1 citations · 1 across the 1 of their papers we have counts for
3 papers
eess.AS2021★ 1 cited
ASR4REAL: An extended benchmark for speech models
Morgane Riviere, Jade Copet, Gabriel Synnaeve
Popular ASR benchmarks such as Librispeech and Switchboard are limited in the diversity of settings and speakers they represent. We introduce a set of benchmarks matching real-life…
cs.SD2021
Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
Adam Polyak, Yossi Adi, Jade Copet +5
We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representat…
cs.CL2021
Generative Spoken Language Modeling from Raw Audio
Kushal Lakhotia, Evgeny Kharitonov, Wei-Ning Hsu +8
We introduce Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and a set of m…