Generative Spoken Dialogue Language Modeling
Transactions of the Association for Computational Linguistics · 14.03.2023 · 11 · 250-266
DOI: 10.1162/tacl_a_00545 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 14.03.2023. Verfasst von Tu Anh Nguyen und 10 weiteren Autor:innen. Die Arbeit wurde bisher 50-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We 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-channel raw conversational audio (Fisher dataset) without any text or labels. We show that our model is able to generate speech, laughter, and other paralinguistic signals in the two channels simultaneously and reproduces more naturalistic and fluid turn taking compared to a text-based cascaded model.1,2
Zitieren
APA
Nguyen, T. A., Kharitonov, E., Copet, J., Adi, Y., Hsu, W., Elkahky, A., Tomasello, P., Algayres, R., Sagot, B., Mohamed, A., & Dupoux, E. (2023). Generative Spoken Dialogue Language Modeling. Transactions of the Association for Computational Linguistics, 11, 250-266. https://doi.org/10.1162/tacl_a_00545
Vancouver
Nguyen TA, Kharitonov E, Copet J, Adi Y, Hsu W, Elkahky A, et al. Generative Spoken Dialogue Language Modeling. Transactions of the Association for Computational Linguistics. 2023;11:250-266. doi:10.1162/tacl_a_00545
BibTeX
@article{Nguyen2023,
author = {Nguyen, Tu Anh and Kharitonov, Eugene and Copet, Jade and Adi, Yossi and Hsu, Wei-Ning and Elkahky, Ali and Tomasello, Paden and Algayres, Robin and Sagot, Benoît and Mohamed, Abdelrahman and Dupoux, Emmanuel},
title = {Generative Spoken Dialogue Language Modeling},
journal = {Transactions of the Association for Computational Linguistics},
year = {2023},
volume = {11},
pages = {250--266},
doi = {10.1162/tacl_a_00545}
}
EUVIMED