to work together and combine their talents.

While the data shows us that there are fewer women than men working in and with technology, everyone reading this article knows that technology itself is not the problem. It can be learned by anyone – class, race, gender, age – it does not matter. There is no reason why technology needs to be aligned with a particular gender. It is neutral, but a great lever in which to accelerate your reach, your ability, and power to connect with others.

I’m glad I stopped listening to the people who told me I couldn’t do anything, that I’d never amount to anything, that I was not worth bothering with.  I have met many people who have sadly been told something similar. Well, if no-one has said this to you yet, you can do anything. You are worth bothering with. You have the potential to change the world.

Like many people, trying to gain new skills makes my brain hurt and I will get stuck. But that just makes me more determined. I will ask for help. I will keep learning, I will find a community and contribute to it – or create one if it doesn’t exist yet. And at the same time I will keep giving talks and performances that hopefully inspire people despite the fact that a few still find it a novelty that I am female. Occasionally people tell me this in person.

Judging from all the advice I have been given, I never fitted in. I am not what society expects from a person. But that’s OK. When I wanted to fix my broken iPad, so many people told me it was impossible, and it wasn’t worth trying. But I kept trying. I failed the first time, but succeeded on my second attempt. I filmed the whole thing for the BBC at the same time. After I fixed it, many people contacted me to say they saw me do it and realised that they could do it too. Lots of people replaced their phone screens because they could see it was possible and felt confident enough to try it themselves.

So if after reading this one extra person aims to be a Phoenix, a community builder, a world-changer, a coder or even feels that today they can get out of bed and do the washing up –  if you can do something, one thing that you are proud of after reading this, then I shall celebrate International Women’s Day with you, and so will many others, regardless of how different we might be.

LJ Rich

Adapted from a talk given on International Women’s Day, March 6th 2018 to Sheffield Hallam University and Leeds University as part of an ACCAGlobal event.

 

A Musician’s guide to Inventing

I gave a talk at the wonderfully diverse and always thought-provoking Thinking Digital 2015 conference.

But instead of a conventional keynote speech, Herb Kim the organiser kindly said that I could present whatever I liked. The result: “A Musician’s Guide to Inventing”.

I worried before going on stage that this was a completely crazy idea – and a bit far off anything else in the conference. I couldn’t sleep – I was up late tweaking the presentation. I knew the room was full of interesting and influential people who knew about technology trends, and when I give any presentation I’m obsessed with the idea of giving the audience something that they could use – something that would be valuable to them. How could I give something new to feed their amazing brains? Perhaps I could share something more personal that they might not know about… but maybe that’s not going to be interesting enough? Oh, how I fretted…

So, completely unsure if this would work and with the inherent sense of adventure that gets me into all kinds of amazing situations – I did this:

And I’m so glad I did it. I was so relieved! It went better than I could have imagined! What a pleasure to have 3 floors of such an energetic and friendly audience laughing, clapping and bonding! It’s weird, the one thing I wasn’t worried about was the music performance – even though that bit is really complicated!

Of course, with hindsight I was very happy that I decided to go with my audacious idea – it was only then I realised that by doing what I did I was taking the advice of my own presentation! So I guess this is a post dedicated to those thinking about doing something amazing and ambitious and wonderful who perhaps need that extra push to go ahead and start. Go on! And let me know in the comments what you’re gonna do.

Synaesthesia and Interaction – how to talk about it

Well,

this started as a paragraph and escalated to an essay.

It’s dedicated to those of us who find it hard to integrate their synaesthesia in public, those of us who are yet to learn that it’s OK and in some cases lovely to be a little different, and those of us who might be struggling with interacting with the bright loud sharp world that we inhabit compared to those without our quirky neurology.

I went back to see my old music tutor at Oxford a few weeks back. It must have been around 15-20 years ago when I studied music there. The prof told me I spoke like no-one else he taught. I would describe, say, Bach in terms of texture, taste, colour, touch – with so many layers to music it was really important to me to be accurate in my description, but how odd to my tutor for me to describe Bach as a green forest or the smell of damp wood – back then I didn’t know about synaesthesia so it was a joy to finally talk to him about it.

For him, it made sense of all the things I used to say about music – I got a feeling that he was almost relieved to have an explanation for it!

And for me, it made me think a lot more on what might be why many of us with synaesthesia struggle with human interaction.

I think describing the world and especially music cross-modally (i.e. synaesthetically) works really well in a creative context, but in normal conversations I started to wonder if my happily jumping between senses may be jarring to people who are just trying to understand what I’m on about.

Here’s my theory: we synaesthetes freely switch from taste to sound to colour to texture to <insert sense here> when we are talking about something – we engage whatever description works to convey the feeling we have with the most clarity or accuracy, just like someone else would, though we have a much larger vocabulary to choose from, sometimes even including gestures or noises. So to a non-synaesthete I wonder if it might sound like we’re picking from the wrong list.

For example – let us imagine people are expecting a food to taste like <taste>.

