Jesse Engel's guest appearances

Jesse Engel

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

Art + Music + Technology

Cue It Up; A Billiards Podcast

Interdependence

Meredith Broussard

Christopher Reid

Ilias Diakonikolas

John Palmer

Scott Clark

Celeste Kidd

Dennis Mortensen

Rob Walker

Matt Black

Matt Jackson

David Turner

Sanmi Koyejo

Chelsea Finn

Dario Amodei

Jianxiong Xiao

OwlTail

Today we’re joined by Jesse Engel, Staff Research Scientist at Google, working on the Magenta Project.  In our conversation with Jesse, we explore the current landscape of creativity AI, and the role Magenta plays in helping express creativity through ML and deep learning. We dig deep into their Differentiable Digital Signal Processing (DDSP) library, which “lets you combine the interpretable structure of classical DSP elements (such as filters, oscillators, reverberation, etc.) with the expressivity of deep learning.” Finally, Jesse walks us through some of the other projects that the Magenta team undertakes, including NLP and language modeling, and what he wants to see come out of the work that he and others are doing in creative AI research. The complete show notes for this episode can be found at twimlai.com/go/452. 

Today we’re joined by Jesse Engel, Staff Research Scientist at Google, working on the Magenta Project.  In our conversation with Jesse, we explore the current landscape of creativity AI, and the role Magenta plays in helping express creativity through ML and deep learning. We dig deep into their Differentiable Digital Signal Processing (DDSP) library, which “lets you combine the interpretable structure of classical DSP elements (such as filters, oscillators, reverberation, etc.) with the expressivity of deep learning.” Finally, Jesse walks us through some of the other projects that the Magenta team undertakes, including NLP and language modeling, and what he wants to see come out of the work that he and others are doing in creative AI research. The complete show notes for this episode can be found at <a href="https://twimlai.com/go/452" rel="nofollow" target="_blank">twimlai.com/go/452</a>.

Expressive Deep Learning with Magenta DDSP w/ Jesse Engel - #452

In this episode we talk with Jesse Engel, musician, Senior Research Scientist at Google Brain and creative lead of the Magenta project. Magenta is an open source research project exploring the role of machine learning as a tool in the creative process, developed by numerous researchers and engineers from the Google brain team, Google’s self directed machine intelligence group. Amongst many things we discuss the role and research focus of Magenta, look at how research lab OpenAI’s recent Jukebox project raised some necessary ethical debates around the puppeteering of living artists voices and styles, get psychedelic about how making music technology precedes spoken language, and discuss his latest exciting project.Check out the tools they have developed and reach out to Magenta here:https://magenta.tensorflow.org/If you would like to hear the full episode, consider supporting the project athttps://patreon.com/interdependence

In this episode we talk with Jesse Engel, musician, Senior Research Scientist at Google Brain and creative lead of the Magenta project. Magenta is an open source research project exploring the role of machine learning as a tool in the creative process, developed by numerous researchers and engineers from the Google brain team, Google’s self directed machine intelligence group. Amongst many things we discuss the role and research focus of Magenta, look at how research lab OpenAI’s recent Jukebox project raised some necessary ethical debates around the puppeteering of living artists voices and styles, get psychedelic about how making music technology precedes spoken language, and discuss his latest exciting project.Check out the tools they have developed and reach out to Magenta here:<a href="https://magenta.tensorflow.org/" rel="nofollow" target="_blank">https://magenta.tensorflow.org/</a>If you would like to hear the full episode, consider supporting the project at<a href="https://patreon.com/interdependence" rel="nofollow" target="_blank">https://patreon.com/interdependence</a>

Interdependence 4 - Jesse Engel (Google Magenta)

NOTE: This podcast is presented as a collaboration with Synthtopia.com for the presentation of people designing and implementing synthesizers. You can listen to the podcast here, on the Synthtopia website (in an embedded player) or on iTunes. But you can also read the article as well as search for information by viewing the transcription available here:  http://www.synthtopia.com/content/2017/06/25/neural-audio-synthesis-with-google/ I first got to know the Magenta Project at Google when I heard a podcast with Douglas Eck. I subsequently interviewed him for my podcast, where we talked about using machine learning to do interesting work with composition. This led to an invite to meet with the team, and I got a great introduction to their work at their Mountain View headquarters, and first got to me this week's guest, Jesse Engel. But something interesting happened a few months ago: I got blindsided by the project when they put up details on their 'NSynth' project. This effort is about using machine learning for music, but not for composition - but rather for sound design. Somehow, I never saw that coming, but it really makes a lot of sense, and it comes up with some pretty interesting results. As part of this series on Synthesizer Design we've talked to people about their past work in synth design. But it is interesting to also talk to someone about the future of synthesis, how computers might be brought into play to enhance the sound design functions, and how machine learning can drive (and/or be driven into managing) massive parameter sets. Jesse Engel breaks things down for us in this talk, and we get a chance to see how big the datasets are, how all of this data might be managed, and how he goes about wrangling a bunch of scientists and statisticians into working with sound. Sometimes the work is as expected (a "better violin"), and sometimes not (the "cat flute"). It's a crazy ride, and I hope you learn as much as I did about one of the future possibilities for synth design. Enjoy!

NOTE: This podcast is presented as a collaboration with <a href="http://Synthtopia.com" rel="nofollow" target="_blank">Synthtopia.com</a> for the presentation of people designing and implementing synthesizers. You can listen to the podcast here, on the Synthtopia website (in an embedded player) or on iTunes. But you can also read the article as well as search for information by viewing the transcription available here: <a href="http://www.synthtopia.com/content/2017/06/25/neural-audio-synthesis-with-google/" rel="nofollow" target="_blank"> http://www.synthtopia.com/content/2017/06/25/neural-audio-synthesis-with-google/</a> I first got to know the Magenta Project at Google when I heard a podcast with Douglas Eck. I subsequently interviewed him for <a href="http://artmusictech.libsyn.com/podcast-148-douglas-eck" rel="nofollow" target="_blank">my podcast</a>, where we talked about using machine learning to do interesting work with composition. This led to an invite to meet with the team, and I got a great introduction to their work at their Mountain View headquarters, and first got to me this week's guest, Jesse Engel. But something interesting happened a few months ago: I got blindsided by the project when they put up details on <a href="https://magenta.tensorflow.org/nsynth" rel="nofollow" target="_blank">their 'NSynth' project</a>. This effort is about using machine learning for music, but not for composition - but rather for sound design. Somehow, I never saw that coming, but it really makes a lot of sense, and it comes up with some pretty interesting results. As part of this series on Synthesizer Design we've talked to people about their past work in synth design. But it is interesting to also talk to someone about the future of synthesis, how computers might be brought into play to enhance the sound design functions, and how machine learning can drive (and/or be driven into managing) massive parameter sets. Jesse Engel breaks things down for us in this talk, and we get a chance to see how big the datasets are, how all of this data might be managed, and how he goes about wrangling a bunch of scientists and statisticians into working with sound. Sometimes the work is as expected (a "better violin"), and sometimes not (the "cat flute"). It's a crazy ride, and I hope you learn as much as I did about one of the future possibilities for synth design. Enjoy!

Podcast 181: Jesse Engel (Google Magenta Project)