Autocorrelation-based noise subtraction method with smoothing, overestimation, energy, and cepstral mean and variance normalization for noisy speech recognitionReportar como inadecuado




Autocorrelation-based noise subtraction method with smoothing, overestimation, energy, and cepstral mean and variance normalization for noisy speech recognition - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

EURASIP Journal on Audio, Speech, and Music Processing

, 2017:13

First Online: 21 June 2017Received: 10 February 2017Accepted: 04 June 2017DOI: 10.1186-s13636-017-0110-8

Cite this article as: Farahani, G. J AUDIO SPEECH MUSIC PROC. 2017 2017: 13. doi:10.1186-s13636-017-0110-8

Abstract

Autocorrelation domain is a proper domain for clean speech signal and noise separation. In this paper, a method is proposed to decrease effects of noise on the clean speech signal, autocorrelation-based noise subtraction ANS. Then to deal with the error introduced by assumption that noise and clean speech signal are uncorrelated, two methods are proposed. Also to improve recognition rate of speech recognition system, overestimation parameter is used. Finally, with the addition of energy and cepstral mean and variance normalization to features of speech, recognition rate has improved considerably in comparison to standard features and other correlation-based methods. The proposed methods are tested on the Aurora 2 database. Between different proposed methods, autocorrelation-based noise subtraction method with smoothing, overestimation, energy, and cepstral mean and variance normalization ANSSOEMV method has a best recognition rate improvement in average than MFCC features which is 64.91% on the Aurora 2 database.

KeywordsAutocorrelation-based methods Noise subtraction Robustness Recognition rate Speech recognition 



Autor: Gholamreza Farahani

Fuente: https://link.springer.com/







Documentos relacionados