Improving Speech Translation by Fusing Speech and Text.
Wenbiao YinZhicheng LiuChengqi ZhaoTao WangJian TongRong YePublished in: EMNLP (Findings) (2023)
Keyphrases
- text to speech
- speech recognition
- text to speech synthesis
- english text
- multi lingual
- lexical features
- speech signal
- text recognition
- audio visual
- speech synthesis
- automatic speech recognition
- spontaneous speech
- endpoint detection
- emotion recognition
- text retrieval
- recognition engine
- spoken language
- text input
- pattern recognition
- information retrieval
- database
- noisy environments
- text documents
- co occurrence
- text mining
- conversational speech
- language generation