Mostra el registre d'ítem simple

dc.contributor.authorFreitag, Fèlix
dc.contributor.authorMonte Moreno, Enrique
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2017-04-20T16:38:19Z
dc.date.available2017-04-20T16:38:19Z
dc.date.issued1998
dc.identifier.citationFreitag, F., Monte, E. Phoneme recognition with statisticasl modeling of the prediction of the error of neural networks. A: International Conference on Spoken Language Processing. "ICSLP 98: the 5th International Conference on Spoken Language Processing; incorporating the 7th Australian International Speech Science and Technology Conference; Sydney Convention Centre, Sydney, Australia, 30th November-4th December 1998". Sidney: Robert H. Mannel and Jordi Robert-Ribes, 1998, p. 719-722.
dc.identifier.isbn1 876346 17 5
dc.identifier.urihttp://hdl.handle.net/2117/103598
dc.description.abstractThis paper presents a speech recognition system which incorporates predictive neural networks. The neural networks are used to predict observation vectors of speech. The prediction error vectors are modeled on the state level by Gaussian densities, which provide the local similarity measure for the Viterbi algorithm during recognition. The system is evaluated on a continuous speech phoneme recognition task. Compared with a HMM reference system, the proposed system obtained better results in the speech recognition experiments.
dc.format.extent4 p.
dc.language.isoeng
dc.publisherRobert H. Mannel and Jordi Robert-Ribes
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació
dc.subject.lcshTelecommunication
dc.titlePhoneme recognition with statisticasl modeling of the prediction of the error of neural networks
dc.typeConference report
dc.subject.lemacTelecomunicació
dc.contributor.groupUniversitat Politècnica de Catalunya. CNDS - Xarxes de Computadors i Sistemes Distribuïts
dc.contributor.groupUniversitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla
dc.description.peerreviewedPeer Reviewed
dc.rights.accessOpen Access
local.identifier.drac2357267
dc.description.versionPostprint (published version)
local.citation.authorFreitag, F.; Monte, E.
local.citation.contributorInternational Conference on Spoken Language Processing
local.citation.pubplaceSidney
local.citation.publicationNameICSLP 98: the 5th International Conference on Spoken Language Processing; incorporating the 7th Australian International Speech Science and Technology Conference; Sydney Convention Centre, Sydney, Australia, 30th November-4th December 1998
local.citation.startingPage719
local.citation.endingPage722


Fitxers d'aquest items

Thumbnail

Aquest ítem apareix a les col·leccions següents

Mostra el registre d'ítem simple