Improving the naturalness of synthetic speech by utilizing the prosody of natural speech.
Toshimitsu MinowaRyo MochizukiHirofumi NishimuraPublished in: INTERSPEECH (2000)
Keyphrases
- speech synthesis
- text to speech
- speech recognition
- audio visual
- speech signal
- speech processing
- multi stream
- vocal tract
- automatic speech recognition
- spoken language
- recognition engine
- broadcast news
- speech recognizer
- spectral features
- emotion recognition
- endpoint detection
- synthesized speech
- text to speech synthesis
- speaker identification
- multimodal interfaces
- english text
- speaker recognition
- real time
- dialogue system
- human computer interaction
- pattern recognition
- multimedia
- machine learning
- real world