ST: Mix at Three Levels for Speech Translation.
Xuxin ChengQianqian DongFengpeng YueTom KoMingxuan WangYuexian ZouPublished in: ICASSP (2023)
Keyphrases
- speech recognition
- endpoint detection
- speech signal
- automatic speech recognition
- recognition engine
- text to speech
- machine translation
- query translation
- levels of abstraction
- lower levels
- text to speech synthesis
- real time
- language resources
- speech synthesis
- broadcast news
- spoken language
- emotion recognition
- cross language information retrieval
- audio visual