Unsupervised training for farsi-english speech-to-speech translation.
Bing XiangYonggang DengYuqing GaoPublished in: ICASSP (2008)
Keyphrases
- text to speech
- broadcast news
- speech recognition
- hearing impaired
- spoken language
- machine translation
- speech synthesis
- english text
- recognition engine
- speech signal
- statistical machine translation
- cross language information retrieval
- automatic speech recognition
- supervised learning
- query translation
- audio visual
- cross language
- training phase
- binary images
- spontaneous speech
- finite state transducers
- information retrieval
- answer questions
- noisy environments
- comparable corpora
- language resources
- unsupervised learning
- speech recognition technology