Speaker Adaptation of Various Components in Deep Neural Network based Speech Synthesis.
Shinji TakakiSangjin KimJunichi YamagishiPublished in: SSW (2016)
Keyphrases
- speech synthesis
- speech recognition
- speaker adaptation
- vocal tract
- speaker independent
- text to speech
- speech recognizer
- automatic speech recognition
- prosodic features
- pattern recognition
- hidden markov models
- neural network
- speaker dependent
- language model
- speech signal
- noisy environments
- image acquisition
- maximum likelihood