Picture for Yongguo Kang

Yongguo Kang

Multi-reference Tacotron by Intercross Training for Style Disentangling,Transfer and Control in Speech Synthesis

Add code
Apr 04, 2019
Figure 1 for Multi-reference Tacotron by Intercross Training for Style Disentangling,Transfer and Control in Speech Synthesis
Figure 2 for Multi-reference Tacotron by Intercross Training for Style Disentangling,Transfer and Control in Speech Synthesis
Figure 3 for Multi-reference Tacotron by Intercross Training for Style Disentangling,Transfer and Control in Speech Synthesis
Figure 4 for Multi-reference Tacotron by Intercross Training for Style Disentangling,Transfer and Control in Speech Synthesis
Viaarxiv icon

Deep Voice: Real-time Neural Text-to-Speech

Add code
Mar 07, 2017
Figure 1 for Deep Voice: Real-time Neural Text-to-Speech
Figure 2 for Deep Voice: Real-time Neural Text-to-Speech
Figure 3 for Deep Voice: Real-time Neural Text-to-Speech
Figure 4 for Deep Voice: Real-time Neural Text-to-Speech
Viaarxiv icon