Injecting Text in Self-Supervised Speech Pretraining.
Zhehuai ChenYu ZhangAndrew RosenbergBhuvana RamabhadranGary WangPedro J. MorenoPublished in: CoRR (2021)
Keyphrases
- text to speech
- text to speech synthesis
- english text
- text retrieval
- speech recognition
- lexical features
- text recognition
- text input
- text mining
- multi lingual
- information retrieval
- spontaneous speech
- database
- speech synthesis
- free text
- language generation
- spoken documents
- speech signal
- human language
- semantic information
- web documents
- multimedia
- spoken words