Changhao Pan

Changhao Pan

Zhejiang University

I am a master student at College of Computer Science and Technology, Zhejiang University, majoring in Computer Science.

Currently I work on the Audio Research Team at Zhejiang University, under the supervision of Prof. Zhou Zhao. Previously I graduated from Turing Class, a program established by Chu Kochen Honors College, with a bachelor’s degree in Artificial Intelligence.

My research interests primarily focus on Multi-Modal Generative AI, specifically in Speech, Spatial Audio, and Singing. I have published papers at top international AI conference, including NeurIPS, ACL, ACM-MM and EMNLP. Currently, I am working on Spatial Audio Generation and Immersive Audio Synthesis.

I am actively looking for academic collaboration, feel free to contact me via email at panch@zju.edu.cn.

🔥 News

  • 2026.08 🎉 3 Papers are accepted by EMNLP 2026!
  • 2026.08 🚀 We release SwanTale, Hugging Face’s #1 Paper of the Day!
  • 2026.06 🚀 We release SwanVoice, Hugging Face’s #3 Paper of the Day!
  • 2026.05 🎉 2 Papers are accepted by ICML 2026!
  • 2026.04 🎉 Swanbench-Speech is accepted by ACL!
  • 2025.09 🎉 MRSAudio is accepted by NeurIPS 2025!
  • 2024.10 🎉 I am awarded Chu Kochen Scholarship!
  • 2024.09 🎉 GTSinger is accepted by NeurIPS 2024(spotlight) and 1 paper is accepted by EMNLP 2024!

📝 Publications

# denotes co-first authors

🗣 Text-to-Speech

Technique Report
SwanTale

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.
Technique Report
SwanVoice

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.
ACL 2026
SwanBench-Speech

Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios
Changhao Pan, Rui Yang, Han Wang, et al.

Project | GitHub

  • SwanBench-Speech evaluates long-form speech generation across scenario coverage, automatic metrics, and model behavior analysis.

👂 Spatial Audio

NeurIPS 2025
sym

MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations
Wenxiang Guo#, Changhao Pan#, Zhiyuan Zhu#, Xintong Hu#, et al.

Hugging Face Demo

  • 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.
ICML 2026
SwanSphere

Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer
Ke Lei#, Yu Zhang#, Changhao Pan#, et al.

Project | GitHub

  • A causal autoregressive diffusion transformer architecture that enables streaming high-quality spatial audio generation.

🎙 Singing Voice Synthesis

NeurIPS 2024(Spotlight)
sym

GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks
Yu Zhang, Changhao Pan#, Wenxiang Guo#, et al.

Hugging Face Demo

  • 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 weixin, weixin, and zhihu.
EMNLP 2025
sym

Versatile Framework for Song Generation with Prompt-based Control
Yu Zhang#, Wenxiang Guo#, Changhao Pan#, et al.

| Project

  • VersBand is a multi-task song generation framework for synthesizing high-quality, aligned songs with prompt-based control.

📹 Audio-Visual Generation

Others

🎖 Honors and Awards

  • Chu Kochen Scholarship(as undergraduate), 2024
    • Highest scholarship at Zhejiang University
  • Chinese National Scholarship, 2022, 2023, 2024
    • Awarded by Ministry of Education of China; Top 1%; 3 consecutive times
  • CCF Outstanding Undergraduate Students, 2024
    • Awarded to 100 undergraduates in the field of Computer Scicence
  • Top-10 Outstanding Undergraduate Students of the College of Computer Science and Technology, 2024
  • Top-10 Outstanding Students of the Chu Kozhen Honors College, 2023
  • BaoGang Elite Scholarship, 2023

📖 Educations

  • 2025.09 - 2028.06(Expected), Master, College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang
    • Major: Computer Science
  • 2021.09 - 2025.06, Undergraduate, Chu Kochen Honors College & College of Computer Science and Technology, Zhejiang Univeristy, Hangzhou, Zhejiang
    • Major: Artificial Intelligence (Turing Honor Program)
    • GPA: 4.85/5.0, 94.04/100, Rank: 1/79
  • 2018.09 - 2021.06, Yuying Experimental School, Wenzhou, Zhejiang

💻 Research & Internships

📚 Academic Service

  • Conference Reviewer: NeurIPS 2025 & 2026, ACL 2025 & 2026, AAAI 2026, ACM-MM 2026