@inproceedings{tang-etal-2022-unified,
title = "Unified Speech-Text Pre-training for Speech Translation and Recognition",
author = "Tang, Yun and
Gong, Hongyu and
Dong, Ning and
Wang, Changhan and
Hsu, Wei-Ning and
Gu, Jiatao and
Baevski, Alexei and
Li, Xian and
Mohamed, Abdelrahman and
Auli, Michael and
Pino, Juan",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.105",
doi = "10.18653/v1/2022.acl-long.105",
pages = "1488--1499",
abstract = "In this work, we describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method utilizes multi-task learning to integrate four self-supervised and supervised subtasks for cross modality learning. A self-supervised speech subtask, which leverages unlabelled speech data, and a (self-)supervised text to text subtask, which makes use of abundant text training data, take up the majority of the pre-training time. Two auxiliary supervised speech tasks are included to unify speech and text modeling space. Detailed analysis reveals learning interference among subtasks. In order to alleviate the subtask interference, two pre-training configurations are proposed for speech translation and speech recognition respectively. Our experiments show the proposed method can effectively fuse speech and text information into one model. It achieves between 1.7 and 2.3 BLEU improvement above the state of the art on the MuST-C speech translation dataset and comparable WERs to wav2vec 2.0 on the Librispeech speech recognition task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2022-unified">
<titleInfo>
<title>Unified Speech-Text Pre-training for Speech Translation and Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yun</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ning</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changhan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Ning</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiatao</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexei</namePart>
<namePart type="family">Baevski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelrahman</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Auli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method utilizes multi-task learning to integrate four self-supervised and supervised subtasks for cross modality learning. A self-supervised speech subtask, which leverages unlabelled speech data, and a (self-)supervised text to text subtask, which makes use of abundant text training data, take up the majority of the pre-training time. Two auxiliary supervised speech tasks are included to unify speech and text modeling space. Detailed analysis reveals learning interference among subtasks. In order to alleviate the subtask interference, two pre-training configurations are proposed for speech translation and speech recognition respectively. Our experiments show the proposed method can effectively fuse speech and text information into one model. It achieves between 1.7 and 2.3 BLEU improvement above the state of the art on the MuST-C speech translation dataset and comparable WERs to wav2vec 2.0 on the Librispeech speech recognition task.</abstract>
<identifier type="citekey">tang-etal-2022-unified</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.105</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.105</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1488</start>
<end>1499</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unified Speech-Text Pre-training for Speech Translation and Recognition
%A Tang, Yun
%A Gong, Hongyu
%A Dong, Ning
%A Wang, Changhan
%A Hsu, Wei-Ning
%A Gu, Jiatao
%A Baevski, Alexei
%A Li, Xian
%A Mohamed, Abdelrahman
%A Auli, Michael
%A Pino, Juan
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F tang-etal-2022-unified
%X In this work, we describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method utilizes multi-task learning to integrate four self-supervised and supervised subtasks for cross modality learning. A self-supervised speech subtask, which leverages unlabelled speech data, and a (self-)supervised text to text subtask, which makes use of abundant text training data, take up the majority of the pre-training time. Two auxiliary supervised speech tasks are included to unify speech and text modeling space. Detailed analysis reveals learning interference among subtasks. In order to alleviate the subtask interference, two pre-training configurations are proposed for speech translation and speech recognition respectively. Our experiments show the proposed method can effectively fuse speech and text information into one model. It achieves between 1.7 and 2.3 BLEU improvement above the state of the art on the MuST-C speech translation dataset and comparable WERs to wav2vec 2.0 on the Librispeech speech recognition task.
%R 10.18653/v1/2022.acl-long.105
%U https://aclanthology.org/2022.acl-long.105
%U https://doi.org/10.18653/v1/2022.acl-long.105
%P 1488-1499
Markdown (Informal)
[Unified Speech-Text Pre-training for Speech Translation and Recognition](https://aclanthology.org/2022.acl-long.105) (Tang et al., ACL 2022)
ACL
- Yun Tang, Hongyu Gong, Ning Dong, Changhan Wang, Wei-Ning Hsu, Jiatao Gu, Alexei Baevski, Xian Li, Abdelrahman Mohamed, Michael Auli, and Juan Pino. 2022. Unified Speech-Text Pre-training for Speech Translation and Recognition. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1488–1499, Dublin, Ireland. Association for Computational Linguistics.