Discriminative auditory-based features for robust speech recognition.
Brian Kan-Wing MakYik-Cheung TamPeter Qi LiPublished in: IEEE Trans. Speech Audio Process. (2004)
Keyphrases
- speech recognition
- speech recognition systems
- hidden markov models
- noisy environments
- pattern recognition
- cepstral coefficients
- speech processing
- language model
- automatic speech recognition
- feature extraction
- speech synthesis
- speech recognizer
- speaker identification
- mel frequency cepstral coefficients
- speech signal
- feature set
- low level
- speech retrieval
- information retrieval
- speech recognition errors
- speech recognition technology
- speaker diarization
- feature space
- computer vision
- speech understanding
- keyword spotting
- non stationary
- multi modal
- feature vectors