<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elsner-shain-2017-speech">
    <titleInfo>
        <title>Speech segmentation with a neural encoder model of working memory</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Micha</namePart>
        <namePart type="family">Elsner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cory</namePart>
        <namePart type="family">Shain</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Martha</namePart>
            <namePart type="family">Palmer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rebecca</namePart>
            <namePart type="family">Hwa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Riedel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Copenhagen, Denmark</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present the first unsupervised LSTM speech segmenter as a cognitive model of the acquisition of words from unsegmented input. Cognitive biases toward phonological and syntactic predictability in speech are rooted in the limitations of human memory (Baddeley et al., 1998); compressed representations are easier to acquire and retain in memory. To model the biases introduced by these memory limitations, our system uses an LSTM-based encoder-decoder with a small number of hidden units, then searches for a segmentation that minimizes autoencoding loss. Linguistically meaningful segments (e.g. words) should share regular patterns of features that facilitate decoder performance in comparison to random segmentations, and we show that our learner discovers these patterns when trained on either phoneme sequences or raw acoustics. To our knowledge, ours is the first fully unsupervised system to be able to segment both symbolic and acoustic representations of speech.</abstract>
    <identifier type="citekey">elsner-shain-2017-speech</identifier>
    <identifier type="doi">10.18653/v1/D17-1112</identifier>
    <location>
        <url>https://aclanthology.org/D17-1112</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>1070</start>
            <end>1080</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Speech segmentation with a neural encoder model of working memory
%A Elsner, Micha
%A Shain, Cory
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F elsner-shain-2017-speech
%X We present the first unsupervised LSTM speech segmenter as a cognitive model of the acquisition of words from unsegmented input. Cognitive biases toward phonological and syntactic predictability in speech are rooted in the limitations of human memory (Baddeley et al., 1998); compressed representations are easier to acquire and retain in memory. To model the biases introduced by these memory limitations, our system uses an LSTM-based encoder-decoder with a small number of hidden units, then searches for a segmentation that minimizes autoencoding loss. Linguistically meaningful segments (e.g. words) should share regular patterns of features that facilitate decoder performance in comparison to random segmentations, and we show that our learner discovers these patterns when trained on either phoneme sequences or raw acoustics. To our knowledge, ours is the first fully unsupervised system to be able to segment both symbolic and acoustic representations of speech.
%R 10.18653/v1/D17-1112
%U https://aclanthology.org/D17-1112
%U https://doi.org/10.18653/v1/D17-1112
%P 1070-1080

Markdown (Informal)

[Speech segmentation with a neural encoder model of working memory](https://aclanthology.org/D17-1112) (Elsner & Shain, EMNLP 2017)

• Speech segmentation with a neural encoder model of working memory (Elsner & Shain, EMNLP 2017)

ACL

• Micha Elsner and Cory Shain. 2017. Speech segmentation with a neural encoder model of working memory. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1070–1080, Copenhagen, Denmark. Association for Computational Linguistics.