Show simple item record

dc.contributor.authorLleida Solano, Eduardo
dc.contributor.authorNadeu Camprubí, Climent
dc.contributor.authorMariño Acebal, José Bernardo
dc.contributor.authorSalavedra Molí, Josep
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2017-02-03T14:03:56Z
dc.date.available2017-02-03T14:03:56Z
dc.date.issued1991
dc.identifier.citationLleida, E., Nadeu, C., Mariño, J.B., Salavedra, J. Demisyllable-based HMM spotting for continuous speech recognition. A: IEEE International Conference on Acoustics, Speech, and Signal Processing. "Proceedings ICASSP 91: 1991 International Conference on Acoustics, Speech and Signal Processing: May 14-17, 1991: Toronto, Canada". Toronto, Ontario: Institute of Electrical and Electronics Engineers (IEEE), 1991, p. 709-712.
dc.identifier.isbn0-7803-0003-3
dc.identifier.urihttp://hdl.handle.net/2117/100552
dc.description.abstractThe authors describe the acoustic processor of a Spanish continuous speech recognition system based on demisyllable units. The acoustic processor is based on a spotting algorithm which takes as input the unknown utterance, the HMM (hidden Markov model) of the reference demisyllables, and the lexical knowledge in terms of a finite state network. The spotting algorithm is a modified version of the one-step Viterbi algorithm with multiple hypotheses. The output of the system is a lattice of word hypotheses suitable to be parsed by a linguistic analyzer. The proposed acoustic processor was tested using the integers from 0 to 1000 and telephonic numbers in a speaker-independent approach. The results show the good performance of the demisyllable as a recognition unit for the Spanish language and the efficiency of the spotting algorithm.
dc.format.extent4 p.
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació
dc.subject.lcshTelecommunication
dc.subject.otherSpeech recognition
dc.subject.otherMarkov processes
dc.titleDemisyllable-based HMM spotting for continuous speech recognition
dc.typeConference report
dc.subject.lemacTelecomunicació
dc.contributor.groupUniversitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla
dc.identifier.doi10.1109/ICASSP.1991.150438
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://ieeexplore.ieee.org/document/150438/
dc.rights.accessOpen Access
drac.iddocument2434143
dc.description.versionPostprint (published version)
upcommons.citation.authorLleida, E.; Nadeu, C.; Mariño, J.B.; Salavedra, J.
upcommons.citation.contributorIEEE International Conference on Acoustics, Speech, and Signal Processing
upcommons.citation.pubplaceToronto, Ontario
upcommons.citation.publishedtrue
upcommons.citation.publicationNameProceedings ICASSP 91: 1991 International Conference on Acoustics, Speech and Signal Processing: May 14-17, 1991: Toronto, Canada
upcommons.citation.startingPage709
upcommons.citation.endingPage712


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder