📝 Publications
# denotes co-first authors
🗣 Text-to-Speech
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks
Yu Zhang#, Ruiqi Li#, Changhao Pan#, et al.
Project | #1st of the Daily Paper
- SwanTale is a unified model for multi-speaker expressive speech and audio generation across instruct and zero-shot tasks.
SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue
Ruiqi Li#, Yu Zhang#, Changhao Pan#, et al.
Project | #3rd of the Daily Pape
- SwanVoice is a zero-shot TTS model for expressive long-form monologue and dialogue with one to four speakers.
Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios
Changhao Pan, Rui Yang, Han Wang, et al.
Project |
- SwanBench-Speech evaluates long-form speech generation across scenario coverage, automatic metrics, and model behavior analysis.
-
PreprintAudio Editing in the Era of Foundation Models: A Survey, Changhao Pan, Yifei Fan, Fan Zhuo, Yifu Chen, Wenxiang Guo, Yu Zhang, et al. | Project -
PreprintVoxAudio: Vocalized Audio Synthesis via Multi-Reward Autoregressive Flow Matching, Wenxiang Guo, Changhao Pan, Ziyue Jiang, Zhou Zhao, Fei Wu. | Project -
ACL 2026Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness, Jingyu Lu, Yuhan Wang, Fan Zhuo, Xize Cheng, Changhao Pan, et al. -
EMNLP 2026Speaking While Listening: A Survey and Empirical Audit of Full-Duplex Spoken Dialogue Systems, Jingyu Lu, Yuhan Wang, Jianming Luo, Yifu Chen, Tianle Liang, Shengpeng Ji, Ziyue Jiang, Xiaoda Yang, Yu Zhang, Changhao Pan et al. | Project
👂 Spatial Audio
MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations
Wenxiang Guo#, Changhao Pan#, Zhiyuan Zhu#, Xintong Hu#, et al.
- The largest recorded spatial audio dataset contains four scenarios: daily life, singing, music, and speech, with a total duration of 500 hours.
- Supports multiple spatial audio tasks: audio spatialization, spatial TTA, acoustic event localization and detection(SELD), etc.
Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer
Ke Lei#, Yu Zhang#, Changhao Pan#, et al.
Project |
- A causal autoregressive diffusion transformer architecture that enables streaming high-quality spatial audio generation.
-
ACM-MM-2025A Multimodal Evaluation Framework for Spatial Audio Playback Systems: From Localization to Listener Preference, Changhao Pan#, Wenxiang Guo#, Yu Zhang#, et al. | Project -
ACMMM-2025ISDrama: Immersive Spatial Drama Generation through Multimodal Prompting, Yu Zhang#, Wenxiang Guo#, Changhao Pan#, et al. |Project
-
EMNLP-2026One-Stage Multi-Task Instruction-Guided 3D Spatial Audio Editing, Ke Lei, Chenyuhao Wen, Yu Zhang, Wenxiang Guo, Changhao Pan, et al. -
EMNLP-2026CSAVocoder: A Causal Spatial Audio Vocoder Towards Real-Time Spatial Audio Generation, Zhiyuan Zhu, Han Wang, Wenxiang Guo, Yu Zhang, Changhao Pan, et al. -
AACL-IJCNLP-2025ASAudio: A Survey of Advanced Spatial Audio Research, Zhiyuan Zhu, Yu Zhang, Wenxiang Guo, Changhao Pan, Zhou Zhao. | -
PreprintSpatial-Omni: Spatial Audio Understanding Integration in Multimodal LLMs via FOA Encoding, Zhiyuan Zhu, Yixuan Chen, Yiwen Shao, Wenxiang Guo, Changhao Pan, Yu Zhang, et al. |
🎙 Singing Voice Synthesis
GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks
Yu Zhang, Changhao Pan#, Wenxiang Guo#, et al.
- GTSinger is a large Global, multi-Technique, free-to-use, high-quality singing corpus with realistic music scores, designed for all singing tasks.
- Our work is promoted by multiple media and forums, such as
,
, and
.
Versatile Framework for Song Generation with Prompt-based Control
Yu Zhang#, Wenxiang Guo#, Changhao Pan#, et al.
- VersBand is a multi-task song generation framework for synthesizing high-quality, aligned songs with prompt-based control.
-
AACL-IJCNLP-2025(Oral)Synthetic Singers: A Review of Deep-Learning-based Singing Voice Synthesis Approaches, Changhao Pan, Dongyu Yao, Yu Zhang, et al. | -
ACL 2025(Findings)STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation, Wenxiang Guo#, Yu Zhang#, Changhao Pan#, et al. | Project | -
ACL 2025(Findings)TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis, Yu Zhang#, Wenxiang Guo#, Changhao Pan#, et al. | Project | -
EMNLP-2024TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control, Yu Zhang, Ziyue Jiang, Ruiqi Li, Changhao Pan, Jinzheng He, Rongjie Huang, Chuxin Wang, Zhou Zhao. ｜ Project | -
AAAI-2025TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching, Wenxiang Guo, Yu Zhang, Changhao Pan, et. al. | Project |
📹 Audio-Visual Generation
-
Technical ReportALIVE: Animate Your World with Lifelike Audio-Video Generation, Ying Guo, Qijun Gan, Yifu Zhang, et al.
Contributor: Changhao Pan -
ICML-2026TMD-Bench: A Multi-Level Evaluation Paradigm for Music-Dance Co-Generation, Xiaoda yang#, Majun Zhang#, Changhao Pan, et al. -
ArxivImVideoEdit: Image-learning Video Editing via 2D Spatial Difference Attention Blocks, Jiayang Xu, Fan Zhuo, Majun Zhang, Changhao Pan, et al.
Others
IEEE-TVCGInteractive Table Synthesis with Natural Language, Yanwei Huang, Yunfan Zhou, Ran Chen, Changhao Pan, Xinhuan Shu, Di Weng, Yingcai Wu.