Large-vocabulary spoken word recognition using time-delay neural network phoneme spotting and predictive lr-parsing.
Yasuhiro MinamiHidefumi SawaiMasanori MiyatakePublished in: Systems and Computers in Japan (1991)
Keyphrases
- speech recognition
- keyword spotting
- speech understanding
- speech recognizer
- automatic speech recognition
- hidden markov models
- logistic regression
- speech synthesis
- language model
- sign language recognition
- low resolution
- speech recognition systems
- speaker adaptation
- word order
- speech signal
- continuous speech recognition
- context free grammars
- sign language
- natural language
- parse tree
- speaker identification
- linguistic analysis
- natural language processing
- syntactic and semantic dependencies
- natural language parsing
- image processing
- phrase structure
- intermediate representation
- noisy environments
- context dependent
- unsupervised learning
- pattern recognition