Voice conversion using duration-embedded bi-HMMs for expressive speech synthesis.
Chung-Hsien WuChi-Chun HsiaTe-Hsien LiuJhing-Fa WangPublished in: IEEE Trans. Speech Audio Process. (2006)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- hidden markov models
- prosodic features
- vocal tract
- language model
- business intelligence
- pattern recognition
- hierarchical hidden markov models
- voice activity detection
- hidden semi markov models
- speech signal
- speech corpus
- automatic speech recognition
- noisy environments
- feature extraction
- information processing
- digital images
- computer vision
- information retrieval
- machine learning
- neural network
- data sets