My research aims to build and improve computer-based interactive systems. I am interested in speaker verification, speech recognition, speech synthesis and other speech/audio processing technologies.

I received my Ph.D. degree from Tsinghua University under the supervision of Prof. Jia Liu in 2020, with the dissertation titled Research on Speaker Embedding Extraction Methods based on Deep Learning. I was a visiting student in Cambridge University Engineering Department (CUED) in 2018. I received my M.E. degree from Tsinghua University in 2015 and my B.E. degree from Wuhan University in 2012.

I joined ByteDance AI Lab as an engineer in 2020. Now I am a Research Scientist at Moore Threads.

I am also a fan of embedded electronics and create some gadgets in my spare time.

Publications

Token-level speaker change detection using speaker difference and speech content via continuous integrate-and-fire Zhiyun Fan, Zhenlin Liang, Linhao Dong, Yi Liu, Shiyu Zhou, Meng Cai, Jun Zhang, Zejun Ma, Bo Xu Interspeech 2022

The volcspeech system for the icassp 2022 multi-channel multi-party meeting transcription challenge Chen Shen, Yi Liu, Wenzhi Fan, Bin Wang, Shixue Wen, Yao Tian, Jun Zhang, Jingsheng Yang, Zejun Ma ICASSP 2022

Introducing phonetic information to speaker embedding for speaker verification Yi Liu, Liang He, Jia Liu, Michael T. Johnson EURASIP Journal on Audio, Speech, and Music Processing. 2019

Large Margin Softmax Loss for Speaker Verification [code] Yi Liu, Liang He, Jia Liu Interspeech 2019

Exploring a Unified Attention-Based Pooling Framework for Speaker Verification Yi Liu, Liang He, Weiwei Liu, Jia Liu ISCSLP 2018

Speaker Embedding Extraction with Phonetic Information [code] Yi Liu, Liang He, Jia Liu, Michael T. Johnson INTERSPEECH 2018

Investigation of Frame Alignments for GMM-based Digit-prompted Speaker Verification Yi Liu, Liang He, Wei-Qiang Zhang, Jia Liu, Michael T. Johnson APSIPA ASC 2018

Comparison of Multiple Features and Modeling Methods for Text-dependent Speaker Verification Yi Liu, Liang He, Yao Tian, Zhuzi Chen, Jia Liu, Michael T. Johnson ASRU 2017

Investigating Various Diarization Algorithms for Speaker in the Wild (SITW) Speaker Recognition Challenge Yi Liu, Yao Tian, Liang He, Jia Liu INTERSPEECH 2016

Simultaneous Utilization of Spectral Magnitude and Phase Information to Extract Supervectors for Speaker Verification Anti-spoofing Yi Liu, Yao Tian, Liang He, Jia Liu, Michael T. Johnson INTERSPEECH 2015

Improved multitaper PNCC feature for robust speaker verification Yi Liu, Liang He, and Jia Liu ISCSLP 2014

Technical Blogs (in Chinese)

Contact