Biography
I received my Ph.D. in Informatics from National Institute of Informatics (NII) and SOKENDAI. After graduation, I joined Li Auto as a multimodal generative AI researcher, and I am now a Speech AI Researcher at Shanda AI Research Tokyo. My research focuses on speech and audio foundation models, speaker recognition and antispoofing, and generative audio AI including speech and singing voice synthesis.
Download my resumé .
Interests
- Artificial Intelligence
- Speech Signal Processing
- Singing Voice / Speech Synthesis
- Speech Recognition
- Language Processing
Education
PhD in Informatics, 2024
National Institute of Informatics & SOKENDAI
MEng in Electrical Engineer and Information Systems (EEIS), 2020
The University of Tokyo
BSc in Measurement and Control Technology and Instruments, 2016
Tianjin University
News
- 2026.01: Released A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation on arXiv.
- 2026.01: DrivingScene and PAGS accepted by ICASSP 2026.
- 2025.12: Released Towards Interactive Intelligence for Digital Humans on arXiv.
- 2025.10: Critical Information Only accepted by IEEE TDSC.
- 2025.01: SonicSim accepted by ICLR 2025.
- 2025.01: A Benchmark for Multi-Speaker Anonymization accepted by IEEE TIFS.
- 2024.12: InstructSing accepted by SLT 2024.
- 2024.12: Spoofing-Aware Speaker Verification Robust Against Domain and Channel Mismatches accepted by SLT 2024.
- 2024.03: Released HAM-TTS on arXiv.
Publications
Quickly discover relevant content by filtering publications.
(2026).
A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation.
In arXiv.
(2026).
DrivingScene: A Multi-Task Online Feed-Forward 3D Gaussian Splatting Method for Dynamic Driving Scenes.
Accepted by ICASSP 2026.
(2026).
PAGS: Priority-Adaptive Gaussian Splatting for Dynamic Driving Scenes.
Accepted by ICASSP 2026.
(2025).
Towards Interactive Intelligence for Digital Humans.
In arXiv.
(2025).
Critical Information Only: A Content Privacy-Preserving Framework for Detecting Audio Deepfakes.
In IEEE TDSC.
(2025).
SonicSim: A Customizable Simulation Platform for Speech Processing in Moving Sound Source Scenarios.
Accepted by ICLR 2025.
(2025).
A Benchmark for Multi-Speaker Anonymization.
In IEEE TIFS.
(2024).
InstructSing: High-Fidelity Singing Voice Generation via Instructing Yourself.
In SLT 2024.
(2024).
Spoofing-Aware Speaker Verification Robust Against Domain and Channel Mismatches.
In SLT 2024.
(2024).
HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling.
In ArXiv.
(2024).
Joint Speaker Encoder and Neural Back-end Model for Fully End-to-End Automatic Speaker Verification with Multiple Enrollment Utterances.
In Computer Speech & Language.
(2023).
CrossSinger: A Cross-Lingual Multi-Singer High-Fidelity Singing Voice Synthesizer Trained on Monolingual Singers.
In ASRU 2023.
(2023).
HiFi-WaveGAN: Generative Adversarial Network with Auxiliary Spectrogram-Phase Loss for High-Fidelity Singing Voice Generation.
In ISNN 2024.
(2023).
Improving Generalization Ability of Countermeasures for New Mismatch Scenario by Combining Multiple Advanced Regularization Terms.
In Interspeech 2023.
(2023).
Xiaoicesing 2: A High-Fidelity Singing Voice Synthesizer Based on Generative Adversarial Network.
In Interspeech 2023.
(2023).
Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition.
In ISNN 2024.
(2023).
Cross-Modal Audio-Visual Co-Learning for Text-Independent Speaker Verification.
In ICASSP 2023.
(2023).
SSI-Net: A Multi-Stage Speech Signal Improvement System for ICASSP 2023 SSI Challenge.
In ICASSP 2023.
(2022).
Deep Spectro-temporal Artifacts for Detecting Synthesized Speech.
In DDAM 2022 Workshop.
(2022).
Data Augmentation Using McAdams-Coefficient-Based Speaker Anonymization for Fake Audio Detection.
In Interspeech 2022.
(2022).
Spoofing-Aware Attention based ASV Back-end with Multiple Enrollment Utterances and a Sampling Strategy for the SASV Challenge 2022.
In Interspeech 2022.
(2022).
Attention Back-end for Automatic Speaker Verification with Multiple Enrollment Utterances.
In ICASSP 2022.
Skills
Python
100%
C++
80%
Audio Signal Processing
100%
Audio Generative AI
90%
Speech Recognition
90%
PyTorch
100%
Activities
Reviewer Service
- Conference:
- NeurIPS, ICLR, ICML, ACL
- INTERSPEECH, ICASSP, ASRU, SLT
- Journal:
- IEEE/ACM TASLP, IEEE OJSP
Experience
Speech AI Researcher
Shanda AI Research Tokyo
Responsibilities include:
- Speech synthesis
- Speech understanding
- Full-duplex spoken dialogue
Multimodal Generative AI Researcher
Responsibilities include:
- Foundation model algorithm research for text and speech generation
- Singing voice generation and controllable singing synthesis
- Sound/audio generation and understanding
- Cross-modal alignment and instruction tuning for text, speech, and audio
Speech ML Researcher (Intern)
Responsibilities include:
- Speech signal processing
- Speech recognition
- Speech synthesis
- Generative AI
Avatar Researcher (Joint Project)
Responsibilities include:
- Speech signal processing
- Singing voice synthesis
- Speech synthesis
Research Assistant
Responsibilities include:
- Speech signal processing
- Speaker recognition
- Antispoofing
Speech Recognition Researcher
Responsibilities include:
- Speech signal processing
- Speaker recognition
- Speech recognition
- Self-supervised learning
- Spoken term detection
Speech Recognition Researcher (Intern)
Responsibilities include:
- Speech signal processing
- Speaker recognition