Dual-ALU structure processor for speech recognition

Author

Wu, Gin-Der ; Kuo, Kuei-Ting

Author_Institution

Dept. of Electr. Eng., Nat. Chi Nan Univ., Puli

fYear

2006

fDate

24-26 April 2006

Abstract

This paper proposed a low-cost dual-ALU processor for speech recognition. It does not give an emphasis on sophistication but on low-cost solution. The dual-ALU architecture provides parallel calculation capability. For the consideration of chip size, the area of the second ALU is only half of the first ALU. We use hardware-software codesign method to implement the speech recognition. The feature extraction bases on LPC-cepstrum coefficients, and template matching employs hidden Markov models (HMM). The processor is designed to process the HMM and connect with the ASIC of LPC-cepstrum

Keywords

application specific integrated circuits; cepstral analysis; feature extraction; hardware-software codesign; hidden Markov models; microprocessor chips; parallel architectures; pattern matching; speech recognition; ASIC; HMM; Hidden Markov model; LPC-cepstrum coefficients; feature extraction; hardware-software codesign method; low-cost dual-ALU structure processor architecture; parallel calculation capability; speech recognition; template matching; Application specific integrated circuits; Built-in self-test; Circuit testing; Computer aided instruction; Computer architecture; Digital signal processing; Hardware; Hidden Markov models; Registers; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

System of Systems Engineering, 2006 IEEE/SMC International Conference on

Conference_Location

Los Angeles, CA

Print_ISBN

1-4244-0188-7

Type

conf

DOI

10.1109/SYSOSE.2006.1652296

Filename

1652296