Unsupervised Speaker Adaptation for DNN-based Speech Synthesis using Input Codes.
Shinji TakakiYoshikazu NishimuraJunichi YamagishiPublished in: APSIPA (2018)
Keyphrases
- speech synthesis
- speech recognition
- speaker adaptation
- vocal tract
- speaker independent
- speech recognizer
- speaker dependent
- automatic speech recognition
- text to speech
- hidden markov models
- speech signal
- language model
- noisy environments
- unsupervised learning
- pattern recognition
- speaker identification
- information retrieval
- image coding
- maximum likelihood