JHU IWSLT 2023 Dialect Speech Translation System Description.
Amir HusseinCihan XiaoNeha VermaThomas ThebaudMatthew WiesnerSanjeev KhudanpurPublished in: IWSLT@ACL (2023)
Keyphrases
- speech recognition
- high level
- speech signal
- machine translation
- neural network
- multimedia
- recognition engine
- linear prediction
- statistical machine translation
- machine translation system
- parallel corpora
- text to speech synthesis
- real time
- endpoint detection
- speech synthesis
- broadcast news
- spoken language
- noisy environments
- automatic speech recognition
- cross language information retrieval
- audio visual