Compact and robust speech recognition for embedded use on microprocessors

Author

Hataoka, N. ; Kokubo, H. ; Obuchi, Y. ; Amano, A.

Author_Institution

Central Res. Lab., Hitachi Ltd., Tokyo, Japan

fYear

2002

fDate

9-11 Dec. 2002

Firstpage

288

Lastpage

291

Abstract

We propose a compact and noise robust embedded speech recognition system implemented on microprocessors aiming for sophisticated HMIs (human machine interfaces) of car information systems. The compactness is essential for embedded systems because there are strict restrictions of CPU (central processing unit) power and available memory capacities. In this paper, first we report noise robust acoustic HMMs (hidden Markov models) and a compact spectral subtraction (SS) method after exhausting evaluation stages using real speech data recorded at car running environments. Next, we propose very novel memory assignment of acoustic models based on the product codes or sub-vector quantization technique resulting on 1 fourth memory reduction for the 2000-word vocabulary.

Keywords

embedded systems; hidden Markov models; microprocessor chips; reduced instruction set computing; speech recognition; speech-based user interfaces; CPU power; HMI; RISC microprocessor; SuperH; car information system; central processing unit; compact spectral subtraction; compact speech recognition; embedded speech recognition system; hidden Markov model; human machine interface; memory assignment; memory capacity; memory reduction; noise robust acoustic HMM; product code; robust speech recognition; speech middleware; sub-vector publication technique; Acoustic noise; Central Processing Unit; Embedded system; Hidden Markov models; Humans; Information systems; Microprocessors; Noise robustness; Speech recognition; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Signal Processing, 2002 IEEE Workshop on

Print_ISBN

0-7803-7713-3

Type

conf

DOI

10.1109/MMSP.2002.1203302

Filename

1203302