Result: Topic identification techniques applied to dynamic language model adaptation for automatic speech recognition

Title:
Topic identification techniques applied to dynamic language model adaptation for automatic speech recognition
Authors:
ECHEVERRY-CORREA, J. D, FERREIROS-LOPEZ, J, COUCHEIRO-LIMERES, A, CORDOBA, R, MONTERO, J. M
Source:
Expert systems with applications. 42(1):101-112
Publisher Information:
Amsterdam: Elsevier, 2015.
Publication Year:
2015
Physical Description:
print, 3/4 p
Original Material:
INIST-CNRS
Subject Terms:
Computer science, Informatique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Logiciel, Software, Organisation des mémoires. Traitement des données, Memory organisation. Data processing, Traitement des données. Listes et chaînes de caractères, Data processing. List processing. Character string processing, Systèmes d'information. Bases de données, Information systems. Data bases, Intelligence artificielle, Artificial intelligence, Reconnaissance et synthèse de la parole et du son. Linguistique, Speech and sound recognition and synthesis. Linguistics, Telecommunications et theorie de l'information, Telecommunications and information theory, Théorie de l'information, du signal et des communications, Information, signal and communications theory, Traitement du signal, Signal processing, Traitement de la parole, Speech processing, Actualités, News, Noticias, Ajustement modèle, Model matching, Ajustamiento modelo, Algorithme k moyenne, K means algorithm, Algoritmo k media, Amas, Cluster, Montón, Base de données, Database, Base dato, Classification, Clasificación, Confiance, Confidence, Confianza, Démocratie, Democracy, Democracia, Erreur relative, Relative error, Error relativo, Identification système, System identification, Identificación sistema, Langage modélisation, Modelling language, Lenguaje modelización, Langage naturel, Natural language, Lenguaje natural, Linguistique mathématique, Computational linguistics, Linguística matemática, Modèle dynamique, Dynamic model, Modelo dinámico, Modèle linéaire, Linear model, Modelo lineal, Modélisation, Modeling, Modelización, Méthode moindre carré, Least squares method, Método cuadrado menor, Méthode vectorielle, Vector method, Método vectorial, Partition, Partición, Programmation dynamique, Dynamic programming, Programación dinámica, Recherche information, Information retrieval, Búsqueda información, Reconnaissance automatique, Automatic recognition, Reconocimiento automático, Reconnaissance parole, Speech recognition, Reconocimiento voz, Sémantique algébrique, Algebraic semantic, Semántica algebraica, Texte, Text, Texto, Analyse texte, Text analysis, Análisis de textos, Automatic speech recognition, Language model adaptation, Topic identification
Document Type:
Academic journal Article
File Description:
text
Language:
English
Author Affiliations:
Speech Technology Group, E.TS.I. de Telecomunicación, Av. Complutense, 30. Universidad Politécnica de Madrid, Spain
ISSN:
0957-4174
Access URL:
http://pascal-francis.inist.fr/vibad/index.php?action=search&terms=28843385
Rights:
Copyright 2015 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Computer science; theoretical automation; systems

Telecommunications and information theory
Accession Number:
edscal.28843385
Database:
PASCAL Archive

Further Information

In this paper we present an efficient speech recognition approach for multitopic speech by combining information retrieval techniques and topic-based language modeling. Information retrieval based techniques, such as topic identification by means of Latent Semantic Analysis, are used to identify the topic in a recognized transcription of an audio segment. According to the confidence on the topics that have been identified, we propose a dynamic language model adaptation in order to improve the recognition performance in 'a two stages' automatic speech recognition system. The scheme used for the adaptation of the language model is a linear interpolation between a background general LM and a topic dependent LM. We have studied different approaches to generate the topic dependent LM and also for determining the interpolation weight of this model with the background model. In one of these approaches we use the given topic labels in the training dataset to obtain the topic models. In the other approach we separate the documents in the training dataset into topic clusters by using the k-means algorithm. For strengthening the adaptation models we also use topic identification techniques to group non topic-labeled documents from the EUROPARL text database in order to increase the amount of data for training specific topic based language models. For the evaluation of the proposed system we are using the Spanish partition of the European Parliament Plenary Sessions (EPPS) Database; we selected a subset of the database with 67 labeled topics for the evaluation. For the task of topic identification our experiments show a relative reduction in topic identification error of 44.94% when compared to the baseline method, the Generalized Vector Model with a classic TF-IDF weighting scheme. For the task of dynamic adaptation of LMs applied to ASR we have achieved a relative reduction in WER of 13.52% over a single background language model.