A Paradigm for Limited Vocabulary Speech Recognition Based on Redundant Spectro-Temporal Feature Sets.
Sourish ChaudhuriBhiksha RajTony EzzatPublished in: INTERSPEECH (2011)
Keyphrases
- speech recognition
- feature set
- cepstral coefficients
- isolated word
- language model
- hidden markov models
- feature selection
- pattern recognition
- speech signal
- automatic speech recognition
- speech synthesis
- speaker identification
- feature space
- structural features
- classification accuracy
- speech recognizer
- feature extraction
- feature vectors
- noisy environments
- speaker independent
- data mining
- out of vocabulary
- audio features
- extracted features
- bayesian networks