activity
20192025
most citedSequence-to-Sequence Piano Transcription with Transformers

20 citations · 48 across the 11 of their papers we have counts for

collaborators
Showing cs.SDShow all

12 papers · 1 filter

cs.SD2025

Live Music Models

Lyria Team, Antoine Caillon, Brian McWilliams +33

We introduce a new class of generative models for music called live music models that produce a continuous stream of music in real-time with synchronized user control. We release M…

cs.SD20228 cited

The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling

Yusong Wu, Josh Gardner, Ethan Manilow +3

Data is the lifeblood of modern machine learning systems, including for those in Music Information Retrieval (MIR). However, MIR has long been mired by small datasets and unreliabl…

cs.SD2022

Improving Source Separation by Explicitly Modeling Dependencies Between Sources

Ethan Manilow, Curtis Hawthorne, Cheng-Zhi Anna Huang +2

We propose a new method for training a supervised source separation system that aims to learn the interdependent relationships between all combinations of sources in a mixture. Rat…

cs.SD2021

Deep Learning Tools for Audacity: Helping Researchers Expand the Artist's Toolkit

Hugo Flores Garcia, Aldo Aguilar, Ethan Manilow +2

We present a software framework that integrates neural networks into the popular open-source audio editing software, Audacity, with a minimal amount of developer effort. In this pa…

cs.SD2021

Unsupervised Source Separation By Steering Pretrained Music Models

Ethan Manilow, Patrick O'Reilly, Prem Seetharaman +1

We showcase an unsupervised method that repurposes deep models trained for music generation and music tagging for audio source separation, without any retraining. An audio generati…

cs.SD20217 cited

Leveraging Hierarchical Structures for Few-Shot Musical Instrument Recognition

Hugo Flores Garcia, Aldo Aguilar, Ethan Manilow +1

Deep learning work on musical instrument recognition has generally focused on instrument classes for which we have abundant data. In this work, we exploit hierarchical relationship…