<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hori-etal-2017-joint">
    <titleInfo>
        <title>Joint CTC/attention decoding for end-to-end speech recognition</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Takaaki</namePart>
        <namePart type="family">Hori</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shinji</namePart>
        <namePart type="family">Watanabe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">John</namePart>
        <namePart type="family">Hershey</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Regina</namePart>
            <namePart type="family">Barzilay</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Min-Yen</namePart>
            <namePart type="family">Kan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vancouver, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>End-to-end automatic speech recognition (ASR) has become a popular alternative to conventional DNN/HMM systems because it avoids the need for linguistic resources such as pronunciation dictionary, tokenization, and context-dependency trees, leading to a greatly simplified model-building process. There are two major types of end-to-end architectures for ASR: attention-based methods use an attention mechanism to perform alignment between acoustic frames and recognized symbols, and connectionist temporal classification (CTC), uses Markov assumptions to efficiently solve sequential problems by dynamic programming. This paper proposes joint decoding algorithm for end-to-end ASR with a hybrid CTC/attention architecture, which effectively utilizes both advantages in decoding. We have applied the proposed method to two ASR benchmarks (spontaneous Japanese and Mandarin Chinese), and showing the comparable performance to conventional state-of-the-art DNN/HMM ASR systems without linguistic resources.</abstract>
    <identifier type="citekey">hori-etal-2017-joint</identifier>
    <identifier type="doi">10.18653/v1/P17-1048</identifier>
    <location>
        <url>https://aclanthology.org/P17-1048</url>
    </location>
    <part>
        <date>2017-07</date>
        <extent unit="page">
            <start>518</start>
            <end>529</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Joint CTC/attention decoding for end-to-end speech recognition
%A Hori, Takaaki
%A Watanabe, Shinji
%A Hershey, John
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F hori-etal-2017-joint
%X End-to-end automatic speech recognition (ASR) has become a popular alternative to conventional DNN/HMM systems because it avoids the need for linguistic resources such as pronunciation dictionary, tokenization, and context-dependency trees, leading to a greatly simplified model-building process. There are two major types of end-to-end architectures for ASR: attention-based methods use an attention mechanism to perform alignment between acoustic frames and recognized symbols, and connectionist temporal classification (CTC), uses Markov assumptions to efficiently solve sequential problems by dynamic programming. This paper proposes joint decoding algorithm for end-to-end ASR with a hybrid CTC/attention architecture, which effectively utilizes both advantages in decoding. We have applied the proposed method to two ASR benchmarks (spontaneous Japanese and Mandarin Chinese), and showing the comparable performance to conventional state-of-the-art DNN/HMM ASR systems without linguistic resources.
%R 10.18653/v1/P17-1048
%U https://aclanthology.org/P17-1048
%U https://doi.org/10.18653/v1/P17-1048
%P 518-529

Markdown (Informal)

[Joint CTC/attention decoding for end-to-end speech recognition](https://aclanthology.org/P17-1048) (Hori et al., ACL 2017)

• Joint CTC/attention decoding for end-to-end speech recognition (Hori et al., ACL 2017)

ACL

• Takaaki Hori, Shinji Watanabe, and John Hershey. 2017. Joint CTC/attention decoding for end-to-end speech recognition. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 518–529, Vancouver, Canada. Association for Computational Linguistics.