Curtis Hawthorne

Google (United States) — United States

Computer Science · Physical Sciences

17h-index1.4kcitations37works0.02yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Music and Audio Processing(29), Music Technology and Sound Studies(24), Neuroscience and Music Perception(7), Generative Adversarial Networks and Image Synthesis(6), Speech and Audio Processing(6)

Publications37 total

Multi-instrument Music Synthesis with Spectrogram Diffusion
Zenodo (CERN European Organization for Nuclear Research)·2022· 4 citedOpen Access
Scaling Polyphonic Transcription with Mixtures of Monophonic Transcriptions
Zenodo (CERN European Organization for Nuclear Research)·2022· 2 citedOpen Access
Continuous diffusion for categorical data
arXiv (Cornell University)·2022· 21 citedOpen Access
The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling
arXiv (Cornell University)·2022· 8 citedOpen Access
Multi-instrument Music Synthesis with Spectrogram Diffusion
arXiv (Cornell University)·2022· 15 citedOpen Access
Improving Source Separation by Explicitly Modeling Dependencies between Sources
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)·2022· 3 cited
Scaling Up Models and Data with $\texttt{t5x}$ and $\texttt{seqio}$
arXiv (Cornell University)·2022· 48 citedOpen Access
Improving Source Separation by Explicitly Modeling Dependencies Between Sources
arXiv (Cornell University)·2022Open Access
General-purpose, long-context autoregressive modeling with Perceiver AR
arXiv (Cornell University)·2022· 34 citedOpen Access
Sequence-to-Sequence Piano Transcription with Transformers
Zenodo (CERN European Organization for Nuclear Research)·2021· 6 citedOpen Access
MT3: Multi-Task Multitrack Music Transcription
arXiv (Cornell University)·2021· 4 citedOpen Access
Sequence-to-Sequence Piano Transcription with Transformers
arXiv (Cornell University)·2021· 20 citedOpen Access
Symbolic Music Generation with Diffusion Models
arXiv (Cornell University)·2021· 9 citedOpen Access
MAESTRO
2020Open Access
MAESTRO
Zenodo (CERN European Organization for Nuclear Research)·2020Open Access
Self-supervised Pitch Detection by Inverse Audio Synthesis
2020· 10 cited
Expanded Groove MIDI Dataset
Zenodo (CERN European Organization for Nuclear Research)·2020Open Access
Expanded Groove MIDI Dataset
Zenodo (CERN European Organization for Nuclear Research)·2020Open Access
Improving Perceptual Quality of Drum Transcription with the Expanded Groove MIDI Dataset
arXiv (Cornell University)·2020· 14 citedOpen Access
Expanded Groove MIDI Dataset
Zenodo (CERN European Organization for Nuclear Research)·2020Open Access
page 1 of 2Next →

Frequent Co-authors

Jesse Engel(28), Ian Simon(22), Douglas Eck(15), Adam P. Roberts(15), Cheng-Zhi Anna Huang(13), Ethan Manilow(9), Sander Dieleman(8), Monica Dinculescu(7), Erich Elsen(7), Andriy Stasyuk(6), Noam Shazeer(5), Colin Raffel(5), Ashish Vaswani(4), Jakob Uszkoreit(4), Lee Callender(4), Andrew M. Dai(3), Matthew D. Hoffman(3), Adam Roberts(3), Neil Zeghidour(3), Rigel Swavely(3)