Self-Supervised Singing Voice Pre-Training towards Speech-to-Singing Conversion.
Ruiqi LiRongjie HuangYongqi WangZhiqing HongZhou ZhaoPublished in: ACL (Findings) (2024)
Keyphrases
- audio features
- text to speech
- acoustic features
- hearing impaired
- music information retrieval
- emotion recognition
- audio visual
- speech recognition
- online learning
- low level
- fundamental frequency
- speech recognition errors
- training set
- training examples
- speech synthesis
- training process
- supervised learning
- mel frequency cepstral coefficients
- test set
- training algorithm
- face recognition
- training samples
- support vector machine
- speech quality