Grupo DIANA

  • Increase font size
  • Default font size
  • Decrease font size

Topic-dependent language model switching for embedded automatic speech recognition

Research Area: Year: 2012
Type of Publication: Article Keywords: Automatic speech recognition; Different domains; Embedded device; Language model; Multiple domains; Network availability; New applications; Voice interfaces, Artificial intelligence, Computational linguistics
Authors: Santos Pérez, Marcos; González Parada, Eva; Cano García, José Manuel
Journal: Advances in Intelligent and Soft Computing Volume: 153 AISC
Pages: 235-242
ISSN: 1867-5662
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
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.

Copyright © 2021 Grupo DIANA. All Rights Reserved.

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