Phoneme recognition based on hybrid neural networks with inhibition/enhancement of distinctive phonetic feature (DPF) trajectories.
Mohammad Nurul HudaKouichi KatsuradaTsuneo NittaPublished in: INTERSPEECH (2008)
Keyphrases
- hybrid neural
- phoneme recognition
- neural network
- speaker dependent
- speech recognition
- hidden markov models
- hopfield neural network
- feature vectors
- image processing
- pattern recognition
- machine learning
- image enhancement
- fuzzy systems
- learning rules
- maximum likelihood
- computational intelligence
- feature extraction
- feature selection