Xuechen Liu
Assistant Professor at Xi'an Jiaotong-Liverpool University
Taicang, Jiangsu, China
Summary
👤
Senior🎓
Top SchoolXuechen Liu is an assistant professor and researcher with 10 years of experience specializing in speaker recognition, deepfake detection, multimodal processing, and generative modeling. He holds a PhD in Computer Science and has transitioned academic research across Inria, National Institute of Informatics, and now Xi'an Jiaotong-Liverpool University, blending rigorous theory with practical system development. His engineering contributions include extending the popular SpeechBrain PyTorch toolkit for speaker embedding extraction and inference on VoxCeleb, reflecting hands-on expertise with widely used open-source speech tools. Prior industry roles in ASR and SRE, plus internships in medical/audio signal processing, give him a strong applied background for deploying robust biometric and audio-analysis systems. Colleagues know him for bridging deep research with reproducible code and for bringing novel robustness insights from his PhD into real-world detection and recognition pipelines.
10 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Eastern FinlandMaster of Science (MSc), Artificial Intelligence, Master of Science (MSc), Artificial Intelligence at The University of EdinburghBachelor of Engineering (BEng), Computer Science and Electronic Engineering, Bachelor of Engineering (BEng), Computer Science and Electronic Engineering at University of LiverpoolBachelor of Engineering (BEng), Computer Science and Technology, Bachelor of Engineering (BEng), Computer Science and Technology at Xi'an Jiaotong-Liverpool University
English, Chinese, Japanese
Github Skills (6)
pytorch10
speech-processing10
python10
speaker-recognition10
speaker-verification9
kaldi9
Programming languages (9)
Github contributions (5)
speechbrain/speechbrain
Nov 2021 - Nov 2022
A PyTorch-based Speech Toolkit
Role in this project:
ML Engineer
ML EngineerContributions:24 commits, 5 PRs, 22 comments in 1 year
Contributions summary:Xuechen primarily contributed to speaker embedding extraction and related tasks within the speechbrain/speechbrain repository. The commits focus on creating inference scripts and adapting existing code for speaker-related functionalities, specifically within the context of the VoxCeleb dataset. This includes tasks like computing embeddings, storing them in specific formats, and implementing options such as trimming and chunking. These changes indicate a focus on utilizing and extending existing speaker recognition capabilities within the toolkit.
voice-recognitionasrspeech-recognitionspeech-separationspeaker-verification
searcher1994/kaldi-emotech
Sep 2017 - Nov 2017
Contributions:328 pushes, 2 branches in 2 months
kaldilocation
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.