Distinctive phonetic feature extraction for robust speech recognition.
Takashi FukudaWataru YamamotoTsuneo NittaPublished in: ICASSP (2) (2003)
Keyphrases
- speech recognition
- feature extraction
- noisy environments
- speaker identification
- pattern recognition
- speech signal
- hidden markov models
- cepstral coefficients
- speech processing
- automatic speech recognition
- language model
- speech recognizer
- speaker independent
- speech understanding
- speech synthesis
- speech recognition systems
- image processing
- machine learning
- speech recognition technology
- speaker recognition
- principal component analysis
- feature vectors
- face recognition
- feature selection
- hybrid method
- speaker diarization
- wavelet transform
- neural network