Generative Spoken Dialogue Language Modeling

Generative Spoken Dialogue Language Modeling

AbstractWe introduce dGSLM, the first “textless” model able to generate audio samples of naturalistic spoken dialogues. It uses recent work on unsupervised spoken unit discovery coupled with a dual-tower transformer architecture with cross-attention trained on 2000 hours of two-chann...

Full description

Bibliographic Details
Main Authors: Tu Anh Nguyen, Eugene Kharitonov, Jade Copet, Yossi Adi, Wei-Ning Hsu, Ali Elkahky, Paden Tomasello, Robin Algayres, Benoît Sagot, Abdelrahman Mohamed, Emmanuel Dupoux
Format: Article
Language:English
Published: The MIT Press 2023-01-01
Series:Transactions of the Association for Computational Linguistics
Online Access:https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00545/115240/Generative-Spoken-Dialogue-Language-Modeling

Internet

https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00545/115240/Generative-Spoken-Dialogue-Language-Modeling

Similar Items