Robust speech recognition using harmonic features. Issue 2 (1st April 2014)

• Record Type: Journal Article
• Authors: Goh, Yeh Huann; Raveendran, Paramesran; Jamuar, Sudhanshu Shekhar
• Is Part Of: IET signal processing. Volume 8:Issue 2(2014)
• Page Start: 167
• Page End: 175
• Publication Date: 2014-04-01
• Subjects: signal reconstruction -- speech recognition; robust speech recognition -- harmonic features -- speech recognition system -- harmonic structure related information -- noisy environment -- harmonic components -- speech signals -- sine function convolution -- speech signal frequency -- reconstructed signal -- extracted harmonic components -- high degree of correlation -- extracted frame energy -- dynamic harmonic features -- European Telecommunications Standards Institute -- front‐end processed mel‐frequency cepstral coefflcients -- perceptual linear prediction -- ETSI front‐end processed MFCC -- PLP‐based speech recognition system; Signal processing -- Periodicals; 621.3822
• DOI: 10.1049/iet-spr.2013.0094
• Languages: English
• ISSNs: 1751-9675

Abstract

Abstract : In this study, the authors propose a speech recognition system using harmonic structure related information to detect harmonic features in noisy environment. The proposed algorithm first extracts the harmonic components contained inside the speech signals using sine function convolution. By setting the frequency of the sine function as equal to the fundamental frequency of speech signals, harmonic components can be extracted out. The reconstructed signal obtained by summing up the extracted harmonic components is found to have a high degree of correlation with the original signal. The extracted frame energy measure of the harmonic components has been further processed to become dynamic harmonic features and then used together with the European Telecommunications Standards Institute (ETSI) front‐end processed mel‐frequency cepstral coefficients (MFCC) feature or the perceptual linear prediction (PLP) feature in the speech recognition system. The proposed enhanced speech recognition system shows a better recognition rate over the ETSI front‐end processed MFCC (or PLP)‐based speech recognition system.