Phoneix: Acoustic Feature Processing Strategy for Enhanced Singing Pronunciation With Phoneme Distribution Predictor.
Yuning WuJiatong ShiTao QianDongji GaoQin JinPublished in: ICASSP (2023)
Keyphrases
- speech recognition
- automatic speech recognition
- speaker independent
- speech recognition systems
- real time
- hidden markov models
- neural network
- data processing
- pattern recognition
- feature vectors
- image features
- random variables
- central processor
- acoustic models
- feature distributions
- feature set
- probability distribution
- data distribution
- selection criterion
- information processing
- feature extraction
- speech sounds
- face recognition