- 2022 1st place in NTCIR-16 Real-MedNLP subtask2 (Few-resource Named Entity Recognition)
- 2022 1st place in NTCIR-16 Real-MedNLP subtask1 on radiology report dataset (Few-resource Named Entity Recognition)
- Open Source Software: houou, a large language model trained by Japanese instruction data from scratch (joint research with Riken)
- Beamforming-for-speech-enhancement: A software project on GitHub that has received over 260 stars, used by Alibaba research and referenced in academic publications
Research Experience
- SB Intuitions, Nov 2024-present: Researcher - Development of LLM-based multimodal speech models
- Money Forward Lab, May 2023-Oct 2024: Senior researcher - Integration of large language models into commercial products and release of an open-source large language model
- lilo company, Sep 2023-Dec 2023: Software engineer (side job) - Development of text-to-speech models for YouTube character voice
- rinna Co., Ltd., Apr 2022-May 2023: Data scientist - Analysis and evaluation of large language models for conversation tasks and their improvement
- Advanced Media, Inc., Apr 2017-Apr 2022: Software engineer - Research and development in automatic speech recognition, leading a natural language processing research team for named entity recognition competitions
- NTT Media Intelligence laboratory, Oct 2015: Intern student - Natural language processing research
- Panasonic Corporation, Sep 2013: Intern student
Education
Hosei University, Japan
- April 2015-March 2017: MS in Computer Science
- April 2011-March 2015: BS in Computer Science
Background
Research Interests: automatic speech recognition, natural language processing, large language model, speech enhancement, machine learning, deep learning, acoustic signal processing.
Miscellany
Other Interests and Information:
- Google Scholar: https://scholar.google.co.jp/citations?user=y__gbBkAAAAJ&hl=ja