Noise-robust ASR by using distinctive phonetic features approximated with logarithmic normal distribution of HMM.
Takashi FukudaTsuneo NittaPublished in: INTERSPEECH (2003)
Keyphrases
- normal distribution
- speech recognition
- noisy environments
- hidden markov models
- automatic speech recognition
- feature extraction
- pattern recognition
- feature vectors
- speech signal
- random variables
- higher order
- parameter estimation
- probability distribution
- feature space
- feature selection
- statistical analysis
- decision makers
- machine learning
- principal component analysis