To access the full text documents, please follow this link:

Joint training of codebooks and acoustic models in automatic speech recognition using semi-continuous HMMs
Nogueiras Rodríguez, Albino; Caballero Galeote, Mónica; Mariño Acebal, José Bernardo
Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions; Universitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla
In this paper, three different techniques for building semicontinuousHMMbased speech recognisers are compared: the classical one, using Euclidean generated codebooks and independently trained acoustic models; jointly reestimating the codebooks and models obtained with the classical method; and jointly creating codebooks and models growing their size from one centroid to the desired number of them. The way this growth may be done is carefully addressed, focusing on the selection of the splitting direction and the way splitting is implemented. Results in a large vocabulary task show the ef ciency of the approach, with noticeable improvements both in accuracy and CPU consumption. Moreover, this scheme enables the use of the concatenation of features, avoiding the independence assumption usually needed in semi-continuous HMM modelling, and leading to further improvements in accuracy and CPU.
Peer Reviewed
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Llenguatge natural
Automatic speech recognition
Reconeixement automàtic de la parla
Eduardo Lleida Solano

Show full item record

Related documents

Other documents of the same author

Nogueiras Rodríguez, Albino; Casar López, Marta; Rodríguez Fonollosa, José Adrián; Caballero Galeote, Mónica
Nogueiras Rodríguez, Albino; Caballero Galeote, Mónica; Moreno Bilbao, M. Asunción
Caballero Galeote, Mónica; Moreno Bilbao, M. Asunción; Nogueiras Rodríguez, Albino
Nogueiras Rodríguez, Albino; Mariño Acebal, José Bernardo
Nogueiras Rodríguez, Albino; Mariño Acebal, José Bernardo; Bonafonte Cávez, Antonio; Moreno Bilbao, M. Asunción