Picture for Xinsheng Wang

Xinsheng Wang

Delivering Speaking Style in Low-resource Voice Conversion with Multi-factor Constraints

Nov 16, 2022
Zhichao Wang, Xinsheng Wang, Lei Xie, Yuanzhe Chen, Qiao Tian, Yuping Wang

Figure 1 for Delivering Speaking Style in Low-resource Voice Conversion with Multi-factor Constraints

Figure 2 for Delivering Speaking Style in Low-resource Voice Conversion with Multi-factor Constraints

Figure 3 for Delivering Speaking Style in Low-resource Voice Conversion with Multi-factor Constraints

Figure 4 for Delivering Speaking Style in Low-resource Voice Conversion with Multi-factor Constraints

* Submitted to ICASSP 2023

Access Paper or Ask Questions

Robust MelGAN: A robust universal neural vocoder for high-fidelity TTS

Nov 02, 2022
Kun Song, Jian Cong, Xinsheng Wang, Yongmao Zhang, Lei Xie, Ning Jiang, Haiying Wu

Figure 1 for Robust MelGAN: A robust universal neural vocoder for high-fidelity TTS

Figure 2 for Robust MelGAN: A robust universal neural vocoder for high-fidelity TTS

Figure 3 for Robust MelGAN: A robust universal neural vocoder for high-fidelity TTS

Figure 4 for Robust MelGAN: A robust universal neural vocoder for high-fidelity TTS

* Accepted by ISCSLP 2022

Access Paper or Ask Questions

Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher

Mar 30, 2022
Heyang Xue, Xinsheng Wang, Yongmao Zhang, Lei Xie, Pengcheng Zhu, Mengxiao Bi

Figure 1 for Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher

Figure 2 for Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher

Figure 3 for Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher

Figure 4 for Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher

* Submitted to INTERSPEECH 2022

Access Paper or Ask Questions

Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

Jan 20, 2022
Yu Wang, Xinsheng Wang, Pengcheng Zhu, Jie Wu, Hanzhao Li, Heyang Xue, Yongmao Zhang, Lei Xie, Mengxiao Bi

Figure 1 for Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

Figure 2 for Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

Figure 3 for Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

Figure 4 for Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

* will be submitted to Interspeech 2022

Access Paper or Ask Questions

Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios

Dec 23, 2021
Qicong Xie, Tao Li, Xinsheng Wang, Zhichao Wang, Lei Xie, Guoqiao Yu, Guanglu Wan

Figure 1 for Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios

Figure 2 for Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios

Figure 3 for Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios

Figure 4 for Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios

* submitted to icassp2022

Access Paper or Ask Questions