Picture for Deyi Tuo

Deyi Tuo

Improving Mandarin Prosodic Structure Prediction with Multi-level Contextual Information

Add code
Aug 31, 2023
Viaarxiv icon

Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic Information

Add code
Aug 31, 2023
Viaarxiv icon

CoverHunter: Cover Song Identification with Refined Attention and Alignments

Add code
Jun 15, 2023
Viaarxiv icon

FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement

Add code
Mar 26, 2022
Figure 1 for FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement
Figure 2 for FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement
Figure 3 for FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement
Figure 4 for FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement
Viaarxiv icon

Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion

Add code
Mar 24, 2022
Figure 1 for Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion
Figure 2 for Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion
Figure 3 for Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion
Figure 4 for Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion
Viaarxiv icon

Speaker Independent and Multilingual/Mixlingual Speech-Driven Talking Head Generation Using Phonetic Posteriorgrams

Add code
Jun 20, 2020
Figure 1 for Speaker Independent and Multilingual/Mixlingual Speech-Driven Talking Head Generation Using Phonetic Posteriorgrams
Figure 2 for Speaker Independent and Multilingual/Mixlingual Speech-Driven Talking Head Generation Using Phonetic Posteriorgrams
Figure 3 for Speaker Independent and Multilingual/Mixlingual Speech-Driven Talking Head Generation Using Phonetic Posteriorgrams
Figure 4 for Speaker Independent and Multilingual/Mixlingual Speech-Driven Talking Head Generation Using Phonetic Posteriorgrams
Viaarxiv icon

DurIAN: Duration Informed Attention Network For Multimodal Synthesis

Add code
Sep 05, 2019
Figure 1 for DurIAN: Duration Informed Attention Network For Multimodal Synthesis
Figure 2 for DurIAN: Duration Informed Attention Network For Multimodal Synthesis
Figure 3 for DurIAN: Duration Informed Attention Network For Multimodal Synthesis
Figure 4 for DurIAN: Duration Informed Attention Network For Multimodal Synthesis
Viaarxiv icon