Nicholas J. Bryan

Senior Research Scientist
Audio Research Group, Adobe Research
San Francisco, CA

email: njb at ieee dot org


About: I am a senior research scientist and head of the Music AI group at Adobe Research. My research interests include audio and music, generative AI, and signal processing. I received my PhD and MA from CCRMA, Stanford University and MS in Electrical Eng., also from Stanford. Before that, I received my Bachelor of Music and BS in Electrical Eng. with summa cum laude, general honors, and departmental honors at the U. of Miami-FL. I have received 2 best paper awards, 1 AES Graduate Design Gold award, and 1 best reviewer award. I was general co-chair of WASPAA 2023, a 2x elected member of the IEEE AASP TC, and am an Adobe distinguished inventor.


News

[03/2024] MusicHiFi: Fast High-Fidelity Stereo Vocoding! arXiv | web | video
[02/2024] Project Music GenAI Control Adobe News!
[01/2024] DITTO: Diffusion Inference-time T-Optimization for Music Generation! arXiv | web | video
[11/2023] Music ControlNet: Multiple Time-varying Controls for Music Generation! arXiv | web | video
[10/2023] IEEE WASPAA 2023 General Co-Chair (w/Minje Kim).
[11/2022] Meta-AF: Meta-learning for Adaptive Filters! IEEE TASLP arXiv | web | code | video
[11/2022] Re-elected to the IEEE SPS AASP Technical Committee (second-term).
[09/2022] DeepAFx-ST: Style Transfer of Audio Effects with Differentiable Signal Processing! arXiv | JAES paper | web | code | video


Adobe Internships

For current students, I offer research internships at Adobe Research in San Francisco, CA. Internships are typically during the summer months and for graduate students studying audio/music signal processing, machine learning, or related field. If you are interested, please send me an email with your CV and research interests in October-December before the given summer. My Adobe webpage is here.


Publications


"MusicHiFi: Fast High-Fidelity Stereo Vocoding"
G. Zhu J.-P. Caceres, Z. Duan, N. J. Bryan
Submitted to ArXiv, March, 2024.
(arXiv, web, video)

"DITTO: Diffusion Inference-time T-Optimization for Music Generation"
Z. Novack J. McAuley, T. Berg-Kirkpatrick, N. J. Bryan
Submitted to ArXiv, January, 2024.
(arXiv, web, video)

