Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Hawthorne, Curtis"'
Autor:
Dieleman, Sander, Sartran, Laurent, Roshannai, Arman, Savinov, Nikolay, Ganin, Yaroslav, Richemond, Pierre H., Doucet, Arnaud, Strudel, Robin, Dyer, Chris, Durkan, Conor, Hawthorne, Curtis, Leblond, Rémi, Grathwohl, Will, Adler, Jonas
Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement. Their success hinges on the fact that the underlying physical phenomena are continuous. Fo
Externí odkaz:
http://arxiv.org/abs/2211.15089
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 unreliable labels. In this work, we propose to break this bottleneck using gene
Externí odkaz:
http://arxiv.org/abs/2209.14458
Autor:
Hawthorne, Curtis, Simon, Ian, Roberts, Adam, Zeghidour, Neil, Gardner, Josh, Manilow, Ethan, Engel, Jesse
An ideal music synthesizer should be both interactive and expressive, generating high-fidelity audio in realtime for arbitrary combinations of instruments and notes. Recent neural synthesizers have exhibited a tradeoff between domain-specific models
Externí odkaz:
http://arxiv.org/abs/2206.05408
Autor:
Roberts, Adam, Chung, Hyung Won, Levskaya, Anselm, Mishra, Gaurav, Bradbury, James, Andor, Daniel, Narang, Sharan, Lester, Brian, Gaffney, Colin, Mohiuddin, Afroz, Hawthorne, Curtis, Lewkowycz, Aitor, Salcianu, Alex, van Zee, Marc, Austin, Jacob, Goodman, Sebastian, Soares, Livio Baldini, Hu, Haitang, Tsvyashchenko, Sasha, Chowdhery, Aakanksha, Bastings, Jasmijn, Bulian, Jannis, Garcia, Xavier, Ni, Jianmo, Chen, Andrew, Kenealy, Kathleen, Clark, Jonathan H., Lee, Stephan, Garrette, Dan, Lee-Thorp, James, Raffel, Colin, Shazeer, Noam, Ritter, Marvin, Bosma, Maarten, Passos, Alexandre, Maitin-Shepard, Jeremy, Fiedel, Noah, Omernick, Mark, Saeta, Brennan, Sepassi, Ryan, Spiridonov, Alexander, Newlan, Joshua, Gesmundo, Andrea
Recent neural network-based language models have benefited greatly from scaling up the size of training datasets and the number of parameters in the models themselves. Scaling can be complicated due to various factors including the need to distribute
Externí odkaz:
http://arxiv.org/abs/2203.17189
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. Rather than independently estimating each source from a mix, we reframe t
Externí odkaz:
http://arxiv.org/abs/2203.15140
Autor:
Hawthorne, Curtis, Jaegle, Andrew, Cangea, Cătălina, Borgeaud, Sebastian, Nash, Charlie, Malinowski, Mateusz, Dieleman, Sander, Vinyals, Oriol, Botvinick, Matthew, Simon, Ian, Sheahan, Hannah, Zeghidour, Neil, Alayrac, Jean-Baptiste, Carreira, João, Engel, Jesse
Real-world data is high-dimensional: a book, image, or musical performance can easily contain hundreds of thousands of elements even after compression. However, the most commonly used autoregressive models, Transformers, are prohibitively expensive t
Externí odkaz:
http://arxiv.org/abs/2202.07765
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), which typically focuses on the words of a single speaker, AMT often requ
Externí odkaz:
http://arxiv.org/abs/2111.03017
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 domain-specific design of network architectures, input/output represe
Externí odkaz:
http://arxiv.org/abs/2107.09142
Score-based generative models and diffusion probabilistic models have been successful at generating high-quality samples in continuous domains such as images and audio. However, due to their Langevin-inspired sampling mechanisms, their application to
Externí odkaz:
http://arxiv.org/abs/2103.16091
We introduce the Expanded Groove MIDI dataset (E-GMD), an automatic drum transcription (ADT) dataset that contains 444 hours of audio from 43 drum kits, making it an order of magnitude larger than similar datasets, and the first with human-performed
Externí odkaz:
http://arxiv.org/abs/2004.00188