ACL RD-TEC 1.0 Summarization of P98-1107
Paper Title:
A METHOD FOR CORRECTING ERRORS IN SPEECH RECOGNITION USING THE STATISTICAL FEATURES OF CHARACTER CO-OCCURRENCE
A METHOD FOR CORRECTING ERRORS IN SPEECH RECOGNITION USING THE STATISTICAL FEATURES OF CHARACTER CO-OCCURRENCE
Authors: Satoshi Kaki and Eiichiro Sumita and Hitoshi Iida
Primarily assigned technology terms:
- database
- databases
- detection method
- error correction
- error detection
- example-based approach
- language processing
- learning
- machine translation
- matching
- noisy-channel model
- parsing
- parsing technique
- pattern-matching
- processing
- recognition
- recognition process
- recognition system
- recognition systems
- recognizer
- regular expression
- robust parsing
- speech recognition
- speech recognition systems
- speech recognizer
- speech translation
- speech translation system
- translation system
- translation systems
Other assigned terms:
- approach
- case
- character sequence
- characters
- co-occurrence
- content words
- context-free grammar
- grammar
- input string
- language database
- meaning
- method
- n-gram
- noise
- particle
- posterior
- precision
- probability
- procedure
- process
- query
- recognition errors
- segments
- semantic
- semantic distance
- sentence
- spoken language
- substring
- technique
- understanding
- user
- utterance
- word
- words
