http://www.cnr.it/ontology/cnr/individuo/prodotto/ID240877

High Performance Telephone Bandwidth Speaker Independent Continuous Digit Recognition. (Contributo in atti di convegno)

Type

Label

High Performance Telephone Bandwidth Speaker Independent Continuous Digit Recognition. (Contributo in atti di convegno) (literal)

Anno

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#doi

Alternative label

Cosi P., Hosom J.P., Valente A. (2001)
High Performance Telephone Bandwidth Speaker Independent Continuous Digit Recognition.
in ASRU 2001 - Automatic Speech Recognition and Understanding Workshop, Madonna di Campiglio, Trento (Italy), December 9-13, 2001
(literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori

Pagina inizio

Pagina fine

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#altreInformazioni

Cosi P., Hosom J.P., Valente A. \"High Performance Telephone Bandwidth Speaker Independent Continuous Digit Recognition\" Proceedings ASRU 2001 - Automatic Speech Recognition and Understanding Workshop Madonna di Campiglio, Trento (Italy) December 9-13, 2001 http://www2.pd.istc.cnr.it/Papers/PieroCosi/cp-ASRU2001.pdf Published in: Automatic Speech Recognition and Understanding, 2001. ASRU '01. IEEE Workshop on Date of Conference: 2001 Page(s): 405 - 408 Print ISBN: 0-7803-7343-X INSPEC Accession Number: 7501191 Digital Object Identifier: 10.1109/ASRU.2001.1034670 (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#url

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#titoloVolume

Note

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni

Piero Cosi', John-Paul Hosom**ondAlberro Volenfe***. ISTC CNR, UOS Padova Cosi P. Center for Spoken Language Understanding (CSLU-OGI) Oregon Graduate Institute (OGI), P.O. Box 91000, Portland, Oregon 97291 USA Hosom J.P. Università di Padova - Dipartimento di Elenronica e Informatica Via Gradenigo 6/a, 3513 I Padova ITALY Valente A. (literal)

Titolo

High Performance Telephone Bandwidth Speaker Independent Continuous Digit Recognition. (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#isbn

Abstract

The development of a high-performance telephone-bandwidth speaker independent connected digit recognizer for Italian is described. The CSLU Speech Toolkit was used to develop and implement the hybrid ANN/HMM system, which is trained on context-dependent categories to account for coarticulatory variation. Various front-end processing and system architectures were compared and, when the best features (MFCC with CMS + ?) and network (4-layer fully connected feed-forward network) were considered, there was a 98.92% word recognition accuracy and a 92.62% sentence recognition accuracy on a test set of the FIELD continuous digits recognition task. (literal)

Editore