<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="papi-etal-2021-speechformer">
    <titleInfo>
        <title>Speechformer: Reducing Information Loss in Direct Speech Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sara</namePart>
        <namePart type="family">Papi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marco</namePart>
        <namePart type="family">Gaido</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matteo</namePart>
        <namePart type="family">Negri</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marco</namePart>
        <namePart type="family">Turchi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Transformer-based models have gained increasing popularity achieving state-of-the-art performance in many research fields including speech translation. However, Transformer’s quadratic complexity with respect to the input sequence length prevents its adoption as is with audio signals, which are typically represented by long sequences. Current solutions resort to an initial sub-optimal compression based on a fixed sampling of raw audio features. Therefore, potentially useful linguistic information is not accessible to higher-level layers in the architecture. To solve this issue, we propose Speechformer, an architecture that, thanks to reduced memory usage in the attention layers, avoids the initial lossy compression and aggregates information only at a higher level according to more informed linguistic criteria. Experiments on three language pairs (en→de/es/nl) show the efficacy of our solution, with gains of up to 0.8 BLEU on the standard MuST-C corpus and of up to 4.0 BLEU in a low resource scenario.</abstract>
    <identifier type="citekey">papi-etal-2021-speechformer</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.127</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.127</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>1698</start>
            <end>1706</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Speechformer: Reducing Information Loss in Direct Speech Translation
%A Papi, Sara
%A Gaido, Marco
%A Negri, Matteo
%A Turchi, Marco
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F papi-etal-2021-speechformer
%X Transformer-based models have gained increasing popularity achieving state-of-the-art performance in many research fields including speech translation. However, Transformer’s quadratic complexity with respect to the input sequence length prevents its adoption as is with audio signals, which are typically represented by long sequences. Current solutions resort to an initial sub-optimal compression based on a fixed sampling of raw audio features. Therefore, potentially useful linguistic information is not accessible to higher-level layers in the architecture. To solve this issue, we propose Speechformer, an architecture that, thanks to reduced memory usage in the attention layers, avoids the initial lossy compression and aggregates information only at a higher level according to more informed linguistic criteria. Experiments on three language pairs (en→de/es/nl) show the efficacy of our solution, with gains of up to 0.8 BLEU on the standard MuST-C corpus and of up to 4.0 BLEU in a low resource scenario.
%R 10.18653/v1/2021.emnlp-main.127
%U https://aclanthology.org/2021.emnlp-main.127
%U https://doi.org/10.18653/v1/2021.emnlp-main.127
%P 1698-1706

Markdown (Informal)

[Speechformer: Reducing Information Loss in Direct Speech Translation](https://aclanthology.org/2021.emnlp-main.127) (Papi et al., EMNLP 2021)

• Speechformer: Reducing Information Loss in Direct Speech Translation (Papi et al., EMNLP 2021)

ACL

• Sara Papi, Marco Gaido, Matteo Negri, and Marco Turchi. 2021. Speechformer: Reducing Information Loss in Direct Speech Translation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1698–1706, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.