publications

@inproceedings{watcharasupat_separate_2026,

title = {Separate This, and All of these Things Around It: Music Source Separation via Hyperellipsoidal Queries},

author = {Karn N. Watcharasupat and Alexander Lerch},

url = {http://arxiv.org/abs/2501.16171},

doi = {10.48550/arXiv.2501.16171},

year  = {2026},

date = {2026-01-01},

urldate = {2026-01-01},

booktitle = {Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

publisher = {Institute of Electrical and Electronics Engineers (IEEE)},

address = {Barcelona, Spain},

abstract = {Music source separation is an audio-to-audio retrieval task of extracting one or more constituent components, or composites thereof, from a musical audio mixture. Each of these constituent components is often referred to as a "stem" in literature. Historically, music source separation has been dominated by a stem-based paradigm, leading to most state-of-the-art systems being either a collection of single-stem extraction models, or a tightly coupled system with a fixed, difficult-to-modify, set of supported stems. Combined with the limited data availability, advances in music source separation have thus been mostly limited to the "VDBO" set of stems: textbackslashtextitvocals, textbackslashtextitdrum, textbackslashtextitbass, and the catch-all textbackslashtextitothers. Recent work in music source separation has begun to challenge the fixed-stem paradigm, moving towards models able to extract any musical sound as long as this target type of sound could be specified to the model as an additional query input. We generalize this idea to a textbackslashtextitquery-by-region source separation system, specifying the target based on the query regardless of how many sound sources or which sound classes are contained within it. To do so, we propose the use of hyperellipsoidal regions as queries to allow for an intuitive yet easily parametrizable approach to specifying both the target (location) as well as its spread. Evaluation of the proposed system on the MoisesDB dataset demonstrated state-of-the-art performance of the proposed system both in terms of signal-to-noise ratios and retrieval metrics.},

keywords = {audio signal processing, audio source separation, Computer Science - Information Retrieval, Computer Science - Machine Learning, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hung_transcription_2021,

title = {Transcription Is All You Need: Learning To Separate Musical Mixtures With Score As Supervision},

author = {Yun-Ning Hung and Gordon Wichern and Jonathan Le Roux},

url = {https://ieeexplore.ieee.org/abstract/document/9413358/authors#authors},

doi = {10.1109/ICASSP39728.2021.9413358},

year  = {2021},

date = {2021-06-01},

urldate = {2024-02-08},

booktitle = {ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

pages = {46\textendash50},

abstract = {Most music source separation systems require large collections of isolated sources for training, which can be difficult to obtain. In this work, we use musical scores, which are comparatively easy to obtain, as a weak label for training a source separation system. In contrast with previous score-informed separation approaches, our system does not require isolated sources, and score is used only as a training target, not required for inference. Our model consists of a separator that outputs a time-frequency mask for each instrument, and a transcriptor that acts as a critic, providing both temporal and frequency supervision to guide the learning of the separator. A harmonic mask constraint is introduced as another way of leveraging score information during training, and we propose two novel adversarial losses for additional fine-tuning of both the transcriptor and the separator. Results demonstrate that using score information outper-forms temporal weak-labels, and adversarial structures lead to further improvements in both separation and transcription performance.},

note = {ISSN: 2379-190X},

keywords = {audio source separation, Conferences, Instruments, music, music transcription, Particle separators, Source separation, Time-frequency analysis, Training, weakly-labeled data, weakly-supervised separation},

pubstate = {published},

tppubtype = {inproceedings}

}