Joint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation.
Kun WeiLong ZhouZiqiang ZhangLiping ChenShujie LiuLei HeJinyu LiFuru WeiPublished in: CoRR (2022)
Keyphrases
- speech recognition
- speech signal
- text to speech synthesis
- text to speech
- text input
- automatic speech recognition
- speech synthesis
- machine translation
- spoken language
- speaker identification
- text recognition
- hearing impaired
- conversational speech
- english text
- lexical features
- multi lingual
- broadcast news
- synthesized speech
- dialogue system
- vocal tract
- training set