Saltar al contenido
Saltar a la navegación principal
Saltar a la primera columna
Saltar a la segunda columna

Grupo DIANA

Topic-dependent language model switching for embedded automatic speech recognition

BibTex:
Líneas de Trabajo:		Año:	2012
Tipo de publicación:	Artículo	Palabras clave:	Automatic speech recognition; Different domains; Embedded device; Language model; Multiple domains; Network availability; New applications; Voice interfaces, Artificial intelligence, Computational linguistics
Autores:	Santos Pérez, Marcos; González Parada, Eva; Cano García, José Manuel
Journal:	Advances in Intelligent and Soft Computing	Volumen:	153 AISC
Páginas:	235-242

ISSN:	1867-5662

@article{Santos-Pérez2012235, author = "Santos P{\'e}rez, Marcos and Gonz{\'a}lez Parada, Eva and Cano Garc{\'i}a, Jos{\'e} Manuel", abstract = "Embedded devices incorporate everyday new applications in different domains due to their increasing computational power.Many of these applications have a voice interface that uses Automatic Speech Recognition (ASR). When the complexity of the language model is high, it is common to use an external server to perform the recognition at the expense of certain limitations (network availability, latency, etc.). This paper focuses on a new proposal to improve the efficiency of the usage of the language model in a recognizer for multiple domains. The idea is based on the selection of a proper language model for each domain within the ASR system. © 2012 Springer-Verlag.", address = "Salamanca", doi = "10.1007/978-3-642-28783-1_30", isbn = "9783642287824", issn = "18675662", journal = "Advances in Intelligent and Soft Computing", keywords = "Automatic speech recognition; Different domains; Embedded device; Language model; Multiple domains; Network availability; New applications; Voice interfaces, Artificial intelligence, Computational linguistics", note = "Conference of org.apache.xalan.xsltc.dom.DOMAdapter@6625d1ea ; Conference Date: org.apache.xalan.xsltc.dom.DOMAdapter@3cf88e0a Through org.apache.xalan.xsltc.dom.DOMAdapter@623551cb; Conference Code:89851", pages = "235-242", title = "{T}opic-dependent language model switching for embedded automatic speech recognition", volume = "153 AISC", year = "2012", }
Nota:	Conference of org.apache.xalan.xsltc.dom.DOMAdapter@6625d1ea ; Conference Date: org.apache.xalan.xsltc.dom.DOMAdapter@3cf88e0a Through org.apache.xalan.xsltc.dom.DOMAdapter@623551cb; Conference Code:89851
Abstract:	Embedded devices incorporate everyday new applications in different domains due to their increasing computational power.Many of these applications have a voice interface that uses Automatic Speech Recognition (ASR). When the complexity of the language model is high, it is common to use an external server to perform the recognition at the expense of certain limitations (network availability, latency, etc.). This paper focuses on a new proposal to improve the efficiency of the usage of the language model in a recognizer for multiple domains. The idea is based on the selection of a proper language model for each domain within the ASR system. © 2012 Springer-Verlag.
[Bibtex] [RIS]

Mostrar comentarios Comentar

Castellano (España)

English (United Kingdom)

Formulario de acceso

Copyright © 2022 Grupo DIANA. Todos los derechos reservados.

GRUPO DIANA | Dpto. Tecnología Electrónica | UNIVERSIDAD DE MÁLAGA
Campus de Teatinos| 29071 MÁLAGA | Tlf: +34 95 2131352 | FAX: +34 95 2131447