PHONEix: Acoustic Feature Processing Strategy for Enhanced Singing Pronunciation with Phoneme Distribution Predictor.
Yuning WuJiatong ShiTao QianDongji GaoQin JinPublished in: CoRR (2023)
Keyphrases
- speech recognition
- speaker independent
- speech recognition systems
- automatic speech recognition
- real time
- image features
- acoustic models
- information processing
- random variables
- data processing
- feature set
- hidden markov models
- feature vectors
- speech sounds
- search strategy
- selection scheme
- speech synthesis
- neural network
- automatic speech recognition systems
- speaker dependent
- speech recognizer
- optimal strategy
- language learning
- data distribution
- low level