<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pino-etal-2019-harnessing">
    <titleInfo>
        <title>Harnessing Indirect Training Data for End-to-End Automatic Speech Translation: Tricks of the Trade</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Juan</namePart>
        <namePart type="family">Pino</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Liezl</namePart>
        <namePart type="family">Puzon</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">Xutai</namePart>
        <namePart type="family">Ma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Arya</namePart>
        <namePart type="given">D</namePart>
        <namePart type="family">McCarthy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Deepak</namePart>
        <namePart type="family">Gopinath</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-nov&quot; 2-3&quot;</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 16th International Conference on Spoken Language Translation</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hong Kong</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>For automatic speech translation (AST), end-to-end approaches are outperformed by cascaded models that transcribe with automatic speech recognition (ASR), then trans- late with machine translation (MT). A major cause of the performance gap is that, while existing AST corpora are small, massive datasets exist for both the ASR and MT subsystems. In this work, we evaluate several data augmentation and pretraining approaches for AST, by comparing all on the same datasets. Simple data augmentation by translating ASR transcripts proves most effective on the English–French augmented LibriSpeech dataset, closing the performance gap from 8.2 to 1.4 BLEU, compared to a very strong cascade that could directly utilize copious ASR and MT data. The same end-to-end approach plus fine-tuning closes the gap on the English–Romanian MuST-C dataset from 6.7 to 3.7 BLEU. In addition to these results, we present practical rec- ommendations for augmentation and pretraining approaches. Finally, we decrease the performance gap to 0.01 BLEU us- ing a Transformer-based architecture.</abstract>
    <identifier type="citekey">pino-etal-2019-harnessing</identifier>
    <location>
        <url>https://aclanthology.org/2019.iwslt-1.18</url>
    </location>
    <part>
        <date>2019-nov&quot; 2-3&quot;</date>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Harnessing Indirect Training Data for End-to-End Automatic Speech Translation: Tricks of the Trade
%A Pino, Juan
%A Puzon, Liezl
%A Gu, Jiatao
%A Ma, Xutai
%A McCarthy, Arya D.
%A Gopinath, Deepak
%S Proceedings of the 16th International Conference on Spoken Language Translation
%D 2019
%8 nov" 2 3"
%I Association for Computational Linguistics
%C Hong Kong
%F pino-etal-2019-harnessing
%X For automatic speech translation (AST), end-to-end approaches are outperformed by cascaded models that transcribe with automatic speech recognition (ASR), then trans- late with machine translation (MT). A major cause of the performance gap is that, while existing AST corpora are small, massive datasets exist for both the ASR and MT subsystems. In this work, we evaluate several data augmentation and pretraining approaches for AST, by comparing all on the same datasets. Simple data augmentation by translating ASR transcripts proves most effective on the English–French augmented LibriSpeech dataset, closing the performance gap from 8.2 to 1.4 BLEU, compared to a very strong cascade that could directly utilize copious ASR and MT data. The same end-to-end approach plus fine-tuning closes the gap on the English–Romanian MuST-C dataset from 6.7 to 3.7 BLEU. In addition to these results, we present practical rec- ommendations for augmentation and pretraining approaches. Finally, we decrease the performance gap to 0.01 BLEU us- ing a Transformer-based architecture.
%U https://aclanthology.org/2019.iwslt-1.18

Markdown (Informal)

[Harnessing Indirect Training Data for End-to-End Automatic Speech Translation: Tricks of the Trade](https://aclanthology.org/2019.iwslt-1.18) (Pino et al., IWSLT 2019)

• Harnessing Indirect Training Data for End-to-End Automatic Speech Translation: Tricks of the Trade (Pino et al., IWSLT 2019)

ACL

• Juan Pino, Liezl Puzon, Jiatao Gu, Xutai Ma, Arya D. McCarthy, and Deepak Gopinath. 2019. Harnessing Indirect Training Data for End-to-End Automatic Speech Translation: Tricks of the Trade. In Proceedings of the 16th International Conference on Spoken Language Translation, Hong Kong. Association for Computational Linguistics.