Self-Supervised Singing Voice Pre-Training towards Speech-to-Singing Conversion.
Ruiqi LiRongjie HuangYongqi WangZhiqing HongZhou ZhaoPublished in: CoRR (2024)
Keyphrases
- audio features
- text to speech
- acoustic features
- hearing impaired
- music information retrieval
- emotion recognition
- voice activity detection
- training process
- speech recognition errors
- audio visual
- prosodic features
- supervised learning
- data sets
- speech synthesis
- online learning
- training set
- spectral features
- face recognition
- human computer interaction
- data conversion
- recognition engine
- noisy environments
- speech signal
- multimedia
- speech recognition