I am an engineer and researcher on speech technologies. Currently I am a postdoctoral researcher at Yamagishi lab @ National Institute of Informatics . My primary research focus revolves around multi-modal learning (speaker-oriented), spoofing detection, and speech synthesis.

I have obtained my BEng, MSc, and PhD degree in 2016, 2017, and 2023 respectively. My PhD dissertation has been jointly supervised by Md Sahidullah and Tomi Kinnunen . The PhD program is jointly funded by School of Computing @ Uni. of Eastern Finland and MULTISPEECH @ Inria Nancy Grand Est . From 2017 to 2019, I was an R&D engineer at Emotech , a London-based startup (although I was based at Edinburgh).

Some fun and undisturbing facts about me:

• I find solace and joy in training and participating in various ball sports. They are responsible to my procrastination.
• I am a huge fan of rap music for decades, without any genre preference. I almost never avoid controversial content in rap songs; it’s a reflection of embracing the diverse aspects of life. I used to chop, but no longer at that level anymore.
• I don’t like intentional traveling yet life has made me a bit of a nomad. I’ve been living (not short-term traveling) in 8 cities among 5 countries.
• I’ve transformed from a digital product hoarder into a practicing minimalist.

More detailed ver. of CV is available on request. Cheers to the journey ahead!

Email: xuecliu@nii.ac.jp

Recent News

• 2024-01-20: One paper has been accepted to IEEE/ACM TASLP . It is also available on Arxiv .
• 2023-10-18: I have defended my PhD dissertation. My opponent was Lauri Juvela . The press release is here .
• 2023-10-06: My doctoral dissertation is online .