Picture for Frank K. Soong

Frank K. Soong

ContextSpeech: Expressive and Efficient Text-to-Speech for Paragraph Reading

Add code
Jul 03, 2023
Viaarxiv icon

A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS

Add code
Sep 22, 2022
Figure 1 for A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS
Figure 2 for A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS
Figure 3 for A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS
Figure 4 for A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS
Viaarxiv icon

ParaTTS: Learning Linguistic and Prosodic Cross-sentence Information in Paragraph-based TTS

Add code
Sep 14, 2022
Figure 1 for ParaTTS: Learning Linguistic and Prosodic Cross-sentence Information in Paragraph-based TTS
Figure 2 for ParaTTS: Learning Linguistic and Prosodic Cross-sentence Information in Paragraph-based TTS
Figure 3 for ParaTTS: Learning Linguistic and Prosodic Cross-sentence Information in Paragraph-based TTS
Figure 4 for ParaTTS: Learning Linguistic and Prosodic Cross-sentence Information in Paragraph-based TTS
Viaarxiv icon

Disentangling Style and Speaker Attributes for TTS Style Transfer

Add code
Jan 24, 2022
Figure 1 for Disentangling Style and Speaker Attributes for TTS Style Transfer
Figure 2 for Disentangling Style and Speaker Attributes for TTS Style Transfer
Figure 3 for Disentangling Style and Speaker Attributes for TTS Style Transfer
Figure 4 for Disentangling Style and Speaker Attributes for TTS Style Transfer
Viaarxiv icon

Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge

Add code
Oct 19, 2021
Figure 1 for Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge
Figure 2 for Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge
Figure 3 for Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge
Figure 4 for Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge
Viaarxiv icon

Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS

Add code
Jun 18, 2021
Figure 1 for Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS
Figure 2 for Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS
Figure 3 for Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS
Figure 4 for Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS
Viaarxiv icon

Speech BERT Embedding For Improving Prosody in Neural TTS

Add code
Jun 15, 2021
Figure 1 for Speech BERT Embedding For Improving Prosody in Neural TTS
Figure 2 for Speech BERT Embedding For Improving Prosody in Neural TTS
Figure 3 for Speech BERT Embedding For Improving Prosody in Neural TTS
Figure 4 for Speech BERT Embedding For Improving Prosody in Neural TTS
Viaarxiv icon

Forward-Backward Decoding for Regularizing End-to-End TTS

Add code
Jul 18, 2019
Figure 1 for Forward-Backward Decoding for Regularizing End-to-End TTS
Figure 2 for Forward-Backward Decoding for Regularizing End-to-End TTS
Figure 3 for Forward-Backward Decoding for Regularizing End-to-End TTS
Figure 4 for Forward-Backward Decoding for Regularizing End-to-End TTS
Viaarxiv icon

A New GAN-based End-to-End TTS Training Algorithm

Add code
Apr 09, 2019
Figure 1 for A New GAN-based End-to-End TTS Training Algorithm
Figure 2 for A New GAN-based End-to-End TTS Training Algorithm
Figure 3 for A New GAN-based End-to-End TTS Training Algorithm
Figure 4 for A New GAN-based End-to-End TTS Training Algorithm
Viaarxiv icon

Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS

Add code
Apr 09, 2019
Figure 1 for Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS
Figure 2 for Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS
Figure 3 for Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS
Figure 4 for Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS
Viaarxiv icon