Keynote speech 3: Toward simultaneous, natural and multimodal speech-to-speech translation.
Satoshi NakamuraPublished in: O-COCOSDA/CASLRE (2015)
Keyphrases
- speech recognition
- audio visual
- speech signal
- endpoint detection
- speech synthesis
- automatic speech recognition
- text to speech
- recognition engine
- dialogue system
- multimodal interfaces
- finite state transducers
- data sets
- emotion recognition
- language acquisition
- noisy environments
- multi stream
- speaker verification
- speaker identification
- machine translation
- human computer interaction
- multi modal
- natural language processing
- multimedia