@inproceedings{fu-etal-2024-wav2vec,
title = "wav2vec-{S}: Adapting Pre-trained Speech Models for Streaming",
author = "Fu, Biao and
Fan, Kai and
Liao, Minpeng and
Chen, Yidong and
Shi, Xiaodong and
Huang, Zhongqiang",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.681",
doi = "10.18653/v1/2024.findings-acl.681",
pages = "11465--11480",
abstract = "Pre-trained speech models, such as wav2vec 2.0, have significantly advanced speech-related tasks, including speech recognition and translation. However, their applicability in streaming scenarios is limited because these models are trained on complete utterances, leading to a mismatch with incremental streaming inputs. This paper identifies three critical design aspects within the architecture of wav2vec 2.0 and proposes a novel model, wav2vec-S, which incorporates simple modifications to ensure consistent speech representations during both training and inference phases for streaming speech inputs. Furthermore, we demonstrate that wav2vec-S models can be efficiently adapted from pre-trained wav2vec 2.0 models through continued pre-training and effectively finetuned to meet various latency requirements in downstream applications. Experiments on speech recognition and translation tasks show that wav2vec-S outperforms strong baseline models and achieves a superior balance between quality and latency.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fu-etal-2024-wav2vec">
<titleInfo>
<title>wav2vec-S: Adapting Pre-trained Speech Models for Streaming</title>
</titleInfo>
<name type="personal">
<namePart type="given">Biao</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minpeng</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yidong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodong</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongqiang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained speech models, such as wav2vec 2.0, have significantly advanced speech-related tasks, including speech recognition and translation. However, their applicability in streaming scenarios is limited because these models are trained on complete utterances, leading to a mismatch with incremental streaming inputs. This paper identifies three critical design aspects within the architecture of wav2vec 2.0 and proposes a novel model, wav2vec-S, which incorporates simple modifications to ensure consistent speech representations during both training and inference phases for streaming speech inputs. Furthermore, we demonstrate that wav2vec-S models can be efficiently adapted from pre-trained wav2vec 2.0 models through continued pre-training and effectively finetuned to meet various latency requirements in downstream applications. Experiments on speech recognition and translation tasks show that wav2vec-S outperforms strong baseline models and achieves a superior balance between quality and latency.</abstract>
<identifier type="citekey">fu-etal-2024-wav2vec</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.681</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.681</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>11465</start>
<end>11480</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T wav2vec-S: Adapting Pre-trained Speech Models for Streaming
%A Fu, Biao
%A Fan, Kai
%A Liao, Minpeng
%A Chen, Yidong
%A Shi, Xiaodong
%A Huang, Zhongqiang
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F fu-etal-2024-wav2vec
%X Pre-trained speech models, such as wav2vec 2.0, have significantly advanced speech-related tasks, including speech recognition and translation. However, their applicability in streaming scenarios is limited because these models are trained on complete utterances, leading to a mismatch with incremental streaming inputs. This paper identifies three critical design aspects within the architecture of wav2vec 2.0 and proposes a novel model, wav2vec-S, which incorporates simple modifications to ensure consistent speech representations during both training and inference phases for streaming speech inputs. Furthermore, we demonstrate that wav2vec-S models can be efficiently adapted from pre-trained wav2vec 2.0 models through continued pre-training and effectively finetuned to meet various latency requirements in downstream applications. Experiments on speech recognition and translation tasks show that wav2vec-S outperforms strong baseline models and achieves a superior balance between quality and latency.
%R 10.18653/v1/2024.findings-acl.681
%U https://aclanthology.org/2024.findings-acl.681
%U https://doi.org/10.18653/v1/2024.findings-acl.681
%P 11465-11480
Markdown (Informal)
[wav2vec-S: Adapting Pre-trained Speech Models for Streaming](https://aclanthology.org/2024.findings-acl.681) (Fu et al., Findings 2024)
ACL
- Biao Fu, Kai Fan, Minpeng Liao, Yidong Chen, Xiaodong Shi, and Zhongqiang Huang. 2024. wav2vec-S: Adapting Pre-trained Speech Models for Streaming. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11465–11480, Bangkok, Thailand. Association for Computational Linguistics.