Sub-Phonetic Modeling For Capturing Pronunciation Variations For Conversational Speech Synthesis.
Kishore PrahalladAlan W. BlackMosur RavishankarPublished in: ICASSP (1) (2006)
Keyphrases
- speech recognition
- speech synthesis
- vocal tract
- hidden markov models
- prosodic features
- speech signal
- language model
- automatic speech recognition
- noisy environments
- pattern recognition
- speaker identification
- speech recognizer
- acoustic models
- real time
- text to speech
- machine learning
- neural network
- speaker independent
- data sets