Shota Horiguchi
horiguchi [at] ieee.org
I am a Research Specialist at NTT Human Informatics Laboratories. My research interests are not limited to speech-related technology such as speech recognition, speech separation, and speaker diarization, but also include image processing and multimodal processing.
Prior to joining NTT, I was a Senior Researcher at Hitachi, Ltd. Research and Development Group from 2017 to 2024.
I received my Ph.D. degree in 2023 from University of Tsukuba under the supervision of Prof. Takeshi Yamada. At University of Tsukuba, I was a member of the Multimedia Laboratory.
Before that, I studied computer vision at the Aizawa-Yamasaki Laboratory (now Aizawa-Yamakata-Matsui Laboratory) of the University of Tokyo, where I received B.E. and M.E. degrees under the supervision of Prof. Kiyoharu Aizawa.
news
Feb 1, 2024 | I’m starting a new position as Research Specialist at NTT Human Informatics Laboratories. |
---|---|
Dec 14, 2023 | Our paper “Streaming Active Learning for Regression Problems Using Regression via Classification” has been accepted to ICASSP 2024. |
Sep 14, 2023 | My PhD thesis is now open. |
Sep 6, 2023 | Released a preprint regarding streaming active learning for regression problem. |
Aug 25, 2023 | A co-authored paper has been accepted to APSIPA ASC 2023. |