Consideration of Infants' Vocal Imitation Through Modeling Speech as Timbre-Based Melody.
Nobuaki MinematsuTazuko NishimuraPublished in: JSAI (2007)
Keyphrases
- speech signal
- acoustic features
- music information retrieval
- language acquisition
- speech recognition
- emotion recognition
- speaker verification
- video retrieval
- neural network
- audio visual
- biologically inspired
- speech synthesis
- multi modal
- probabilistic model
- feature extraction
- face recognition
- genetic algorithm
- information retrieval