Speaker conversion in ARX-based source-formant type speech synthesis.
Hiroki MoriHideki KasuyaPublished in: INTERSPEECH (2003)
Keyphrases
- speech synthesis
- speech recognition
- vocal tract
- prosodic features
- speech signal
- language model
- text to speech
- hidden markov models
- automatic speech recognition
- speaker diarization
- speech recognizer
- speaker independent
- speech corpus
- speaker identification
- speaker dependent
- speaker verification
- image acquisition
- speaker adaptation
- noisy environments
- real time
- pattern recognition
- decision trees
- website
- real world
- neural network