Jesse Engel

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

TMLR

General-purpose, long-context autoregressive modeling with Perceiver AR

arXiv 2022

Multi-instrument Music Synthesis with Spectrogram Diffusion

arXiv 2022

HEAR: Holistic Evaluation of Audio Representations

arXiv 2022

MT3: Multi-Task Multitrack Music Transcription

mt3-multi-task-multitrack-music-transcription

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

midi-ddsp-detailed-control-of-musical

DDSP: Differentiable Digital Signal Processing

ICLR 2020 1

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

arXiv 2015

Curtis Hawthorne

Ethan Manilow

Ian Simon

Adam Roberts

Josh Gardner

Neil Zeghidour

Aarohi Srivastava

researcher

Aaron Courville

Abhinav Rastogi

researcher

Abhishek Rao