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

20 citations · 85 across the 16 of their papers we have counts for

collaborators
Showing 2021Show all

6 papers · 1 filter

cs.SD2021★ 10 cited

MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling

Yusong Wu, Ethan Manilow, Yi Deng +6

Musical expression requires control of both what notes are played, and how they are performed. Conventional audio synthesizers provide detailed expressive controls, but at the cost…

cs.SD2021

MT3: Multi-Task Multitrack Music Transcription

Josh Gardner, Ian Simon, Ethan Manilow +2

Automatic Music Transcription (AMT), inferring musical notes from raw audio, is a challenging task at the core of music understanding. Unlike Automatic Speech Recognition (ASR), wh…

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.SD2021★ 7 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…

cs.SD2021★ 20 cited

Sequence-to-Sequence Piano Transcription with Transformers

Curtis Hawthorne, Ian Simon, Rigel Swavely +2

Automatic Music Transcription has seen significant progress in recent years by training custom deep neural networks on large datasets. However, these models have required extensive…