<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fang-feng-2023-back">
    <titleInfo>
        <title>Back Translation for Speech-to-text Translation Without Transcripts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Qingkai</namePart>
        <namePart type="family">Fang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The success of end-to-end speech-to-text translation (ST) is often achieved by utilizing source transcripts, e.g., by pre-training with automatic speech recognition (ASR) and machine translation (MT) tasks, or by introducing additional ASR and MT data. Unfortunately, transcripts are only sometimes available since numerous unwritten languages exist worldwide. In this paper, we aim to utilize large amounts of target-side monolingual data to enhance ST without transcripts. Motivated by the remarkable success of back translation in MT, we develop a back translation algorithm for ST (BT4ST) to synthesize pseudo ST data from monolingual target data. To ease the challenges posed by short-to-long generation and one-to-many mapping, we introduce self-supervised discrete units and achieve back translation by cascading a target-to-unit model and a unit-to-speech model. With our synthetic ST data, we achieve an average boost of 2.3 BLEU on MuST-C En-De, En-Fr, and En-Es datasets. More experiments show that our method is especially effective in low-resource scenarios.</abstract>
    <identifier type="citekey">fang-feng-2023-back</identifier>
    <identifier type="doi">10.18653/v1/2023.acl-long.251</identifier>
    <location>
        <url>https://aclanthology.org/2023.acl-long.251</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>4567</start>
            <end>4587</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Back Translation for Speech-to-text Translation Without Transcripts
%A Fang, Qingkai
%A Feng, Yang
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F fang-feng-2023-back
%X The success of end-to-end speech-to-text translation (ST) is often achieved by utilizing source transcripts, e.g., by pre-training with automatic speech recognition (ASR) and machine translation (MT) tasks, or by introducing additional ASR and MT data. Unfortunately, transcripts are only sometimes available since numerous unwritten languages exist worldwide. In this paper, we aim to utilize large amounts of target-side monolingual data to enhance ST without transcripts. Motivated by the remarkable success of back translation in MT, we develop a back translation algorithm for ST (BT4ST) to synthesize pseudo ST data from monolingual target data. To ease the challenges posed by short-to-long generation and one-to-many mapping, we introduce self-supervised discrete units and achieve back translation by cascading a target-to-unit model and a unit-to-speech model. With our synthetic ST data, we achieve an average boost of 2.3 BLEU on MuST-C En-De, En-Fr, and En-Es datasets. More experiments show that our method is especially effective in low-resource scenarios.
%R 10.18653/v1/2023.acl-long.251
%U https://aclanthology.org/2023.acl-long.251
%U https://doi.org/10.18653/v1/2023.acl-long.251
%P 4567-4587

Markdown (Informal)

[Back Translation for Speech-to-text Translation Without Transcripts](https://aclanthology.org/2023.acl-long.251) (Fang & Feng, ACL 2023)

• Back Translation for Speech-to-text Translation Without Transcripts (Fang & Feng, ACL 2023)

ACL

• Qingkai Fang and Yang Feng. 2023. Back Translation for Speech-to-text Translation Without Transcripts. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4567–4587, Toronto, Canada. Association for Computational Linguistics.