Voice recognition based on MFCC, SBC and Spectrograms

Main Article Content

Guillermo Arturo Martínez Mascorro
Gualberto Aguilar Torres

Abstract

One of the problems of the Automatic Speech Recognition systems is the voice’s changes. Typically, a person can have voluntary and involuntary voice’s changes and the system can get confused in these cases, also the changes could be natural and artificial. This paper proposes and recognition system with a parallel identification, using three different algorithms: MFCC, SBC and Spectrogram. Using a Support Vector Machine as a classifier, every algorithm gives a group of persons with the highest likelihood and, after an evaluation, the result is obtained. The aim of this paper is to take advantage of the three algorithms.

Keywords

Reconocimiento del hablante con cambios en la voz, coeficientes cepstrales en la frecuencia de Mel, parámetros cepstrales basados en sub-banda, espectrograma, máquina de soporte vectorial. Speech recognition with voice changes, Mel Frequency Cepstral Coefficients, Subband-Based Cepstral Parameters, Spectrogram, Support Vector Machine.

Abstract 1569 | PDF (Español (España)) Downloads 964

References

I. Mporas, T. Ganchev, M. Siafarikas, and N. Fako- takis, “Comparison of speech features on the speech recognition task,” Journal of Computer Science, vol. 3, no. 8, pp. 608–616, 2007.

B. Logan, “Mel frequency cepstral coefficients for music modeling.” in International Symposium on Music Information Retrieval, 2000.

R. Sarikaya and J. H. Hansen, “High resolution speech feature parametrization for monophone- based stressed speech recognition,” Signal Process- ing Letters, IEEE, vol. 7, no. 7, pp. 182–185, 2000.

G. A. Martínez and G. Aguilar, “Sistema para identificación de hablantes robusto a cambios en la voz,” Ingenius, no. 8, pp. 45–53, 2012.

T. Acharya and A. K. Ray, Image processing: prin- ciples and applications. Wiley, 2005.

R. Solera-Urena, J. Padrell-Sendra, D. Martín- Iglesias, A. Gallardo-Antolín, C. Peláez-Moreno, and F. Díaz-De-María, “Svms for automatic speech recognition: a survey,” Progress in nonlinear speech processing, pp. 190–216, 2007.

Article Sidebar

PDF (Español (España))
Published
Dec 30, 2013
DOI https://doi.org/10.17163/ings.n10.2013.02

Article Details

Issue
No. 10 (2013): July / December
Section
Scientific Paper
Author Biographies

Guillermo Arturo Martínez Mascorro

Ingeniero en Electrónica, Estudiante de la Maestría en Ciencias de Ingeniería en Microelectrónica, Instituto Politécnico Nacional, México DF, México

Gualberto Aguilar Torres

Doctor en Ciencias en Comunicaciones y Electrónica, Maestro en Ciencias de Ingeniería en Microelectrónica, Ingeniero en Comunicaciones y Electrónica, Docente del Instituto Politécnico Nacional en la Sección de Estudios de Posgrado e Investigación de la ESIME Culhuacán, México DF, México.