"Music ControlNet: Multiple Time-varying Controls for Music Generation"
S-L. Wu C. Donahue, S. Watanabe, N. J. Bryan
Submitted to IEEE Transactions on Audio, Speech, and Language Processsing (TASLP), November, 2023.
(arXiv, web, video)
"Meta-AF: Meta-learning for Adaptive Filters."
J. Casebeer N. J. Bryan, P. Smaragdis
IEEE Transactions on Audio, Speech, and Language Processsing (TASLP), January, 2022.
Presented at IEEE International Conf. on Acoustics, Speech, and Signal Processing (ICASSP), June, 2023.
(TASLP, arXiv, web, code, video)
"Style Transfer of Audio Effects with Differentiable Signal Processing."
C. J. Steinmetz, N. J. Bryan, J. D. Reiss,
Journal of the Audio Engineering Society (JAES), September, 2022.
Presented at 154th AES Europe Convention, May, 2023.
(arXiv, code, demo)
"Meta-learning for Adaptive Filters with Higher-order Frequency Dependencies."
J. Wu, J. Casebeer N. J. Bryan, P. Smaragdis,
IEEE Workshop on Acoustic Signal Enhancement (IWAENC), September, 2022.
(arXiv, code, demo)
"Don't Separate, Learn to Remix: End-to-End Neural Remixing with Joint Optimization."
H. Yang, S. Firodiya N. J. Bryan, M. Kim,
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022.
(arXiv, paper code)
"Emotion Embedding Spaces for Matching Music to Stories."
M. Won, J. Salamon N. J. Bryan, G. J. Mysore, X. Serra
International Society for Music Information Retrieval Conference (ISMIR), 2021.
(code, paper)
ISMIR Best Student Paper Award Winner
"Deep Embeddings and Section Fusion Improve Music Segmentation."
J. Salamon O. Nieto, N. J. Bryan,
International Society for Music Information Retrieval Conference (ISMIR), 2021.
(code, paper)
"Who Calls the Shots? Rethinking Few-Shot Learning for Audio."
Y. Wang, N. J. Bryan, J. Salamon M. Cartwright, J. P. Bello
IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2021.
(arXiv, data, code, paper, full talk)
IEEE WASPAA Special Best Paper Award Winner
"Auto-DSP: Learning to Optimize Acoustic Echo Cancellers."
J. Casebeer, N. J. Bryan P. Smaragdis,
IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2021.
(arXiv, web, code, paper, short talk, full talk)
"Differentiable Signal Processing with Black-Box Audio Effects."
M. A. Martínez Ramírez, O. Wang, P. Smaragdis, N. J. Bryan
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021.
(arXiv, web, code, ieee explore, paper long-talk)
"Few-shot Continual Learning for Audio Classification."
Y. Wang, N. J. Bryan, M. Cartwright, J.-P. Bello, J. Salamon
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021.
(paper, ieee explore)
"Context-aware Prosody Correction for Text-based Speech Editing."
M. Morrison, L. Rencker, Z. Jin, N. J. Bryan, J.P. Caceres, B. Pardo
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021.
(arXiv, web, paper)
"A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differences."
P. Manocha, A. Finkelstein, R. Zhang, N. J. Bryan, G. J. Mysore, Z. Jin
Interspeech, 2020.
(arXiv, web, code)
Interspeech Best Student Paper Finalist
"Controllable Neural Prosody Synthesis."
M. Morrison, Z. Jin, J. Salamon, N. J. Bryan, G. J. Mysore
Interspeech, 2020.
(paper | arXiv, web)
"Metric Learning vs Classification for Disentangled Music Representation Learning."
J. Lee, N. J. Bryan, J. Salamon, Z. Jin J. Nam
International Society for Music Information Retrieval (ISMIR), 2020.
(paper | arXiv | web)
"Few-shot Drum Transcription in Polyphonic Music."
Y. Wang, J. Salamon, M. Cartwright, N. J. Bryan, J.-P. Bello
International Society for Music Information Retrieval (ISMIR), 2020.
(paper | arXiv)
"Disentangled Multidimensional Metric Learning For Music Similarity."
J. Lee, N. J. Bryan, J. Salamon, Z. Jin J. Nam
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020.
(project page | paper | ieee link | arXiv | talk | data set)
"One-Shot Parametric Audio Production Style Transfer With Application to Frequency Equalization."
S. I. Mimilakis, N. J. Bryan, P. Smaragdis
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020.
(project page | paper | ieee link | talk)
"Few-Shot Sound Event Detection."
Y. Wang, J. Salamon, N. J. Bryan, J.-P. Bello
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020.
(paper | ieee link | talk)
"Impulse Response Data Augmentation and Deep Neural Networks For Blind Room Acoustic Parameter Estimation."
N. J. Bryan
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020.
(paper | ieee link | talk)
"Scene-Aware Audio Rendering via Deep Acoustic Analysis."
Z. Tang N. J. Bryan D. Li T. Langlois D. Manocha
IEEE VR Journal Track (TVCG), 2020.
(paper | ieee | arXiv | project page | video )
"ISSE: An Interactive Source Separation Editor."
N. J. Bryan, G. J. Mysore, G. Wang
Human Factors in Computing Systems (CHI), 2014.
(project page | paper | video)
"Interactive Sound Source Separation."
N. J. Bryan.
Stanford University, Stanford, CA, USA. March, 2014.
(PhD Thesis)

* Tutorial on single-channel source separation (slides + code)
* ISSE: An Interactive Source Separation Editor (talk 1) (talk 2)
* Software (link)
* C++ code (link)
* Matlab code (link)
* Demos (link)
* SiSEC results (link)
* Publications (link)
AES Graduate Student Design Gold Award
"Source Separation of Polyphonic Music With Interactive User-Feedback on a Piano Roll Display."
N. J. Bryan, G. J. Mysore, G. Wang
International Society for Music Information Retrieval Conference (ISMIR), 2013.
(web | paper)
"An Efficient Posterior Regularized Latent Variable Model for Interactive Sound Source Separation."
N. J. Bryan, G. J. Mysore
International Conference on Machine Learning (ICML), 2013.
(web | paper | sisec | Adobe MAX | poster | slides)
"Interactive Refinement of Supervised and Semi-Supervised Sound Source Separation Estimates."
N. J. Bryan, G. J. Mysore
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2013.
(web | pre-print | poster)
"Interactive User-Feedback for Sound Source Separation."
N. J. Bryan, G. J. Mysore
International Conf. on Intelligent User-Interfaces, Workshop on Interative Machine Learning, 2013.
(web | abstract)
"User-Guided Variable-Rate Time-Stretching Via Stiffness Control."
N. J. Bryan, J. Herrera, G. Wang
International Conference on Digital Audio Effects (DAFX), 2012.
(web | paper | slides (long) | slides (short) )
"Clustering and Synchronizing Multi-Camera Video via Landmark Cross-Correlation"
N. J. Bryan, P. Smaragdis, G. J. Mysore
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2012.
(paper | poster | pre-print | slides, Adobe MAX)
"Musical Influence Network Analysis and Rank of Sampled-Based Music."
N. J. Bryan, G. Wang
International Society for Music Information Retrieval Conference (ISMIR), 2011.
(paper | whosampled | slides)
"Two Turntables and a Mobile Phone."
N. J. Bryan, G. Wang
International Conference on New Interfaces for Musical Expression (NIME), 2011.
(paper | slides | web)
"Instinct-Based Mating in Genetic Algorithms Applied to the Tuning of 1-NN Classifiers."
T. Quirino, M. Kubat, N. J. Bryan
IEEE Transactions on Knowledge and Data Engineering (TKDE), December, 2010.
(paper)
"Methods For Extending Room Impulse Responses Beyond Their Noise Floor."
N. J. Bryan, J. S. Abel
Audio Engineering Society Convention (AES), 2010.
(paper | slides | web)
"Impulse Response Measurements in the Presence of Clock Drift."
N. J. Bryan, M. A. Kolar, J. S. Abel
Audio Engineering Society Convention (AES), 2010.
(paper | slides | web)
"Estimating Room Impulse Responses from Recorded Balloon Pops."
J. S. Abel N. J. Bryan, P. Huang, M. A. Kolar, B. Pentcheva,
Audio Engineering Society Convention (AES), 2010.
(paper | slides | web)
"Approximating Measured Reverberation Using A Hybrid Fixed/Switched Convolution Structure."
K. Lee, N. J. Bryan, J. S. Abel
International Conference on Digital Audio Effects (DAFX), 2010.
(paper | web)
"MoMu: A Mobile Music Toolkit."
N. J. Bryan, J. Herrera, J. Oh, G. Wang
International Conference on New Interfaces for Musical Expression (NIME), 2010.
(paper | web | speaker hands | slides)
"Evolving The Mobile Phone Orchestra."
J. Oh, J. Herrera, N. J. Bryan, L. Dahl, G. Wang
International Conference on New Interfaces for Musical Expression (NIME), 2010.
(paper | speaker hands)
"A Configurable Microphone Array with Acoustically Transparent Omnidirectional Elements."
J. S. Abel N. J. Bryan, T. Skare, M. A. Kolar, P. Huang, D. Mostowfi, J. O. Smith III
Audio Engineering Society Convention (AES), 2009.
(paper | poster | web)
"Stanford Laptop Orchestra (SLOrk)."
G. Wang N. J. Bryan, J. Oh, R. Hamilton,
International Computer Music Conference (ICML), 2009.
(pdf: paper | web | speakers )


Teaching & Talks

"Learning to Control Signal Processing Algorithms with Deep Learning."
N. J. Bryan
Women in Music Information Retreival (WiMIR) Workshop & Project Guide. (Invited Talk)
Online, USA 2021.
Slides

"Tutorial on Single-Channel Source Separation."
N. J. Bryan, Dennis Sun, Eunjoon Cho,
Stanford University. Stanford, USA 2013.
slides + code

"Building the Stanford Laptop Orchestra Speaker Arrays."
N. J. Bryan,
Stanford University. Stanford, USA 2009.
Link



Press

"Audio Layers."
Adobe TV May 8th, 2013.
In collaboration with Gautham Mysore at Adobe Research.
"Automatic Synchronization of Crowd Sourced Videos."
Adobe TV October, 2011.
In collaboration with Gautham Mysore and Paris Smaragdis at Adobe's Advanced Technology Labs.
"Smartphone turntables put new spin on DJing."
NewScientist, May, 2011.

In addition to:
OH GIZMO, Geek.com, Engadget, DVICE, Gizmodo, musicradar.com, tecca, All about tech & gadgets, FUTUREMUSIC, InFlexWeTrust!, and Skratchworx.
"Air Instruments only."
The Stanford Daily, October 28, 2010. (link)
"From Pocket to Stage, Music in the Key of iPhone."
New York Times (Front Page), December 4, 2009. (link)
"Make-TV: Computer Making Music."
PBS TV, February 28, 2009. (link)
"The music machines."
The Stanford Daily, October, 2008. (comments regarding the slork speaker design) (link)
"Rhythm and Cubes."
Stanford Magazine, July, 2008. (link)
"Stanford Students invent new music."
Local ABC TV Drive to Discover (San Francisco, CA), April 6, 2008. (link)