Inductive generation of phoneme recognition knowledge for a continuous speech recognition system SPREX

1988 ◽  
Vol 84 (S1) ◽  
pp. S170-S170
Author(s):  
Katsuhiko Tsujino ◽  
Riichiro Mizoguchi ◽  
Osamu Kakusho
Keyword(s):  
Speech Recognition ◽  
Recognition System ◽  
Speech Recognition System ◽  
Continuous Speech ◽  
Continuous Speech Recognition ◽  
Phoneme Recognition ◽  
Inductive Generation

A CONTINUOUS SPEECH RECOGNITION SYSTEM USING A MODIFIED LVQ2 METHOD AND A DEPENDENCY GRAMMAR WITH SEMANTIC CONSTRAINTS

1994 ◽  
Vol 08 (01) ◽  
pp. 197-213
Author(s):  
SHOZO MAKINO ◽  
AKINORI ITO ◽  
MITSURU ENDO ◽  
KEN’ITI KIDO
Keyword(s):  
Speech Recognition ◽  
Recognition System ◽  
Finite State Automaton ◽  
Speech Recognition System ◽  
Continuous Speech ◽  
Continuous Speech Recognition ◽  
Phoneme Recognition ◽  
Dependency Grammar ◽  
Matching Algorithm ◽  
Finite State

This paper describes an overview of a continuous speech recognition system composed of an acoustic processor and a linguistic processor. The system deals with 843 conceptual words and 431 functional words. We have constructed an acoustic processor using a modified learning vector quantization method (MLVQ2) for phoneme recognition. The phoneme recognition score was 85.5% for 226 sentences uttered by two male speakers. The linguistic processor is composed of a processor for spotting bunsetsu units (i.e. units similar to a “phrase” in English) and a syntactic processor. The structure of the bunsetsu unit is effectively described by a finite-state automaton, the test-set word-perplexity of which is 230. In the processor for spotting bunsetsu units, using a syntax-driven continuous-DP matching algorithm, the bunsetsu units are spotted from a recognized phoneme sequence and then a bunsetsu unit lattice is generated. In the syntactic processor, the bunsetsu unit lattice is parsed based on the dependency grammar, which is expressed as the correspondence between a FEATURE marker in a modifier-bunsetsu and a SLOT-FILLER marker in a head-bunsetsu. The recognition scores of the bunsetsu units and conceptual words were 75.2% and 88.9% respectively for 226 sentences uttered by the two male speakers.

Sign in / Sign up

Export Citation Format

Share Document