Robust features derived from temporal trajectory filtering for speech recognition under the corruption of additive and convolutional noises.
Kuo-Hwei YuoHsiao-Chuan WangPublished in: ICASSP (1998)
Keyphrases
- speech recognition
- speech recognition systems
- noisy environments
- hidden markov models
- speech synthesis
- speech processing
- pattern recognition
- salt pepper
- language model
- speech recognizer
- cepstral coefficients
- temporal information
- speech signal
- automatic speech recognition
- speech understanding
- feature set
- speech recognition technology
- neural network
- extracted features
- low level
- speech retrieval
- feature space
- isolated word