Text-Free Prosody-Aware Generative Spoken Language Modeling

Eugene Kharitonov, Ann Lee, Adam Polyak, Yossi Adi, Jade Copet, Kushal Lakhotia, Tu Anh Nguyen, Morgane Riviere, Abdelrahman Mohamed, Emmanuel Dupoux, Wei-Ning Hsu


Abstract
Speech pre-training has primarily demonstrated efficacy on classification tasks, while its capability of generating novel speech, similar to how GPT-2 can generate coherent paragraphs, has barely been explored. Generative Spoken Language Modeling (GSLM) (CITATION) is the only prior work addressing the generative aspect of speech pre-training, which builds a text-free language model using discovered units. Unfortunately, because the units used in GSLM discard most prosodic information, GSLM fails to leverage prosody for better comprehension and does not generate expressive speech. In this work, we present a prosody-aware generative spoken language model (pGSLM). It is composed of a multi-stream transformer language model (MS-TLM) of speech, represented as discovered unit and prosodic feature streams, and an adapted HiFi-GAN model converting MS-TLM outputs to waveforms. Experimental results show that the pGSLM can utilize prosody to improve both prosody and content modeling, and also generate natural, meaningful, and coherent speech given a spoken prompt. Audio samples can be found at https://speechbot.github.io/pgslm. Codes and models are available at https://github.com/pytorch/fairseq/tree/main/examples/textless_nlp/pgslm.
Anthology ID:
2022.acl-long.593
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8666–8681
Language:
URL:
https://aclanthology.org/2022.acl-long.593
DOI:
10.18653/v1/2022.acl-long.593
Bibkey:
Cite (ACL):
Eugene Kharitonov, Ann Lee, Adam Polyak, Yossi Adi, Jade Copet, Kushal Lakhotia, Tu Anh Nguyen, Morgane Riviere, Abdelrahman Mohamed, Emmanuel Dupoux, and Wei-Ning Hsu. 2022. Text-Free Prosody-Aware Generative Spoken Language Modeling. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8666–8681, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Text-Free Prosody-Aware Generative Spoken Language Modeling (Kharitonov et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.593.pdf
Code
 pytorch/fairseq
Data
LibriSpeech