06.11 - Alex François wins ICMC Best Paper Award

Alex François who created the MuSA.RT and MIMI software, and whose software architecture style powered the ESP application, wins the Best Paper Award at the 50th International Computer Conference in Boston, Massachusetts, for his paper, "Resonate: Efficient Low Latency Spectral Analysis of Audio Signal".

Alexandre R.J. François’ research focuses on the modeling and design of interactive (software) systems, as an enabling step towards the understanding of perception and cognition. His interdisciplinary research projects explore interactions within and across music, vision, visualization and video games. He was a 2007-2008 Fellow of the Radcliffe Institute for Advanced Study at Harvard University, where he co-lead a music research cluster on Analytical Listening Through Interactive Visualization.

From 2004 to 2010, François was a Research Assistant Professor of Computer Science in the USC Viterbi School of Engineering at the University of Southern California. In 2010, he was a Visiting Associate Professor of Computer Science at Harvey Mudd College. In 2008-2009, he was a Visiting Assistant Professor in the Department of Computer Science at Tufts University. From 2001 to 2004 he was a Research Associate with the Integrated Media Systems Center and with the Institute for Robotics and Intelligent Systems, both at USC.

François received the Diplôme d’Ingénieur from the Institut National Agronomique Paris-Grignon (France) in 1993, the Diplôme d’Etudes Approfondies (M.S.) from the University Paris IX – Dauphine (France) in 1994, and the M.S. and Ph.D. degrees in Computer Science from USC in 1997 and 2000 respectively.

Resonate: Efficient Low Latency Spectral Analysis of Audio Signal

Abstract:This paper describes Resonate, an original low latency, low memory footprint, and low computational cost algorithm to evaluate perceptually relevant spectral information from audio signals. The fundamental building block is a resonator model that accumulates the signal contribution around its resonant frequency in the time domain, using the Exponentially Weighted Moving Average (EWMA).A compact, iterative formulation of the model affords computing an update at each signal input sample, requiring no buffering and involving only a handful of arithmetic operations. Consistently with on-line perceptual signal analysis, the EWMA gives more weight to recent input values, whereas the contributions of older values decay exponentially. A single parameter governs the dynamics of the system. Banks of such resonators, independently tuned to geometrically spaced resonant frequencies allow to compute an instantaneous, perceptually relevant estimate of the spectral content of an input signal in real-time. Both memory and per-sample computational complexity of such a bank are linear in the number of resonators, and independent of the number of input samples processed, or duration of processed signal. Furthermore, since the resonators are independent, there is no constraint on the tuning of their resonant frequencies or time constants, and all per sample computations can be parallelized across resonators. The cumulative computational cost for a given duration increases linearly with the number of input samples processed. The low latency afforded by Resonate opens the door to real-time music and speech applications that are out of the reach of FFT-based methods. The efficiency of the approach could reduce computational costs and inspire new designs for low-level audio processing layers in machine learning systems.

06.09 - Anna Huang gives ICMC Keynote

Anna Huang is a keynote speaker at the 50th International Computer Music Conference held in Boston, Massachusetts, from 8-14 June 2025.

“Algorithms and Interaction for Human AI Creative Partnerships”

Monday, June 9, 3:30pm – 4:30pm
Blackman Auditorium, Northeastern University

Cheng-Zhi Anna Huang 黃成之
Assistant Professor of Music
Assistant Professor of Electrical Engineering and Computer Science
Music and Theater Arts
School of Humanities, Arts and Social Sciences
Massachusetts Institute of Technology

In Fall 2024, Cheng-Zhi Anna Huang 黃成之 started a faculty position at Massachusetts Institute of Technology (MIT), with a shared position between Electrical Engineering and Computer Science (EECS) and Music and Theater Arts (MTA). For the past 8 years, she has been a researcher at Magenta in Google Brain and then Google DeepMind, working on generative models and interfaces to support human-AI partnerships in music making.

Anna Huang is the creator of the Machine Learning (ML) model Coconet that powered Google’s first AI Doodle, the Bach Doodle. In two days, Coconet harmonized 55 million melodies from users around the world. In 2018, she created Music Transformer, a breakthrough in generating music with long-term structure, and the first successful adaptation of the transformer architecture to music. Huang’s International Conference on Learning Representations (ICLR) paper is currently the most cited paper in music generation.

Anna Huang was a Canadian Institute for Advanced Research (CIFAR) AI Chair at Mila (Montreal Institute for Learning Algorithms, now Mila Quebec AI Institute), and continues to hold an adjunct professorship at the University of Montreal. Huang was a judge then organizer for the AI Song Contest 2020-22. She did her PhD at Harvard University, master’s at the MIT Media Lab, and a dual bachelor’s at the University of Southern California in music composition and CS.

09.27 - Anna Huang Assistant Professor @ MIT

Anna Huang, MuCoaCo alum, joins MIT's departments of Electrical Engineering and Computer Science and Music and Theater Arts as an assistant professor in September 2024 after eight years with Google Brain and DeepMind where she spearheaded efforts in generative modelling and reinforcement learning, and human-computer interaction in support of human-AI musical partnerships. Anna is creator of Music Transformer and Coconet, which powered the Bach Google Doodle. She holds a Canada CIFAR AI Chair at Mila. Anna holds a BM in music composition and BS in computer science from the University of Southern California, an SM from MIT, and a PhD from Harvard University.

