Title :
Speaker-independent isolated-word recognition LSI
Author :
Miki, Satoshi ; Intoh, Kiyoshi
Author_Institution :
NTT Human Interface Lab., Kanagawa, Japan
Abstract :
Describes the architecture of a newly designed LSI for speaker-independent speech recognition. The recognition algorithm used in this LSI is based on a vector quantization technique and a dynamic time-warping technique using multiple word templates. In order to efficiently execute the complicated recognition algorithm, this LSI has the following architectural features: (1) address-generator independent of the data-calculating circuit, (2) pipelined architecture (3) structure of separate data buses, (4) multiplexed data bus with timing distribution, (5) horizontal-type micro-program. This LSI can recognize up to 32 speaker-independent isolated words (or up to 512 speaker dependent isolated words) within 0.4 seconds after speech endpoint detection. An average of recognition rate for Japanese 10-digit words is 97%. By using this LSI, a speech recognition system can be easily constructed on single board
Keywords :
CMOS integrated circuits; large scale integration; speech recognition; voice equipment; Japanese; address-generator; data buses; dynamic time-warping; horizontal-type micro-program; isolated-word recognition LSI; multiple word templates; multiplexed data bus; pipelined architecture; speaker-independent; speech recognition; timing distribution; vector quantization; Algorithm design and analysis; Fluid flow measurement; Humans; Large scale integration; Linear predictive coding; Signal processing algorithms; Speech analysis; Speech recognition; Telephony; Vector quantization;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on
Conference_Location :
Glasgow
DOI :
10.1109/ICASSP.1989.266547
