Natural vs. Synthesized Speech in Spoken Dialog Systems Research : Comparing the Performance of Recognition Results

Scheffler, Tatjana; Roller, Roland; Kretzschmar, Florian; Möller, Sebastian; Reithinger, Norbert

Natural vs. Synthesized Speech in Spoken Dialog Systems Research : Comparing the Performance of Recognition Results

Files

There are no files associated with this item.

Date

2012

Authors

Scheffler, Tatjana

Roller, Roland

Kretzschmar, Florian

Möller, Sebastian

Reithinger, Norbert

Publication type

Contribution to a conference collection

Published in

Sprachkommunikation 2012 : Beiträge zur 10. ITG-Fachtagung vom 26. bis 28. September 2012 in Braunschweig. - Berlin [u.a.] : VDE-Verl., 2012. - (ITG-Fachbericht ; 236). - pp. 127-130. - ISBN 978-3-8007-3455-9

Abstract

In this paper, we test the effect of using speech synthesis when interacting with a spoken dialog system (SDS). We use a user simulation to connect our speech synthesis to a real, state-of-the-art automatic speech recognition (ASR) component deployed in a working commercial SDS via a standard telephone line. In a series of experiments, we compare human-machine dialogs and their recognition scores with simulated dialogs using synthesis. Our results show that a good text-to-speech synthesis configuration rivals human speech both in recognition scores as well as variability. This makes the speech interface in user simulation quite attractive.

Subject (DDC)

400 Philology, Linguistics

Conference

10. ITG-Fachtagung, Sep 26, 2012 - Sep 28, 2012, Braunschweig

Cite This

ISO 690

SCHEFFLER, Tatjana, Roland ROLLER, Florian KRETZSCHMAR, Sebastian MÖLLER, Norbert REITHINGER, 2012. Natural vs. Synthesized Speech in Spoken Dialog Systems Research : Comparing the Performance of Recognition Results. 10. ITG-Fachtagung. Braunschweig, Sep 26, 2012 - Sep 28, 2012. In: Sprachkommunikation 2012 : Beiträge zur 10. ITG-Fachtagung vom 26. bis 28. September 2012 in Braunschweig. Berlin [u.a.]:VDE-Verl., pp. 127-130. ISBN 978-3-8007-3455-9

BibTex

@inproceedings{Scheffler2012Natur-29021,
  year={2012},
  title={Natural vs. Synthesized Speech in Spoken Dialog Systems Research : Comparing the Performance of Recognition Results},
  number={236},
  isbn={978-3-8007-3455-9},
  publisher={VDE-Verl.},
  address={Berlin [u.a.]},
  series={ITG-Fachbericht},
  booktitle={Sprachkommunikation 2012 : Beiträge zur 10. ITG-Fachtagung vom 26. bis 28. September 2012 in Braunschweig},
  pages={127--130},
  author={Scheffler, Tatjana and Roller, Roland and Kretzschmar, Florian and Möller, Sebastian and Reithinger, Norbert}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/29021">
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/45"/>
    <dcterms:bibliographicCitation>Sprachkommunikation 2012 : Beiträge zur 10. ITG-Fachtagung vom 26. bis 28. September 2012 in Braunschweig. - Berlin [u.a.] : VDE-Verl., 2012. - S. 127-130. - (ITG-Fachbericht ; 236). - ISBN 978-3-8007-3455-9</dcterms:bibliographicCitation>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:issued>2012</dcterms:issued>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2014-09-30T13:20:47Z</dcterms:available>
    <dcterms:abstract xml:lang="eng">In this paper, we test the effect of using speech synthesis when interacting with a spoken dialog system (SDS). We use a user simulation to connect our speech synthesis to a real, state-of-the-art automatic speech recognition (ASR) component deployed in a working commercial SDS via a standard telephone line. In a series of experiments, we compare human-machine dialogs and their recognition scores with simulated dialogs using synthesis. Our results show that a good text-to-speech synthesis configuration rivals human speech both in recognition scores as well as variability. This makes the speech interface in user simulation quite attractive.</dcterms:abstract>
    <dc:contributor>Reithinger, Norbert</dc:contributor>
    <dcterms:title>Natural vs. Synthesized Speech in Spoken Dialog Systems Research : Comparing the Performance of Recognition Results</dcterms:title>
    <dc:contributor>Roller, Roland</dc:contributor>
    <dc:creator>Scheffler, Tatjana</dc:creator>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2014-09-30T13:20:47Z</dc:date>
    <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/29021"/>
    <dc:creator>Roller, Roland</dc:creator>
    <dc:creator>Möller, Sebastian</dc:creator>
    <dc:creator>Kretzschmar, Florian</dc:creator>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/45"/>
    <dc:language>eng</dc:language>
    <dc:contributor>Kretzschmar, Florian</dc:contributor>
    <dc:contributor>Scheffler, Tatjana</dc:contributor>
    <dc:creator>Reithinger, Norbert</dc:creator>
    <dc:contributor>Möller, Sebastian</dc:contributor>
    <dc:rights>terms-of-use</dc:rights>
  </rdf:Description>
</rdf:RDF>

Bibliography of Konstanz

No