Vector Quantization based Speech Recognition System: Implementation of VQ based Isolated Word Recognition with Cepstral Coefficients

Islam, Md. Rabiul, Sohrab Mahmud, Md., Fayzur Rahman, Md.

ISBN 10: 3838368916 / ISBN 13: 9783838368917

Editore: LAP LAMBERT Academic Publishing, 2010

Riguardo questo articolo

Like New.

Codice articolo ERICA79038383689166

Dati bibliografici

• Titolo: Vector Quantization based Speech Recognition System: Implementation of VQ based Isolated Word Recognition with Cepstral Coefficients
• Editore: LAP LAMBERT Academic Publishing
• Data di pubblicazione: 2010
• Lingua: Inglese
• ISBN 10: 3838368916
• ISBN 13: 9783838368917
• Rilegatura: Paperback
• Condizione: Like New
• Tipo di libro: book

Descrizione articolo

Riassunto

Automatic Speech Recognition (ASR) has progressed considerably over the past several decades, but still has not achieved the potential imagined at its very beginning. Almost all of the existing applications of ASR systems are PC based. This work is an attempt to develop a speech recognition system that is independent of any PC support and is small enough in size to be used in a daily use consumer appliance. The proposed system would recognize isolated word utterances from a limited vocabulary, provide speaker independence, require less memory and be cost-efficient compared to present ASR systems. In this system, isolated word recognition is performed by using Vector Quantization (VQ) and Mel-Frequency Cepstral Coefficient (MFCC). The final system has been implemented on a vero board with an ATMEGA32 microcontroller. Learning and recognition algorithm have been used to recognize the speech utterances.