About me

Liumeng Xue is a Postdoctoral Researcher at The Chinese University of Hong Kong, Shenzhen, working with Prof. Haizhou Li and Prof. Zhizheng Wu. She received her Ph.D. degree from the Audio, Speech and Language Processing Laboratory at Northwestern Polytechnical University (ASLP@NWPU), Xian, China, supervised by Prof. Lei Xie. During her studies, she performed research at JD AI Lab (2018-2019), Tencent AI Lab (2021-2022) and Microsoft (2019-2020, 2021-2022). Her research interests include audio, music, and speech generation.

News

• We released Amphion, a toolkit for Audio, Music, and Speech Generation. The technical report is available Amphion: An Open-Source Audio, Music and Speech Generation Toolkit. The Hugging Face of Amphion is here.
• Multi-Scale Sub-Band Constant-Q Transform Discriminator for High-Fidelity Vocoder accepted by ICASSP2024, also integrated in Amphion
• SponTTS: modeling and transferring spontaneous style for TTS accepted by ICASSP2024.
• Leveraging Content-based Features from Multiple Acoustic Models for Singing Voice Conversion accepted by ML4Audio @ NeurIPS 2023.
• HiGNN-TTS: Hierarchical Prosody Modeling with Graph Neural Networks for Expressive Long-form TTS accepted by ASRU2023.

Research Experience

• 2021.11 - 2022.10, Research Intern, Microsoft, China.
• 2021.06 - 2021.11, Research Intern, Tencent AI Lab, China.
• 2019.04 - 2020.06, Research Intern, Microsoft, China.
• 2018.10 - 2019.04, Research Intern, JD.COM AI Lab, China.

Publications

Text to Speech (TTS)

• SponTTS: modeling and transferring spontaneous style for TTS, Hanzhao Li, Xinfa Zhu, Liumeng Xue, Yang Song, Yunlin Chen, Lei Xie, ICASSP, 2024.

• HiGNN-TTS: Hierarchical Prosody Modeling with Graph Neural Networks for Expressive Long-form TTS, Dake Guo, Xinfa Zhu, Liumeng Xue, Tao Li, Yuanjun Lv, Yuepeng Jiang, Lei Xie, ASRU, 2023.

• ParaTTS: Learning Linguistic and Prosodic Cross-sentence Information in Paragraph-based TTS, Liumeng Xue, Frank K. Soong, Shaofei Zhang, Lei Xie. TASLP, 2022

• Cycle consistent network for end-to-end style transfer TTS training Liumeng Xue, Shifeng Pan, Lei He, Lei Xie, Frank K Soong. Neural Networks 2021

• Controllable emotion transfer for end-to-end speech synthesis Tao Li, Shan Yang, Liumeng Xue, Lei Xie. ISCSLP 2021

• On the localness modeling for the self-attention based end-to-end speech synthesis Shan Yang, Heng Lu, Shiyin Kang, Liumeng Xue, Jinba Xiao, Dan Su, Lei Xie, Dong Yu. Neural networks 2020

• Building a mixed-lingual neural TTS system with only monolingual data Liumeng Xue, Wei Song, Guanghui Xu, Lei Xie, Zhizheng Wu. INTERSPEECH 2013

Voice Conversion (VC)

• Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features, Ziqian Ning, Qicong Xie, Pengcheng Zhu, Zhichao Wang, Liumeng Xue, Jixun Yao, Lei Xie, Mengxiao Bi. ICASSP, 2023.

• Learning Noise-independent Speech Representation for High-quality Voice Conversion for Noisy Target Speakers, Liumeng Xue, Shan Yang, Na Hu, Dan Su, Lei Xie. INTERSPEECH, 2022

Sining Voice Conversion (SVC)

• Leveraging Content-based Features from Multiple Acoustic Models for Singing Voice Conversion, Xueyao Zhang, Yicheng Gu, Haopeng Chen, Zihao Fang, Lexiao Zou, Liumeng Xue, Zhizheng Wu, 2023.

Vocoder

• Multi-Scale Sub-Band Constant-Q Transform Discriminator for High-Fidelity Vocoder, Yicheng Gu, Xueyao Zhang, Liumeng Xue, Zhizheng Wu, ICASSP, 2024.

Deepfake Detection

• An Initial Investigation of Neural Replay Simulator for Over-the-Air Adversarial Perturbations to Automatic Speaker Verification, Jiaqi Li, Li Wang, Liumeng Xue, Lei Wang, Zhizheng Wu, 2023.

Reviewer

• Reviewer of TASLP, ICASSP, INTERSPEECH, ASRU, ICMC, etc.