Naoyuki Kanda

About

I am a researcher in the field of spoken language technology. I received the B.S. in Engineering, M.S. in Informatics, and Ph.D. in Informatics from Kyoto University, Kyoto, Japan, in 2004, 2006, and 2014, respectively.

I have been working on a wide range of spoken language technologies, including automatic speech recognition, speaker diarization, speech separation, speech translation, speech and audio generation, spoken dialog systems, and spoken document retrieval systems. My recent research focuses on the distant conversational speech recognition, whose outcome includes the 1st prize at the IWSLT English speech recognition evaluation campaign in 2014, the 2nd prize at the CHiME-5 speech recognition competition in 2018, the 1st prize at the speaker diarization track of the VoxCeleb Speaker Recognition Challenge in 2020, and the IEEE SPS Conference best paper award for industry from the IEEE ICASSP in 2022.

Prior to joining Microsoft in 2019, I was a Senior Researcher at Hitachi Ltd., Tokyo, Japan, where I served from 2006 to 2019. I also conducted research at the National Institute of Information and Communications Technology (NICT), Kyoto, Japan, as a Research Expert (2014-2016) and Cooperative Visiting Researcher (2016-2017). I am a member of the Institute of Electrical and Electronics Engineers (IEEE), the Acoustical Society of Japan (ASJ), the Japanese Society for Artificial Intelligence (JSAI), and the Information Processing Society of Japan (IPSJ).