<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lam-etal-2022-sample">
    <titleInfo>
        <title>Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tsz</namePart>
        <namePart type="given">Kin</namePart>
        <namePart type="family">Lam</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shigehiko</namePart>
        <namePart type="family">Schamoni</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stefan</namePart>
        <namePart type="family">Riezler</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 2: Short 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>End-to-end speech translation relies on data that pair source-language speech inputs with corresponding translations into a target language. Such data are notoriously scarce, making synthetic data augmentation by back-translation or knowledge distillation a necessary ingredient of end-to-end training. In this paper, we present a novel approach to data augmentation that leverages audio alignments, linguistic properties, and translation. First, we augment a transcription by sampling from a suffix memory that stores text and audio data. Second, we translate the augmented transcript. Finally, we recombine concatenated audio segments and the generated translation. Our method delivers consistent improvements of up to 0.9 and 1.1 BLEU points on top of augmentation with knowledge distillation on five language pairs on CoVoST 2 and on two language pairs on Europarl-ST, respectively.</abstract>
    <identifier type="citekey">lam-etal-2022-sample</identifier>
    <identifier type="doi">10.18653/v1/2022.acl-short.27</identifier>
    <location>
        <url>https://aclanthology.org/2022.acl-short.27</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>245</start>
            <end>254</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation
%A Lam, Tsz Kin
%A Schamoni, Shigehiko
%A Riezler, Stefan
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F lam-etal-2022-sample
%X End-to-end speech translation relies on data that pair source-language speech inputs with corresponding translations into a target language. Such data are notoriously scarce, making synthetic data augmentation by back-translation or knowledge distillation a necessary ingredient of end-to-end training. In this paper, we present a novel approach to data augmentation that leverages audio alignments, linguistic properties, and translation. First, we augment a transcription by sampling from a suffix memory that stores text and audio data. Second, we translate the augmented transcript. Finally, we recombine concatenated audio segments and the generated translation. Our method delivers consistent improvements of up to 0.9 and 1.1 BLEU points on top of augmentation with knowledge distillation on five language pairs on CoVoST 2 and on two language pairs on Europarl-ST, respectively.
%R 10.18653/v1/2022.acl-short.27
%U https://aclanthology.org/2022.acl-short.27
%U https://doi.org/10.18653/v1/2022.acl-short.27
%P 245-254

Markdown (Informal)

[Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation](https://aclanthology.org/2022.acl-short.27) (Lam et al., ACL 2022)

• Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation (Lam et al., ACL 2022)

ACL

• Tsz Kin Lam, Shigehiko Schamoni, and Stefan Riezler. 2022. Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 245–254, Dublin, Ireland. Association for Computational Linguistics.