Selecting non-uniform units from a very large corpus for concatenative speech synthesizer.
Min ChuHu PengHong-yun YangEric ChangPublished in: ICASSP (2001)
Keyphrases
- text to speech
- spontaneous speech
- conversational speech
- speech synthesis
- speech recognition
- manually annotated
- lexical features
- automatic speech recognition
- spoken language
- noisy environments
- open domain
- selection algorithm
- test set
- neural network
- lexical units
- linguistic features
- recognition engine
- speaker identification
- spoken dialog
- spanish language
- spoken document retrieval
- word processing
- linear prediction
- speech signal
- user interface
- pattern recognition