DSP based improved Speech Recognition system

Author

Daphal, Swapnil D. ; Jagtap, Sonal K.

Author_Institution

Electr. & Telecommun. Dept., SKN Coll. of Eng., Pune, India

fYear

2012

fDate

19-20 Oct. 2012

Firstpage

1

Lastpage

6

Abstract

Processing of large amount of data is an important aspect of Speech Recognition (SR). However, to formulate speech recognition system in small devices is not simple. This paper suggests Digital Signal Processor (DSP) based speech recognition system with improved performance in terms of recognition accuracies and computational cost. The comprehensive survey of various approaches of feature extraction, like Mel Filter Banks with Mel Frequency Cepstrum Coefficients (MFCC) and Cochlear Filter Banks (CFB) with Zero-crossings is given. Amongst various feature classification techniques, the suitability of the Support Vector Machine (SVM) classifier for the proposed system is significant.

Keywords

channel bank filters; signal classification; speech recognition; support vector machines; CFB; DSP; DSP based improved speech recognition system; MFCC; Mel filter banks; Mel frequency cepstrum coefficients; SR; SVM classifier; cochlear filter banks; computational cost; digital signal processor; feature classification techniques; feature extraction; recognition accuracies; support vector machine classifier; zero-crossings; Accuracy; Feature extraction; Filter banks; Mel frequency cepstral coefficient; Speech; Speech recognition; Support vector machines; CFB; DSP; Feature Classification; Feature Extraction; MFCC; SVM; Speech Recognition; Zero-crossings;

fLanguage

English

Publisher

ieee

Conference_Titel

Communication, Information & Computing Technology (ICCICT), 2012 International Conference on

Conference_Location

Mumbai

Print_ISBN

978-1-4577-2077-2

Type

conf

DOI

10.1109/ICCICT.2012.6398181

Filename

6398181