-
Unmixer: Loop Extraction with Repetition, with Dr. Jordan Smith and Tim de Reuse
Podcast: Play in new window | Download (Duration: 1:00:10 — 55.7MB)
Subscribe: Spotify | RSS | More
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.
Time Stamps
- [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
Show notes
- 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
Credits
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.
-
Why So Strangely?
One of the most famous examples of music science research was the discovery of the Speech-Song Illusion by Diana Deutsch. Turns out that looping a short clip of someone talking, playing the same exact utterance over and over, changes how we processing the sound. What is initially perceived as a simple excerpt of speech becomes a rhythmic, melodic song.
Deutsch first demonstrated this with a clip of her own speech from the sentence:
“The sounds as they appear to you are not only different from those that are really present, but they sometimes behave so strangely as to seem quite impossible.”
She looped the phrase “sometimes behave so strangely” in several clever experiments.
In the years since, “Sometimes behave so strangely” has become a catch phrase in music cognition, and many people no longer need an audio reference to recall this curious and persistent effect.
And beside some famous words, this podcast is called “So Strangely” because music science research often behaves in unexpected ways.
-
Welcome to the So Strangely Podcast
Hello and welcome to the So Strangely Podcast, a new podcast on recent research in Music Science.
What is music science? That is a good question. Its the array of empirically motivated work on the stuff of music, or so we are defining it.
- Neuroscience of embodied perception? Sure.
- Corpus studies of chord progressions? Yup.
- Listeners subjective experiences of concert performances? Of course.
- Music pedagogy? Yes!
- Automatic chord detection? I should hope so.
- Origins of music? Definitely.
I’m Finn, host and producer, but the programming of this podcast isn’t just up to me. So Strangely will be sharing work that other music academics recommend, recent publications they want their peers to hear about.
Every episode, I’ll have another music academic on as a co-host to interview the lead researcher on a recently published project. My co-host is here to talk inside baseball, get into the nitty-gritty of the research as an expert. I’ll be there to help translate for those of us in adjacent disciplines.
Because here is the thing: music science is so interdisciplinary, we often have trouble keeping track of what’s going on in other areas. It can even be a struggle to understand what this other group of academics are so excited about. With this two pronged approach, So Strangely will try to bridge those gaps and helps us within the broader music science research community follow and appreciate what’s new next door.
Here is the warning: this podcast is pitched for people into music and science, not for the general population. We won’t be explaining scales every episode, or breaking down the basics of the experimental method. You don’t need a PhD to follow (I mean, I don’t have a PhD… yet) but some prior contact with music science research will help.
And if there is a recent publication you want more people to know about and you are interested in being on the show, pitch it to us!
Full episodes are in the works, with recordings and scheduling and editing underway. For now, follow us on twitter, and check back soon so you don’t miss out how music science research sometimes behaves so strangely.
