Scholar
Yuma Koizumi
Google Scholar ID: uSV_Dd4AAAAJ
Google DeepMind
Speech and Acoustic Signal Processing
Machine Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
6,097
H-index
31
i10-index
46
Publications
20
Co-authors
0
Contact
No contact links provided.
Publications
2 items
ReverbMiipher: Generative Speech Restoration meets Reverberation Characteristics Controllability
2025
Cited
0
Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration
2025
Cited
0
Resume (English only)
Academic Achievements
- Dec. 2023: Best Reviewer Award, ASRU 2023, IEEE
- Aug. 2023: Outstanding Reviewer Award, INTERSPEECH 2023, ISCA
- Mar. 2022: ASJ Activity Contribution Award, The Acoustical Society of Japan
- Nov. 2021: MIT Tech Review, Innovators Under 35 Japan
- Oct. 2021: Best Speech Enhancement Paper award, IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2021
- Jan. 2021: IEEE Signal Processing Society (SPS) Japan Young Author Best Paper Award
- Nov. 2020: DCASE 2020 Challenge Judges’ award
- Jul. 2020: 1st place in DCASE 2020 Challenge Task 6 'Automated audio captioning'
- Mar. 2020: The Telecom System Technology Award, The Telecommunication Advancement Foundation (TAF)
- Mar. 2019: Itakura Prize Innovative Young Researcher Award, The Acoustical Society of Japan
- Sep. 2017: The Awaya Prize Young Researcher Award, The Acoustical Society of Japan
- Mar. 2015: IPSJ Yamashita SIG Research Award, Information Processing Society of Japan
- Sep. 2013: FUNAI Best Paper Award, Information Processing Society of Japan
- Sep. 2012: The 6th Student Presentation Award, The Acoustical Society of Japan
- Feb. 2012: MEXT Science Inter College Award, MEXT of Japan (MEXT: Ministry of Education, Culture, Sports, Science and Technology)
Research Experience
- Nov. 2024 - Current: Staff Research Scientist at Google DeepMind
- Nov. 2022 - 2024: Senior Research Scientist at Google
- Nov. 2020 - Oct. 2022: Research Scientist at Google
- Apr. 2014 - Nov. 2020: Research Scientist at NTT Media Intelligence Laboratories
- Sep. 2015 - Mar. 2016: Part-Time Lecturer of Digital Data Processing, Faculty of Computer and Information Sciences, Hosei University, Japan
Education
- Sep. 2017: Ph.D. degree in Engineering, The University of Electro-Communications, Japan
- Mar. 2014: M.S. degree, Hosei University, Japan
- Mar. 2012: B.S. degree, Hosei University, Japan
Background
- Research Interests: Speech Enhancement, Separation, and Restoration; Speech Synthesis; Anomaly Detection in Sounds; Machine Learning
- Professional Field: Ph.D. in Engineering
- Brief Introduction: Currently a Research Scientist at Google DeepMind.
Miscellany
- Senior Member of IEEE
- Member of the Acoustical Society of Japan (ASJ)
- Since 2021: A Councilor of the Acoustical Society of Japan
- Organizer for several DCASE challenge tasks
- 2019-2022: Representative of Students and Young Researchers Forum of The ASJ, Japan
- 2017-2023: Member of Students and Young Researchers Forum of The ASJ, Japan
Co-authors
0 total
Co-authors: 0 (list not available)
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up