A demiphoneme network representation of speech and automatic labeling techniques for speech data base construction.
Kazuyo TanakaSatoru HayamizuKozo OhtaPublished in: ICASSP (1986)
Keyphrases
- speech recognition
- speech signal
- audio visual
- databases
- database
- endpoint detection
- network structure
- speech music discrimination
- visual speech recognition
- recognition engine
- speech synthesis
- text to speech
- automatic speech recognition
- complex networks
- semi automatic
- spoken language
- spontaneous speech
- active learning
- relational databases
- network traffic
- communication networks
- social network analysis
- emotion recognition
- image representation
- peer to peer
- digital libraries
- hearing impaired
- multimedia