Alert button
Picture for Xinyu Duan

Xinyu Duan

Alert button

StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis

Jan 02, 2024
Yu Zhang, Rongjie Huang, Ruiqi Li, JinZheng He, Yan Xia, Feiyang Chen, Xinyu Duan, Baoxing Huai, Zhou Zhao

Viaarxiv icon

TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation

Dec 23, 2023
Xize Cheng, Rongjie Huang, Linjun Li, Tao Jin, Zehan Wang, Aoxiong Yin, Minglei Li, Xinyu Duan, changpeng yang, Zhou Zhao

Viaarxiv icon

StyleSinger: Style Transfer for Out-Of-Domain Singing Voice Synthesis

Dec 17, 2023
Yu Zhang, Rongjie Huang, Ruiqi Li, JinZheng He, Yan Xia, Feiyang Chen, Xinyu Duan, Baoxing Huai, Zhou Zhao

Viaarxiv icon

How Well Do Large Language Models Understand Syntax? An Evaluation by Asking Natural Language Questions

Nov 14, 2023
Houquan Zhou, Yang Hou, Zhenghua Li, Xuebin Wang, Zhefeng Wang, Xinyu Duan, Min Zhang

Viaarxiv icon

Is It Really Useful to Jointly Parse Constituency and Dependency Trees? A Revisit

Sep 21, 2023
Yanggang Gu, Yang Hou, Zhefeng Wang, Xinyu Duan, Zhenghua Li

Viaarxiv icon

TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models

Aug 28, 2023
Shengpeng Ji, Jialong Zuo, Minghui Fang, Ziyue Jiang, Feiyang Chen, Xinyu Duan, Baoxing Huai, Zhou Zhao

Figure 1 for TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models
Figure 2 for TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models
Figure 3 for TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models
Figure 4 for TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models
Viaarxiv icon

AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing

Jun 11, 2023
Asaad Alghamdi, Xinyu Duan, Wei Jiang, Zhenhai Wang, Yimeng Wu, Qingrong Xia, Zhefeng Wang, Yi Zheng, Mehdi Rezagholizadeh, Baoxing Huai, Peilun Cheng, Abbas Ghaddar

Figure 1 for AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing
Figure 2 for AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing
Figure 3 for AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing
Figure 4 for AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing
Viaarxiv icon

OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment

Jun 10, 2023
Xize Cheng, Tao Jin, Linjun Li, Wang Lin, Xinyu Duan, Zhou Zhao

Figure 1 for OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment
Figure 2 for OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment
Figure 3 for OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment
Figure 4 for OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment
Viaarxiv icon

VLAD-VSA: Cross-Domain Face Presentation Attack Detection with Vocabulary Separation and Adaptation

Feb 21, 2022
Jiong Wang, Zhou Zhao, Weike Jin, Xinyu Duan, Zhen Lei, Baoxing Huai, Yiling Wu, Xiaofei He

Figure 1 for VLAD-VSA: Cross-Domain Face Presentation Attack Detection with Vocabulary Separation and Adaptation
Figure 2 for VLAD-VSA: Cross-Domain Face Presentation Attack Detection with Vocabulary Separation and Adaptation
Figure 3 for VLAD-VSA: Cross-Domain Face Presentation Attack Detection with Vocabulary Separation and Adaptation
Figure 4 for VLAD-VSA: Cross-Domain Face Presentation Attack Detection with Vocabulary Separation and Adaptation
Viaarxiv icon