Speaker-independent French digit recognition using word-based vector quantization and hidden Markov models.
Alain TassyLaurent MicletPublished in: ICASSP (1986)
Keyphrases
- speaker independent
- vector quantization
- hidden markov models
- speech recognition
- speech recognizer
- speech recognition systems
- speaker dependent
- image compression
- speaker adaptation
- co occurrence
- acoustic models
- speaker recognition
- pattern recognition
- conditional random fields
- word segmentation
- image segmentation
- discriminative training
- speech signal
- speaker identification
- neural network
- n gram
- machine learning