Which model for future speech recognition systems: Hidden Markov models for finite-state automata?

Joseph Di Martino; Jean-François Mari; B. Mathieu; K. Perot; Kamel Smaïli

hal-00589127, version 1

Which model for future speech recognition systems: Hidden Markov models for finite-state automata?

Joseph Di Martino ¹, Jean-François Mari ¹, B. Mathieu, K. Perot, Kamel Smaïli ¹

IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP-94 (1994) 633-635

Résumé : Representation of speech using hidden Markov models is compared with a representatiton based on finite-state automata. Experimental results are presented for both methods and the respective advantages and disadvantages discussed

1 : PAROLE (INRIA Lorraine - LORIA)
INRIA – CNRS : UMR7503 – Université Henri Poincaré - Nancy I – Université Nancy II – Institut National Polytechnique de Lorraine (INPL)

hal-00589127, version 1
http://hal.archives-ouvertes.fr/hal-00589127
oai:hal.archives-ouvertes.fr:hal-00589127
Contributeur : Kamel Smaïli <>
Soumis le : Mercredi 27 Avril 2011, 15:36:05
Dernière modification le : Mardi 24 Mai 2011, 11:53:34

Voir la fiche détaillée

Exporter

Bibtex EndNote TEI RefWorks

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="inproceedings"><head>Communications avec actes</head>
<biblStruct type="inproceedings" xml:id="hal-00589127"><analytic>
<author><persName><forename>Joseph</forename><surname>Di Martino</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA Lorraine - LORIA</orgName>
<orgName type="team">PAROLE</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR7503</orgName>
<orgName type="institution">Université Henri Poincaré - Nancy I</orgName>
<orgName type="institution">Université Nancy II</orgName>
<orgName type="institution">Institut National Polytechnique de Lorraine (INPL)</orgName>
</affiliation>
</author>
<author><persName><forename>Jean-François</forename><surname>Mari</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA Lorraine - LORIA</orgName>
<orgName type="team">PAROLE</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR7503</orgName>
<orgName type="institution">Université Henri Poincaré - Nancy I</orgName>
<orgName type="institution">Université Nancy II</orgName>
<orgName type="institution">Institut National Polytechnique de Lorraine (INPL)</orgName>
</affiliation>
</author>
<author><persName><forename>B.</forename><surname>Mathieu</surname></persName></author>
<author><persName><forename>K.</forename><surname>Perot</surname></persName></author>
<author><persName><forename>Kamel</forename><surname>Smaïli</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA Lorraine - LORIA</orgName>
<orgName type="team">PAROLE</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR7503</orgName>
<orgName type="institution">Université Henri Poincaré - Nancy I</orgName>
<orgName type="institution">Université Nancy II</orgName>
<orgName type="institution">Institut National Polytechnique de Lorraine (INPL)</orgName>
</affiliation>
</author>
<title type="main" level="a">Which model for future speech recognition systems: Hidden Markov models for finite-state automata?</title></analytic><monogr><title level="m" type="main">Acoustics, Speech, and Signal Processing - ICASSP-94</title><meeting>IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP-94</meeting><imprint><publisher>IEEE</publisher><pubPlace><settlement>Adelaïd</settlement><country>Australie</country></pubPlace><biblScope type="publicationDate">1994-00-00</biblScope><biblScope type="pp">633-635</biblScope></imprint></monogr><idno type="HALid">http://hal.archives-ouvertes.fr/hal-00589127</idno></biblStruct>
</listBibl>
</listBibl>