Speaker Adaptation for Speech Synthesis Based on Deep Neural Networks Using Hidden Semi-Markov Model Structures.
Kento NakaoKei HashimotoKeiichiro OuraYoshihiko NankakuKeiichi TokudaPublished in: APSIPA (2018)
Keyphrases
- speech synthesis
- speech recognition
- speaker adaptation
- neural network
- vocal tract
- pattern recognition
- speaker independent
- speaker dependent
- speech recognizer
- text to speech
- hidden markov models
- hidden semi markov models
- automatic speech recognition
- speech signal
- fuzzy logic
- semi markov
- language model
- abnormality detection
- image processing
- information retrieval
- image acquisition
- speaker identification
- field of view
- monitoring system
- fault diagnosis
- high speed