Multi-speaker Text-to-speech Training with Speaker Anonymized Data.
Wen-Chin HuangYi-Chiao WuTomoki TodaPublished in: CoRR (2024)
Keyphrases
- prosodic features
- text to speech
- speaker verification
- speech synthesis
- speech recognition
- audio visual
- automatic speech recognition
- training set
- anonymized data
- speaker identification
- cloud computing
- word processing
- programming tool
- text to speech synthesis
- data sets
- writing skills
- noisy environments
- data model
- database systems