When instead we supply someone with

‘this food tastes like <sound> or <colour> or <noise>’

this may seem at right-angles to conventional expectation and leads to scenarios like:

a) Conversation partner completely ignores modality switch consciously but gets confused on some level; tries their best to continue

b) doesn’t notice cross modality at all; continues as if nothing out of place

c) (common with non-synesthetes) conversation moves to curiosity and synaesthetic experience questions – the question of what the food is like is not as important anymore! Questions, so many questions!

d) (common with other synesthetes and close friends) conversation partner understands, accepts and enjoys description, conversation continues and comparative modalities are explored. Amazing, a meeting of uncommon minds!

All of these are OK.  I’ve probably missed some others out.

So, I learned a few sentences to say that a) put people at ease and b) put me at ease. I’ve found these are great to use with both “unaware synaesthetes” and non-synaesthetes as it gives a context to our choice of words or actions when they don’t quite fit what people expect. Here they are:

“I have synaesthesia which means my senses are a bit mixed together” works really well.

“I think everyone has a version of synaesthesia, some people experience it more intensely than others” is great when people are more curious and want to perhaps explore their own associations. I believe that everyone has the potential to experience cross-modality at some level.

I’m actually happy to talk about my synaesthesia when asked, much happier if I have access to a piano at the same time.  If/when someone says I’m weird that’s OK. I tell them that they are probably right and smile gently. If someone says I’m making it up that’s OK too, it doesn’t matter to me what they think, I smile and say that it’s my experience, which is all we have to go on. If I’m feeling a little like I’m being judged negatively – and some people will be suspicious of things they don’t know about – I try to remember that everyone has their own struggles, perhaps they’re not in a receptive mood for other reasons – then I’ll think privately on how much I’m enjoying delicious food or music around me more than someone who’s not wired the same way.

We have many challenges as synaesthetes.  Having said that though I feel that the overall potential to experience the world so deeply with so little effort is worth the odd strange look, explanatory conversation and sense of overwhelm that we no doubt all have to deal with.

__

Here is an interview I did (it was really early in the morning!) about food and synaesthesia for a documentary on Radio New Zealand – I’m among a variety of artists interviewed all talking about their own experience.

http://www.radionz.co.nz/national/programmes/secretlife/audio/201762931/the-secret-life-of-synesthetes

#ljtunes

I broadcast a weekly streaming show on the Periscope app. 12 weeks in and it’s rather good fun. In fact, my #ljtunes show has picked up quite a bit of late (over 400,000 likes at the time of writing) – for those of you who haven’t visited, please do come by on a Monday night 20:30 UK time.  Or hop on through my twitter account – where links to the show are posted…

 Live – from anywhere with a piano can mean #LJtunes – more info www.ljtunes.com / or twitter.com/ljrich

It’s clear streaming has finally hit the main-stream  – perfect for the sort of concerts I give – live, interactive, conversational composing.  I love playing music while guiding viewers along genre-irrelevant leaps –  awesome tunes, fun with synths – or even performing live-composed glitching soundwalking through London – all this while chatting away to a brilliantly engaged, interactive audience.

And it’s not just playing music – I sometimes talk about the music theory behind the great tunes – what makes things catchy – why the best bits of a song work, my favourite chord progressions, original compositions and pastiches of contemporary and classical tunes, music theory, mashups, music tech and live-composing, all with the simultaneous challenge of conversing with a virtual audience!

A maximum 200 people can chat through the app (though we’ve had 1,600 people on – not sure of the upper limit of viewers).  When the broadcast fills up the chat regularly spills over onto Twitter using the #ljtunes hashtag – it’s amazing and very challenging having to process so much information while playing the piano and chatting to everyone at the same time, but even with those challenges it’s an incredibly pleasing experience.

I’ll see you online!

 

More info about Live Streaming

Background:

Periscope is an app (like Meerkat, Bambuser and predecessors Qik and Seesmic) allowing a bunch of people to watch one person’s smartphone camera – in effect turning everyone with a mobile phone and an internet connection into a broadcaster. Viewers can communicate not just with the person generating the feed but crucially with each other too – and those discussions during real-time events give a sense of immediacy to the wildly varying content.

I was (I think) the first in the world to periscope while broadcasting live on the BBC (BBC World News, April 9, 2015) but just 90 days later it’s quite normal for news outlets to host ‘behind the scenes’ clips or even integrate real-time streaming into their programming. People stream their public transport journeys, back gardens – even sunsets. I’ve seen someone sleeping and chatted with other people who were also watching that person sleeping.

Watching live streams is an oddly voyeuristic experience – an insomniac moment leaves me awake at 3am and instead of browsing a forum I watch someone else’s cat watching TV, or my friend drinking in a hotel bar or someone walking in their garden on the other side of the world.

It feels like there’s currently a sense of authenticity about live-streaming content – which will last at least until someone figures out how to spoof the camera feed.

More great blog posts on periscope here, here and here.

Protected: Space Experiment:

This content is password protected. To view it please enter your password below:

Password: