The So Strangely Podcast

Finn interviews Composer and Machine Learning specialist Dr. Cheng-Zhi Anna Huang about the Music Transformer project at Google’s Magenta Labs. They discuss representations of music for machine learning, algorithmic music generation as a compositional aid, the JS Bach Google Doodle, how self-reference defines structure in music, and compare the musicality of different systems with example outputs.

• [0:01:05] Introducing Dr. Anna Huang
• [0:03:43] JS Bach Google Doodle
• [0:12:52] Representations of musical information for machine learning
• [0:16:26] Music Transformer project
  • [0:25:15] RNN algorithm music sample
• [0:25:45] ABA structure challenge for generative systems
  • [0:30:30] Vanilla Transformer algorithm music sample
  • [0:32:07] Music Transformer algorithm music sample
• [0:36:30] Self Reference Visualisation (see blog post)
• [0:43:27] Everyday music implications
• [0:48:10] What this work says about music
  • [0:50:01] Music Transformer trained on Jazz Piano

• Recommended project:
  • Blog post: Huang, C.Z.A., Simon, I., & Dinculescu, M. (2018, Dec 12). Music Transformer: Generating Music with Long-Term Structure [Blog Post]
  • Paper: Huang, C.Z.A., Vaswani, A., Uszkoreit, J., Shazeer, N., Simon, I., Hawthorne, C., Dai, A.M., Hoffman, M.D., Dinculescu, M., & Eck, D. (2018) MUSIC TRANSFORMER: GENERATING MUSIC WITH LONG-TERM STRUCTURE on arXiv.org
• Interviewee: Dr. Cheng-Zhi Huang at Google AI, on twitter @huangcza
• Google Doodle Celebrating JS Bach with AI harmonising melodies
• Related papers:
  • Huang, C.Z.A., Cooijmans, T., Roberts, A., Courville, A., Eck, D. (2017). Coconet: Counterpoint by Convolution. ISMIR.
  • Huang, C.Z.A., Cooijmans, T., Dinculescu, M., Roberts, A., & Hawthorne, C. (2019, Mar 20). Coconet: the ML model behind today’s Bach Doodle.
  • Huang, C.Z.A., Hawthorne, C., Roberts, A., Dinculescu, M., Wexler, J., Hong, L., Howcroft, J. (2019). The Bach Doodle: Approachable music composition with machine learning at scale. ISMIR.

The So Strangely Podcast is produced by Finn Upham, 2018. Algorithmic music samples from the blog post Music Transformer: Generating Music with Long-Term Structure, and included under the principles of fair dealing. The closing music includes a sample of Diana Deutsch’s Speech-Song Illusion sound demo 1.

Postdoctoral fellow Sarah Sauvé recommends “Individual differences in rhythmic cortical entrainment correlate with predictive behavior in sensorimotor synchronization” by Sylvie Nozaradan, Isabelle Peret, and Peter E. Keller, published in Nature Scientific Reports in 2016. Sarah and Finn interview Dr. Nozaradan about the measures of metrical perception and rhythm production, entrainment to difficult stimuli, and what these results imply for a replication study conducted with older participants.

• [0:00:10] Intro with Sarah
• [0:09:41] Interview: Where this study comes from
• [0:14:25] Interview: Challenging stimuli
• [0:22:09] Interview: Older listeners replication
• [0:26:43] Interview: Task 3, metrical prediction
• [0:38:25] Interview: Implications for everyday musical experiences
• [0:44:43] Closing debrief

• Recommended article:
  • Nozaradan, S., Peretz, I., & Keller, P. E. (2016). Individual differences in rhythmic cortical entrainment correlate with predictive behavior in sensorimotor synchronization. Scientific reports, 6, 20612.
• Interviewee: Dr. Sylvie Nozaradan, Institute of neuroscience at UC Louvain, in Belgium (Google Scholar Profile)
• Co-host: Dr. Sarah Sauvé, Postdoctoral fellow at Memorial University of Newfoundland (Website, twitter)

Questions, comments, and article recommendations are always welcome! Get in touch here, through the contact page, or on twitter, or email the producer directly: finn at sostrangely.com

The So Strangely Podcast is produced by Finn Upham, 2019. The closing music includes a sample of Diana Deutsch’s Speech-Song Illusion sound demo 1.

Music technology PhD Candidate Tim de Reuse recommends “Unmixer: An Interface for Extracting and Remixing Loops” by Jordan Smith,Yuta Kawasaki, and Masataka Goto, published in the proceedings of ISMIR 2019. Tim and Finn interview Jordan about the origins of this project, the algorithm behind the loop extraction, the importance of repetition in music, and the creative and playful applications of Unmixer.

Note: This conversation was recorded in December 2019. Techically issues with some tracks contributed to delays. Apologies for the choppy audio quality.

• [0:01:40] Project Summary
• [0:05:05] Demonstration of Unmixer
• [0:14:27] Origins of the UnMixer project
• [0:19:44] Factorisation algorithm
• [0:28:37] Computational and musical objectives for factorisation
• [0:36:15] The Unmixer web interface
• [0:41:30] 2nd Demonstration, parameters and track selection
• [0:49:13] What Unmixer tells us about music

• Recommended article:
  • Smith, J, Kawasaki, Y, & Goto, M. (2019) Unmixer: An Interface for Extracting and Remixing Loops. Proceedings of 20th ISMIR meeting, Delft Netherlands.
  • UnMixer website: https://unmixer.ongaaccel.jp/
  • Project webpage
• Interviewee: Dr. Jordan BL Smith, Research Scientist at Tik Tok.Website, twitter
• Co-host: PhD Candidate Tim de Reuse, website, twitter
• Papers cited in the discussion:
  • Smith, J. B., & Goto, M. (2018, April). Nonnegative tensor factorization for source separation of loops in audio. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 171-175). IEEE.
  • Schmidhuber, J. (2009). Simple algorithmic theory of subjective beauty, novelty, surprise, interestingness, attention, curiosity, creativity, art, science, music, jokes. Journal of SICE, 48(1).
  • Rafii, Z., & Pardo, B. (2012). Repeating pattern extraction technique (REPET): A simple method for music/voice separation. IEEE transactions on audio, speech, and language processing, 21(1), 73-84.
• Music sampled:
  • Daft Punk, Random Access Memories (2013): Doing it Right (ft. Panda Bear)
  • Martin Solveig & Dragonette, Smash (2011): Hello – Single Edit
  • Mura Masa, Soundtrack To a Death (2014): I’ve Never Felt So Good
• Other references:
  • Madeon’s Adventure Machine
  • Chocolate Rain by Tay Zonday

The So Strangely Podcast is produced by Finn Upham, 2020. The closing music includes a sample of Diana Deutsch’s Speech-Song Illusion sound demo 1.

Music Education doctoral candidate Ethan Hein recommends “Equity and Music Education: Euphemisms, Terminal Naivety, and Whiteness” by Juliet Hess, published in Action, Criticism & Theory for Music Education, 2017. Ethan and Finn interview Dr. Juliet Hess about this study and whiteness in music education, and addressing systemic racism from within our areas of academia.

• [0:00:10] Intro with Ethan Hein
• [0:08:29] Interview: Dr. Juliet Hess, Background and Case Studies
• [0:18:50] Interview: Multiculturalism and Music
• [0:29:31] Interview: Whiteness in the Conservatory
• [0:36:19] Interview: Context and Implications
• [0:44:06] Interview: Future work
• [0:51:50] Closing with Ethan Hein

• Recommended article:
  • Hess, J. (2017). Equity and Music Education: Euphemisms, Terminal Naivety, and Whiteness. Action, Criticism & Theory for Music Education, 16(3). (HTML, PDF)
• Interviewee: Dr. Juliet Hess, Assistant Professor of Music Education at Michigan State University
• Co-host: Ethan Hein, Doctoral Candidate in Music Education at New York University (website, twitter)
• Sources cited in the discussion:
  • Kendrick Lamar’s Alright (youtube)
  • Chris Thile’s performance on Prairie Home companion is no longer available
  • Emma Stevens – Blackbird by The Beatles sung in Mi’kmaq (youtube)
    • Correction: this performance is from Cape Breton, Nova Scotia, not Newfoundland where there has been controversy around seal hunting. Both provinces are within the ancestral territory of Mi’kmaq People.
  • Bonilla-Silva, Eduardo. 2006. Racism without racists: Color-blind racism and the persistence of racial inequality in the United States. 2nd edition. Toronto, ON: Rowman & Littlefield Publishers, Inc. (Publisher page)
  • Juliet Hess (2018) Interrupting the symphony: unpacking the importance placed on classical concert experiences, Music Education Research, 20:1, 11-21, DOI: 10.1080/14613808.2016.1202224 (HTML)
  • Juliet Hess’ new book:
    • Hess, Juliet. (2019) Music Education for Social Change: Constructing an Activist Music Education, Routledge (Publisher page)

The So Strangely Podcast is produced by Finn Upham, 2019. The closing music includes a sample of Diana Deutsch’s Speech-Song Illusion sound demo 1.

Four Music Science attendees of the 2018 meeting of the Society for Neuroscience join Finn to discuss their experience of the conference, their own projects, and other interesting research presented. PhD Candidates Avital Sternin, Andrew Chang, Dr. Keith Doelling, and Prof. Amy Belfi get into the neural processing of song, emotion and alzheimer’s, leadership in small ensembles, onset prediction in the auditory cortex and more. Get an inside view of how Music Science fits into the biggest Neuroscience conference according to the young scientists on the ground.

• [0:01:06] Introduction of panelists
• [0:03:12] Introduction of Society for Neuroscience Conference
• [0:07:11] Music Science at SfN and in Neuroscience
• [0:10:48] Avital’s project (introduced by Amy)
• [0:21:50] Andrew’s project (introduced by Keith)
• [0:33:18] Amy’s project (introduced by Avital)
• [0:44:04] Keith’s project (introduced by Andrew)

• SfN18 website and program
• Avital Sternin, PhD Candidate at The Brain and Mind Institute of The University of Western Ontario
  • Abstract, Poster for Identifying the neural correlates of Music Familiarity using a strict training paradigm by A. Sternin, A. M. Owen, J. A. Grahn.
• Andrew Chang, Ph.D. Candidate in Department of Psychology, Neuroscience & Behaviour at McMaster University
  • Abstract, Poster for Neural oscillatory mechanisms for interpersonal entrainment in music ensembles by A. Chang, P. Chrapka, D. Bosnyak, L. J. Trainor.
  • Associated paper: A. Chang, S.R. Livingstone, D. Bosnyak, and L. J. Trainor. Body sway reflects leadership in joint music performance. PNAS May 23, 2017 114 (21) E4134-E4141
• Prof. Amy Belfi, Department of Psychological Science at Missouri University of Science and Technology
  • Abstract, Poster for Music and emotion in Alzheimer’s disease by A. M. Belfi, A. Resche-Hernandez, E. Guzman-Velez, D. Tranel.
• Dr. Keith Doelling, Dept. of Psychology, Centre for Neural Science, New York University
  • Abstract, Poster for Assessing evoked and oscillatory components in cortical synchronization to music using computational models by K. Doelling, M.F. Assaneo, J. Rowland, D. Bevilacqua, B. Pesaran, D. Poeppel.
  • Associated paper: K. B. Doelling and D. Poeppel. Cortical entrainment to music and its modulation by expertise. PNAS November 10, 2015 112 (45) E6233-E6242
• Other SfN 2018 posters mentioned
  • Beat perception ability and familiarity with music alter gait in older adults during auditory cueing E. A. READY, J. D. HOLMES, J. S. GRAHN (and poster)
  • Finding the beat: A neuro-mechanistic model for rhythmic beat generation Á. BYRNE, A. BOSE, J. M. RINZEL
  •