At MIT, Anna is collaborating with Eran Egozy to devlop and launch MIT's new Music Technology and Computation Graduate Program at the intersection of music, computing, and technology. The program comprises of two two-semester master's degrees – a thesis-based Master of Science program available only to MIT undergraduates, and a coursework-based Master of Applied Science open to all students – and a PhD in MIT's School of Engineering.

“As a composer turned AI researcher who specializes in generative music technology, my long-term goal is to develop AI systems that can shed new light on how we understand, learn, and create music, and to learn from interactions between musicians in order to transform how we approach human-AI collaboration,” says Huang. “This new program will let us further investigate how musical applications can illuminate problems in understanding neural networks, for example.”

10.28 - Distributed Immersive Performance Videos Online

Years ago, at the Integrated Media Systems Center at the University of Southern California, we embarked on a series of Distributed Immersive Performance experiments to determine the effect of network latency on ensemble performance. Building on earlier experiments, these were the first of their kind to use rhythmic and fast classical chamber music to test the limits of collaborative performance over the Internet.  The results and findings were reported in numerous publications including ACM TOMM and proceedings of ACM MM, AES, NASM, and CENIC.

Over the years, these videos have been shown at numerous conferences and invited lectures. In response to requests for these videos, they have been shared online: documentation of the scientific experiments that led to the discovery that tolerance to network latency can be extended by enforcing a common clock, in this case, by delaying players' feedback from their own instruments to lineup with the signal arriving from their partner.


Setup A: Delays: vimeo.com/187646226
This video shows the increasing difficulty in synchronizing over increasing delays.


Setup A: Perspectives: vimeo.com/187647682
This video shows the difference in experience of delay from different perspectives.


Setup A: Commentaries: vimeo.com/189241592
This video shows the players commenting on the experience of playing with delay.


Setup B: vimeo.com/189272144
This video shows the solution we came up with---delaying each players' feedback from their own instrument.



Credits

Elaine Chew, experiment design and analysis
Alexandre R. J. François, software architecture
Christos Kyriakakis, spatial audio
Christos Papadopoulos, audio streaming
Alexander A. Sawchuk, project coordinator
Vely Stoyanova and Ilya Tosheff, performances
Roger Zimmerman, databases

Anja Volk, systematic musicological analysis

Carley Tanoue, performance data analysis
Dwipal Desai, databases
Moses Pawar, databases
Rishi Sinha, audio streaming
Will Meyer, filming and video editing

This material is based upon work supported by the National Science Foundation under grant no. 0321377 at the Integrated Media Systems Center, an NSF Engineering Research Center at the Viterbi School of Engineering, University of Southern California, Los Angeles, California, USA. nsf.gov/awardsearch/showAward?AWD_ID=0321377

09.09 - Isaac Schankler Assistant Professor @ Cal Poly Pomona

Isaac Schankler --> isaacschankler.com

Isaac Schankler, affiliated artist / postdoctoral research affiliate at the Music Computation and Cognition Lab at the University of Southern California (USC), and visiting scholar at the Music Performance and Expression Lab at QMUL's Centre for Digital Music (C4DM) has accepted a position as Assistant Professor of Music Industry Studies at Cal Poly Pomona in California, USA.

Congratulations, Isaac!  A composer, accordionist, and electronic musician, Isaac's electronic-acoustic composition Pheremone has received glowing reviews on Fanfare Magazine, his generative game music techniques have been reviewed on Billboard and presented at GameSoundCon, and he is founder and artistic director of People Inside Electronics in Los Angeles.  He is also an erudite writer of opinion pieces for NewMusicBox and was winner of 2013 was a winner of the ASCAP Deems Taylor Award for excellence in music journalism.

Photos of Cal Poly Pomona by Isaac Schankler:

08.01 - Ching-Hua Chuan promoted to Associate Professor @ UNF

Ching-Hua Chuan, an alumnus of the Music Computation and Cognition Laboratory at the University of Southern California, has received tenure and been promoted to Associate Professor in the School of Computing at the University of North Florida. As in most institutions in the United States, academics on tenure track in computer science (and most engineering fields) are hired as assistant professors without tenure (in a probationary period), and are evaluated after five years for promotion to associate professor with tenure in the sixth year in a highly competitive process.  Congratulations, Ching-Hua!

Ching-Hua is received her PhD from the Department of Computer Science at USC, where she received a Digital Dissertation Award and was elected to Phi Kappa Phi honor society. Her research interests center on artificial intelligence and machine learning, and her projects range from style-specific music harmonization to sign language recognition. She is recipient of a Grace Hopper Celebration Best New Investigator Paper Award, and her work has been featured on Foxnews, MSNBC, the Telegraph, the Miami Herald, and the IEEE Intelligent Systems Magazine. A innovative educator, she is also recipient of UNF's Outstanding Undergraduate Teaching Award and has developed new courses on music informatics and on gaming and mobile app development.

Read more about Ching-Hua's work at www.unf.edu/~c.chuan.

09.26 - Academic Minute Features MuCoaCo Alum Ching-Hua Chuan

MuCoaCo alum, Ching-Hua Chuan, Assistant Professor of Computing at the University of North Florida speaks on Composing with Computers on The Academic Minute with Lynn Pasquerella, President of Mount Holyoke College.  The Academic Minute features a different professor each day, giving anecdotes and updates on groundbreaking scientific research.

Ching-Hua Chuan's segment aired today on WAMC Public Radio in New York and on more than 60 radio stations across the United States.  Hear it at:
academicminute.org/2014/09/ching-hua-chuan-university-of-north-florida-composing-with-computers