A Deep Generative Architecture for Postfiltering in Statistical Parametric Speech Synthesis.
Ling-Hui ChenTuomo RaitioCassia Valentini-BotinhaoZhen-Hua LingJunichi YamagishiPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2015)
Keyphrases
- speech synthesis
- speech recognition
- data driven
- text to speech
- vocal tract
- management system
- generative model
- statistical analysis
- prosodic features
- software architecture
- neural network
- information theoretic
- statistical models
- language model
- hidden markov models
- machine learning
- real time
- speech corpus
- kernel density estimators