Pythonic AI

Textless NLP: Generating expressive speech from raw audio

Generative Spoken Language Model (GSLM), the first high-performance NLP model that leverages recent breakthroughs in representation learning, allowing it to work directly from only raw audio signals, without any labels or text.

Link

#deeplearning #nlp #selfsupervised #facebook

@pythonicAi

www.tgoop.com/pythonicAI/1183

366 viewsSoroush Hashemifar, Sep 12, 2021 at 13:51

Textless NLP: Generating expressive speech from raw audio

Generative Spoken Language Model (GSLM), the first high-performance NLP model that leverages recent breakthroughs in representation learning, allowing it to work directly from only raw audio signals, without any labels or text.

Link

#deeplearning #nlp #selfsupervised #facebook

@pythonicAi

BY Pythonic AI