Injecting Text in Self-Supervised Speech Pretraining.
Zhehuai ChenYu ZhangAndrew RosenbergBhuvana RamabhadranGary WangPedro J. MorenoPublished in: ASRU (2021)
Keyphrases
- text to speech synthesis
- text to speech
- text recognition
- english text
- speech recognition
- multi lingual
- text mining
- information retrieval
- text input
- database
- spontaneous speech
- neural network
- conversational speech
- speech synthesis
- free text
- web documents
- spoken language
- broadcast news
- textual data
- speech signal
- lexical features
- pattern recognition
- spoken documents
- document analysis
- speaker identification
- dialogue system
- text data
- text retrieval
- machine learning