Jinyu Li

关于

Jinyu Li received his Ph.D. degree in electrical and computer engineering from Georgia Institute of Technology, Atlanta, GA, USA in 2008. He joined Microsoft, Redmond, WA, USA in 2008 and now serves as Partner Applied Science Manager, leading a science team advancing speech, translation, and language technologies.  His diverse research areas include speech-LLM, end-to-end modeling for speech recognition and speech translation, deep learning, acoustic modeling, and noise robustness.

Dr. Li is an IEEE Fellow, for contributions to deep-learning-based speech technology innovation and commercialization. He is also an AAIA Fellow. He has been a member of IEEE Speech and Language Processing Technical Committee from 2017 to 2023 and as Vice Chair starting in 2026. He served as the associate editor of IEEE/ACM Transactions on Audio, Speech and Language Processing from 2015 to 2020. He is named as Distinguished Industry Speakers for IEEE Signal Processing Society and received IEEE SPS Best Paper Award in 2025. He was also awarded as the Industrial Distinguished Leader at Asia-Pacific Signal and Information Processing Association (APSIPA) in 2021 and APSIPA Sadaoki Furui Prize Paper Award in 2023.

Latest CV is available here (opens in new tab).

Latest publication is available from my Google scholar page (opens in new tab).

What’s New

• Jun. 2026: Our Azure-Speech-05-2026 model achieved the #1 position on both the main OpenASR (opens in new tab) leaderboard and the multilingual leaderboard.
• Jan. 2026: Elected as the vice chair of IEEE Speech and Language Technical Committee (opens in new tab).
• Dec. 2025: wavLM (opens in new tab) paper received best paper award from IEEE SPS.
• Mar. 2025:  We released Phi-4-multimodal, an advanced model capable of processing inputs from speech, vision, and text.  It provides exceptional performance for speech recognition, speech translation, speech QA, speech summarization, and audio understanding. Technical report (opens in new tab).
• Mar. 2025: AAIA (opens in new tab) Fellow.
• Jan. 2025: IEEE Fellow (opens in new tab), for contributions to deep-learning-based speech technology innovation and commercialization.
• Jan. 2025: Distinguished Industry Speakers (opens in new tab) for IEEE Signal Processing Society. Look forward to working with IEEE SPS chapters to present the speech and multimodal topics in 2025 and 2026.
• May. 2024: IEEE SPS webinar “End-to-End Automatic Speech Recognition”, Slides, Video.  (opens in new tab)
• Nov. 2023: It is my great honor to receive the APSIPA Sadaoki Furui Prize Paper Award for the paper “Recent Advances in End-to-End Automatic Speech Recognition (opens in new tab)” published in APSIPA Transactions on Signal and Information Processing, 2022. Here is the invited talk at APSIPA ASC 2023 for receiving the Award.
• Dec. 2022: It was my pleasure to give a keynote talk, “Advancing end-to-end automatic speech recognition and beyond”,  at International Symposium on Chinese Spoken Language Processing (ISCSLP). Slides, Video (opens in new tab).
• Apr. 2022: The survey paper “Recent Advances in End-to-End Automatic Speech Recognition (opens in new tab)” is published in APSIPA Transactions on Signal and Information Processing.