Speech recognition processors using fuzzy pattern matching

Author

Ariyoshi, T. ; Kuriki, S. ; Kawamoto, T. ; Yasuda, S.

Author_Institution

Ricoh Co. Ltd. Res. & Dev. Center, Yokohama, Japan

fYear

1988

fDate

16-19 May 1988

Abstract

A set of LSIs for speech recognition using binary time spectrum pattern (BTSP) and pattern matching based on fuzzy theory (fuzzy pattern matching) is described. The set offers both speaker-dependent and -independent voice-recognition capabilities by changing the external program ROM. In the speaker-dependent case it has up to 1000 in the vocabulary (recognition rate 95%), while in the independent case it has a 120-word vocabulary (recognition rate 92%). The set consists of two processors: one extracts voice features and generates BTSPs, the other has a 16-bit CPU core for recognition and a unit for calculating similarity. The LSI set needs external ROM and RAM. The former stores recognition, control, and other application programs while latter stores voice templates

Keywords

computerised signal processing; large scale integration; microprocessor chips; pattern recognition; signal processing equipment; speech recognition; voice equipment; 16 bit; LSI; binary time spectrum pattern; fuzzy pattern matching; speaker dependent equipment; speaker independent equipment; voice templates; voice-recognition; Calculators; Fluctuations; Frequency; Large scale integration; Pattern matching; Pattern recognition; Read only memory; Resonance; Speech recognition; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Custom Integrated Circuits Conference, 1988., Proceedings of the IEEE 1988

Conference_Location

Rochester, NY

Type

conf

DOI

10.1109/CICC.1988.20841

Filename

20841