Adversarial Speaker-Consistency Learning Using Untranscribed Speech Data for Zero-Shot Multi-Speaker Text-to-Speech.
Byoung Jin ChoiMyeonghun JeongMinchan KimSung Hwan MunNam Soo KimPublished in: CoRR (2022)
Keyphrases
- text to speech
- data sets
- speech recognition
- database
- prosodic features
- data points
- data analysis
- speech synthesis
- audio visual
- learning process
- prior knowledge
- speaker verification
- automatic speech recognition
- background knowledge
- speaker recognition
- supervised learning
- active learning
- learning models
- labeled data
- language acquisition
- data collection
- word processing
- object oriented
- data sources
- audio stream
- synthesized speech