Objective quality evaluation in blind source separation for speech recognition in a real room

  • Authors:

  • Leandro Di Persia;Masuzo Yanagida;Hugo Leonardo Rufiner;Diego Milone

  • Affiliations:

  • Laboratorio de Cibernética, Facultad de Ingeniería, Universidad Nacional de Entre Ríos, C.C. 47 Suc. 3-3100 Paraná, Argentina and Grupo de Investigación en Señales e ...;Department of Knowledge Engineering, Doshisha University, 1-3, Tatara-Miyakodani, Kyo-Tanabe 610-0321, Japan;Laboratorio de Cibernética, Facultad de Ingeniería, Universidad Nacional de Entre Ríos, C.C. 47 Suc. 3-3100 Paraná, Argentina and Grupo de Investigación en Señales e ...;Laboratorio de Cibernética, Facultad de Ingeniería, Universidad Nacional de Entre Ríos, C.C. 47 Suc. 3-3100 Paraná, Argentina and Grupo de Investigación en Señales e ...

  • Venue:
  • Signal Processing
  • Year:
  • 2007

Quantified Score

Hi-index 0.08

Visualization

Abstract

The determination of quality of the signals obtained by blind source separation is a very important subject for development and evaluation of such algorithms. When this approach is used as a pre-processing stage for automatic speech recognition, the quality measure of separation applied for assessment should be related to the recognition rates of the system. Many measures have been used for quality evaluation, but in general these have been applied without prior research of their capabilities as quality measures in the context of blind source separation, and often they require experimentation in unrealistic conditions. Moreover, these measures just try to evaluate the amount of separation, and this value could not be directly related to recognition rates. Presented in this work is a study of several objective quality measures evaluated as predictors of recognition rate of a continuous speech recognizer. Correlation between quality measures and recognition rates is analyzed for a separation algorithm applied to signals recorded in a real room with different reverberation times and different kinds and levels of noise. A very good correlation between weighted spectral slope measure and the recognition rate has been verified from the results of this analysis. Furthermore, a good performance of total relative distortion and cepstral measures for rooms with relatively long reverberation time has been observed.