Speaker-independent phoneme recognition using large-scale neural networks.
Satoru NakamuraHidefumi SawaiMasahide SugiyamaPublished in: ICASSP (1992)
Keyphrases
- speech recognition
- speaker dependent
- speaker independent
- neural network
- pattern recognition
- hidden markov models
- speaker identification
- speech recognizer
- speech synthesis
- speaker adaptation
- speech recognition systems
- automatic speech recognition
- speech signal
- noisy environments
- noisy images
- digit recognition
- training process
- speaker recognition
- language model
- classification accuracy
- feature extraction
- face recognition
- image processing