Henry Li Xinyuan 李欣远
I am currently a PhD student at Johns Hopkins University Center for Language and Speech Processing (CLSP). My advisor is Prof. Sanjeev Khudanpur.
I obtained my BA at the University of Oxford, majoring in Mathematics and Computer Science. I had previously been part of the Fast Kernels team at Nvidia. Prior to starting my PhD, I received my MSE at Johns Hopkins University advised by Prof. Hynek Hermansky.
My interest lies in the intersection of Natural Language Processing (NLP) and Automatic Speech Recognition (ASR): I believe there is untapped potential to be gained when speech and NLP are studied more closely together. A full list of my publications can be found on my google scholar profile.
Also check out my Github where there are other fun projects that are not included here.
What's new
-
Jun 3, 2026: Our paper, Universal Speech Content Factorization, has been accepted at Interspeech!
-
Aug 5, 2025: Three of our papers were accepted at IEEE ASRU: Scalable Controllable Accented TTS, GenVC: Self-Supervised Zero-Shot Voice Conversion, and Rapidly Adapting to New Voice Spoofing: Few-Shot Detection of Synthesized Speech Under Distribution Shifts!
-
Jan 9, 2025: Our submission to the Voice Privacy Attacker Challenge 2025 has been accepted to ICASSP 2025!
-
Sep 6, 2024: Our submission to the Voice Privacy Challenge 2024 won the Best Paper award at the 4th Symposium on Security and Privacy in Speech Communication (SPSC)!
-
Aug 30, 2024: Two of our papers were accepted at IEEE SLT 2024: Clean Label Attacks against SLU Systems, and Privacy versus Emotion Preservation Trade-offs in Emotion-Preserving Speaker Anonymization!