A Japanese text dictation system based on phoneme recognition and a dependency grammar.
Shozo MakinoAkinori ItoMitsuru EndoKen'iti KidoPublished in: ICASSP (1991)
Keyphrases
- phoneme recognition
- speech recognition
- speaker dependent
- hidden markov models
- automatic speech recognition
- dependency structure
- natural language
- language model
- speaker identification
- speaker independent
- linguistic knowledge
- speech signal
- neural network
- audio signal
- speech corpus
- feature space
- multi modal
- speech recognition systems
- feature extraction
- information retrieval