Segmentation of prosodic phrases for improving the naturalness of synthesized Mandarin Chinese speech.
Zhengyu NiuPeiqi ChaiPublished in: INTERSPEECH (2000)
Keyphrases
- speech recognition
- text to speech synthesis
- text to speech
- prosodic features
- speech synthesis
- medical images
- level set
- image segmentation
- segmentation algorithm
- segmentation method
- automatic speech recognition
- region growing
- shape prior
- speech signal
- fully automatic
- multiscale
- pattern recognition
- natural language
- search engine
- recognition engine
- broadcast news
- grey level
- segmented images
- multiple objects
- object segmentation
- hidden markov models