A time delay radial basis function network for phoneme recognition

Berthold, Michael R.

A time delay radial basis function network for phoneme recognition

Dateien

Zu diesem Dokument gibt es keine Dateien.

Datum

1994

Publikationstyp

Beitrag zu einem Konferenzband

Publikationsstatus

Published

Erschienen in

Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94). IEEE, 1994, pp. 4470-4472,. ISBN 0-7803-1901-X. Available under: doi: 10.1109/ICNN.1994.374991

Zusammenfassung

This paper presents the time delay radial basis function network (TDRBF) for recognition of phonemes. The TDRBF combines features from time delay neural networks (TDNN) and radial basis functions (RBF). The ability to detect acoustic features and their temporal relationship independent of position in time is inherited from TDNN. The use of RBFs leads to shorter training times and less parameters to adjust, which makes it easier to apply TDRBF to new tasks. The recognition of three phonemes with about 750 training and testing tokens each was chosen as an evaluation task. The results suggest an equivalent performance of TDRBF and TDNN presented in Waibel et al. (1989), but TDRBF require much less training time to reach a good performance and in addition have a clear indication when the minimum error is reached, therefore no danger of overtraining exists

Fachgebiet (DDC)

004 Informatik

Konferenz

1994 IEEE International Conference on Neural Networks (ICNN'94), Orlando, FL, USA

Zitieren

ISO 690

BERTHOLD, Michael R., 1994. A time delay radial basis function network for phoneme recognition. 1994 IEEE International Conference on Neural Networks (ICNN'94). Orlando, FL, USA. In: Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94). IEEE, 1994, pp. 4470-4472,. ISBN 0-7803-1901-X. Available under: doi: 10.1109/ICNN.1994.374991

BibTex

@inproceedings{Berthold1994delay-24172,
  year={1994},
  doi={10.1109/ICNN.1994.374991},
  title={A time delay radial basis function network for phoneme recognition},
  isbn={0-7803-1901-X},
  publisher={IEEE},
  booktitle={Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94)},
  pages={4470--4472,},
  author={Berthold, Michael R.}
}

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/123456789/24172">
    <dcterms:bibliographicCitation>The 1994 IEEE International Conference on Neural Networks, IEEE World Congress on Computational Intelligence : June 27 - 29, 1994, Walt Disney World Dolphin Hotel, Orlando, Florida; Vol.7 / IEEE Neural Networks Council. - Piscataway, NJ : IEEE Service Center, 1994. - S. 4470 - 4472. - ISBN 0-7803-1901-X</dcterms:bibliographicCitation>
    <dc:language>eng</dc:language>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Berthold, Michael R.</dc:creator>
    <dcterms:issued>1994</dcterms:issued>
    <dcterms:abstract xml:lang="eng">This paper presents the time delay radial basis function network (TDRBF) for recognition of phonemes. The TDRBF combines features from time delay neural networks (TDNN) and radial basis functions (RBF). The ability to detect acoustic features and their temporal relationship independent of position in time is inherited from TDNN. The use of RBFs leads to shorter training times and less parameters to adjust, which makes it easier to apply TDRBF to new tasks. The recognition of three phonemes with about 750 training and testing tokens each was chosen as an evaluation task. The results suggest an equivalent performance of TDRBF and TDNN presented in Waibel et al. (1989), but TDRBF require much less training time to reach a good performance and in addition have a clear indication when the minimum error is reached, therefore no danger of overtraining exists</dcterms:abstract>
    <dc:contributor>Berthold, Michael R.</dc:contributor>
    <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/24172"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-07-29T15:13:16Z</dcterms:available>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-07-29T15:13:16Z</dc:date>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dcterms:title>A time delay radial basis function network for phoneme recognition</dcterms:title>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:rights>terms-of-use</dc:rights>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Nein