Automatic prosody prediction for Chinese speech synthesis using BLSTM-RNN and embedding features

Computer Science

• Bidirectional Long Short-Term Memory Network 100%
• Conditional Random Field 100%
• Experimental Result 50%
• Learned Feature 50%
• Network Layer 50%
• Neural Network 50%
• Raw Text 50%
• Recurrent Network 50%
• Recurrent Neural Network 100%
• Speech Synthesis 100%
• Superior Performance 50%