Glottal spectral separation for parametric speech synthesis.
João P. CabralSteve RenalsKorin RichmondJunichi YamagishiPublished in: INTERSPEECH (2008)
Keyphrases
- speech synthesis
- speech recognition
- speech signal
- spectral analysis
- linear prediction
- text to speech
- sound source
- vocal tract
- hidden markov models
- prosodic features
- pattern recognition
- automatic speech recognition
- speech corpus
- hyperspectral imagery
- noisy environments
- introducing additional
- data sets
- hyperspectral
- language model
- spectral decomposition
- parametric models
- spectral features
- image segmentation
- neural network
- spectral resolution
- data mining
- machine learning
- shape grammars
- image analysis
- multispectral
- real time