On the use of prosody in a speech-to-speech translator.
Volker StromAnja ElsnerWolfgang HessWalter KasperAlexandra KleinHans-Ulrich KriegerJörg SpilkerHans WeberGünther GörzPublished in: EUROSPEECH (1997)
Keyphrases
- text to speech
- speech synthesis
- speech recognition
- audio visual
- speech signal
- spoken language
- endpoint detection
- prosodic features
- speech recognizer
- multi stream
- information systems
- hearing impaired
- text to speech synthesis
- recognition engine
- broadcast news
- hidden markov models
- spoken dialogue systems
- speech processing
- multimodal interfaces
- speaker identification
- noisy environments
- vocal tract
- natural language processing
- audio stream
- multimedia
- feature selection
- databases