Mutual Information and Perplexity based Clustering of Dialogue Information for Dynamic Adaptation of Language Models


Autoria(s): Lucas Cuesta, Juan Manuel; Fernández Martínez, Fernando; Ferreiros López, Javier; Moreno Solera, Tirso
Data(s)

21/11/2012

Resumo

We present two approaches to cluster dialogue-based information obtained by the speech understanding module and the dialogue manager of a spoken dialogue system. The purpose is to estimate a language model related to each cluster, and use them to dynamically modify the model of the speech recognizer at each dialogue turn. In the first approach we build the cluster tree using local decisions based on a Maximum Normalized Mutual Information criterion. In the second one we take global decisions, based on the optimization of the global perplexity of the combination of the cluster-related LMs. Our experiments show a relative reduction of the word error rate of 15.17%, which helps to improve the performance of the understanding and the dialogue manager modules.

Formato

application/pdf

Identificador

http://oa.upm.es/15206/

Idioma(s)

eng

Publicador

E.T.S.I. Telecomunicación (UPM)

Relação

http://oa.upm.es/15206/1/INVE_MEM_2012_115788.pdf

http://link.springer.com/chapter/10.1007%2F978-3-642-35292-8_16#page-1

Direitos

http://creativecommons.org/licenses/by-nc-nd/3.0/es/

info:eu-repo/semantics/openAccess

Fonte

Springer Communications in Computer and Information Science (CCIS), ISSN 1865-0929, 2012-11-21, Vol. 328

Palavras-Chave #Telecomunicaciones #Electrónica #Matemáticas
Tipo

info:eu-repo/semantics/article

Artículo

PeerReviewed