<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="skantze-2017-towards">
    <titleInfo>
        <title>Towards a General, Continuous Model of Turn-taking in Spoken Dialogue using LSTM Recurrent Neural Networks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Gabriel</namePart>
        <namePart type="family">Skantze</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kristiina</namePart>
            <namePart type="family">Jokinen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Manfred</namePart>
            <namePart type="family">Stede</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">DeVault</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Annie</namePart>
            <namePart type="family">Louis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Saarbrücken, Germany</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Previous models of turn-taking have mostly been trained for specific turn-taking decisions, such as discriminating between turn shifts and turn retention in pauses. In this paper, we present a predictive, continuous model of turn-taking using Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNN). The model is trained on human-human dialogue data to predict upcoming speech activity in a future time window. We show how this general model can be applied to two different tasks that it was not specifically trained for. First, to predict whether a turn-shift will occur or not in pauses, where the model achieves a better performance than human observers, and better than results achieved with more traditional models. Second, to make a prediction at speech onset whether the utterance will be a short backchannel or a longer utterance. Finally, we show how the hidden layer in the network can be used as a feature vector for turn-taking decisions in a human-robot interaction scenario.</abstract>
    <identifier type="citekey">skantze-2017-towards</identifier>
    <identifier type="doi">10.18653/v1/W17-5527</identifier>
    <location>
        <url>https://aclanthology.org/W17-5527</url>
    </location>
    <part>
        <date>2017-08</date>
        <extent unit="page">
            <start>220</start>
            <end>230</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Towards a General, Continuous Model of Turn-taking in Spoken Dialogue using LSTM Recurrent Neural Networks
%A Skantze, Gabriel
%Y Jokinen, Kristiina
%Y Stede, Manfred
%Y DeVault, David
%Y Louis, Annie
%S Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue
%D 2017
%8 August
%I Association for Computational Linguistics
%C Saarbrücken, Germany
%F skantze-2017-towards
%X Previous models of turn-taking have mostly been trained for specific turn-taking decisions, such as discriminating between turn shifts and turn retention in pauses. In this paper, we present a predictive, continuous model of turn-taking using Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNN). The model is trained on human-human dialogue data to predict upcoming speech activity in a future time window. We show how this general model can be applied to two different tasks that it was not specifically trained for. First, to predict whether a turn-shift will occur or not in pauses, where the model achieves a better performance than human observers, and better than results achieved with more traditional models. Second, to make a prediction at speech onset whether the utterance will be a short backchannel or a longer utterance. Finally, we show how the hidden layer in the network can be used as a feature vector for turn-taking decisions in a human-robot interaction scenario.
%R 10.18653/v1/W17-5527
%U https://aclanthology.org/W17-5527
%U https://doi.org/10.18653/v1/W17-5527
%P 220-230

Markdown (Informal)

[Towards a General, Continuous Model of Turn-taking in Spoken Dialogue using LSTM Recurrent Neural Networks](https://aclanthology.org/W17-5527) (Skantze, SIGDIAL 2017)

• Towards a General, Continuous Model of Turn-taking in Spoken Dialogue using LSTM Recurrent Neural Networks (Skantze, SIGDIAL 2017)

ACL

• Gabriel Skantze. 2017. Towards a General, Continuous Model of Turn-taking in Spoken Dialogue using LSTM Recurrent Neural Networks. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pages 220–230, Saarbrücken, Germany. Association for Computational Linguistics.