Mapping speech signals to musical scores through prosodic extraction.
Boyanna TrayanovaDale JoachimPublished in: ICASSP (3) (2005)
Keyphrases
- speech signal
- speech recognition
- acoustic features
- automatic speech recognition
- noisy environments
- automatic speech recognition systems
- speaker identification
- background noise
- additive noise
- linear prediction
- language model
- hidden markov models
- vocal tract
- spectral analysis
- adaptive filtering
- speech synthesis
- blind source separation
- pattern recognition
- speech enhancement
- non stationary
- neural network
- bayesian networks
- feature extraction
- image processing
- speech quality
- sound signals