Realization of speech recognition using DSP (digital signal processor)

Author

Chin, Heungsuk ; Kim, J. ; Kim, I. ; Kwon, Y. ; Lee, K. ; Yang, Sung-il

Author_Institution

Dept. of Phys., Hanyang Univ., Ansan, South Korea

Volume

1

fYear

2001

fDate

2001

Firstpage

508

Abstract

Huge data processing in speech recognition is a tendency. But it is not easy to develop and implement speech recognition system in a small machine. For that reason, the authors have developed a PC-independent speech recognition system using a digital signal processor (DSP). They performed experimental speech recognition tests for some ordinary words. To test the online performance of the system, they developed a program that would detect environmental noise and the endpoint of speech in real time. In experiments, they used 10^th order cepstrum coefficients and log-scaled energy as the feature vectors and the discrete hidden Markov model (DHMM) as the recognition tool. For the experiment, they selected 5 speeches of 5 males per model for training

Keywords

cepstral analysis; digital signal processing chips; hidden Markov models; speech recognition; vectors; 0^th order cepstrum coefficients; DSP realisation; PC-independent speech recognition system; digital signal processor; discrete hidden Markov model; feature vectors; log-scaled energy; online performance testing; real-time speech endpoint detection; speech recognition; speech recognition tests; Data processing; Digital signal processing; Digital signal processors; Hidden Markov models; Performance evaluation; Real time systems; Speech enhancement; Speech recognition; System testing; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Electronics, 2001. Proceedings. ISIE 2001. IEEE International Symposium on

Conference_Location

Pusan

Print_ISBN

0-7803-7090-2

Type

conf

DOI

10.1109/ISIE.2001.931844

Filename

931844