Multi-resolution phonetic/segmental features and models for HMM-based speech recognition.
Saeed VaseghiNaomi HarteBen MilnerPublished in: ICASSP (1997)
Keyphrases
- speech recognition
- hidden markov models
- acoustic models
- speech recognition systems
- multiresolution
- language model
- speaker independent
- speech synthesis
- pattern recognition
- speech processing
- speech signal
- automatic speech recognition
- handwriting recognition
- speech recognizer
- cepstral coefficients
- speech retrieval
- noisy environments
- probabilistic model
- feature extraction
- feature vectors
- feature space
- computer vision
- visual speech
- speaker adaptation
- speech recognition technology