Demos for partial publications of the TTS group in Baidu Speech

Paper List

[1] Multi-task WaveNet: A Multi-task Generative Model for Statistical Parametric Speech Synthesis without Fundamental Frequency Conditions Demo

[2] EMPHASIS: An Emotional Phoneme-based Acoustic Model for Speech Synthesis System Demo

[3] Multi-references Tacotron by Intercross Training for Style Disentangling, Transfer and Control in Speech Synthesis Demo