Combining pulse-based features for rejecting far-field speech in a HMM-based Voice Activity Detector. Computers & Electrical Engineering (CAEE).

Varela Serrano, Oscar; San Segundo Hernández, Rubén y Hernández, Luis A. (2011). Combining pulse-based features for rejecting far-field speech in a HMM-based Voice Activity Detector. Computers & Electrical Engineering (CAEE).. "Computers and Electrical Engineering", v. 37 (n. 4); pp. 589-600. ISSN 0045-7906. https://doi.org/10.1016/j.compeleceng.2011.04.005.

Descripción

Título: Combining pulse-based features for rejecting far-field speech in a HMM-based Voice Activity Detector. Computers & Electrical Engineering (CAEE).
Autor/es:
  • Varela Serrano, Oscar
  • San Segundo Hernández, Rubén
  • Hernández, Luis A.
Tipo de Documento: Artículo
Título de Revista/Publicación: Computers and Electrical Engineering
Fecha: Julio 2011
Volumen: 37
Materias:
Escuela: E.T.S.I. Telecomunicación (UPM)
Departamento: Ingeniería Electrónica
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (304kB) | Vista Previa

Resumen

Nowadays, several computational techniques for speech recognition have been proposed. These techniques suppose an important improvement in real time applications where speaker interacts with speech recognition systems. Although researchers proposed many methods, none of them solve the high false alarm problem when far-field speakers interfere in a human-machine conversation. This paper presents a two-class (speech and non-speech classes) decision-tree based approach for combining new speech pulse features in a VAD (Voice Activity Detector) for rejecting far-field speech in speech recognition systems. This Decision Tree is applied over the speech pulses obtained by a baseline VAD composed of a frame feature extractor, a HMM-based (Hidden Markov Model) segmentation module and a pulse detector. The paper also presents a detailed analysis of a great amount of features for discriminating between close and far-field speech. The detection error obtained with the proposed VAD is the lowest compared to other well-known VADs

Más información

ID de Registro: 8863
Identificador DC: http://oa.upm.es/8863/
Identificador OAI: oai:oa.upm.es:8863
Identificador DOI: 10.1016/j.compeleceng.2011.04.005
URL Oficial: http://www.sciencedirect.com/science/journal/00457906
Depositado por: Memoria Investigacion
Depositado el: 23 Sep 2011 10:15
Ultima Modificación: 20 Abr 2016 17:30
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • e-ciencia
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM