Zobrazeno 1 - 10
of 349
pro vyhledávání: '"O'reilly, Patrick"'
Neural codecs have demonstrated strong performance in high-fidelity compression of audio signals at low bitrates. The token-based representations produced by these codecs have proven particularly useful for generative modeling. While much research ha
Externí odkaz:
http://arxiv.org/abs/2410.11025
This work introduces Text2FX, a method that leverages CLAP embeddings and differentiable digital signal processing to control audio effects, such as equalization and reverberation, using open-vocabulary natural language prompts (e.g., "make this soun
Externí odkaz:
http://arxiv.org/abs/2409.18847
Autor:
O'Reilly, Patrick S.
Thesis: S.M. in Engineering and Management, Massachusetts Institute of Technology, Engineering Systems Division, System Design and Management Program, 2020
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 108
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 108
Externí odkaz:
https://hdl.handle.net/1721.1/145235
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 generation model is conditioned on an input mixture, producing a latent encodi
Externí odkaz:
http://arxiv.org/abs/2110.13071
Autor:
O'Reilly, Patrick, Varkkey, Helena
Publikováno v:
International Review of Modern Sociology, 2020 Jan 01. 46(1/2), 1-17.
Externí odkaz:
https://www.jstor.org/stable/48745002
Autor:
O'Reilly, Patrick, Anshari, Gusti, Sancho, Jonay Jovani, Jaya, Adi, Antang, Emmy, Antang, Corry, Evers, Stephanie, Evans, Chris, Wilson, Paul, Crout, Neil, Sjorgesten, Sofie, Upton, Caroline, Page, Sue
Publikováno v:
International Review of Modern Sociology, 2020 Jan 01. 46(1/2), 103-120.
Externí odkaz:
https://www.jstor.org/stable/48745006