Prosody Generation for Speech-to-Speech Translation.
Pablo Daniel AgüeroJordi AdellAntonio BonafontePublished in: ICASSP (1) (2006)
Keyphrases
- speech synthesis
- text to speech
- speech recognition
- audio visual
- speech signal
- multi stream
- prosodic features
- vocal tract
- automatic speech recognition
- real time
- endpoint detection
- speaker identification
- broadcast news
- spoken language
- query translation
- machine translation
- spoken dialogue systems
- speaker recognition
- human computer interaction
- speech processing
- multi modal
- hidden markov models
- search engine
- artificial intelligence
- database
- synthesized speech