Tts4pretrain 2.0: Advancing the use of Text and Speech in ASR Pretraining with Consistency and Contrastive Losses.
Zhehuai ChenYu ZhangAndrew RosenbergBhuvana RamabhadranPedro J. MorenoGary WangPublished in: ICASSP (2022)
Keyphrases
- text to speech
- speech synthesis
- text to speech synthesis
- spontaneous speech
- automatic speech recognition
- prosodic features
- english text
- speech recognition
- speech corpus
- conversational speech
- spoken words
- word processing
- speech signal
- vocal tract
- human machine interaction
- noisy environments
- database
- text recognition
- recognition errors
- document images
- pattern recognition