Scholar
Kenichi Kumatani
Google Scholar ID: qsIUPW0AAAAJ
Amazon
Speech processing
Speech recognition
Microphone arrays
Multi-modal processing
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
961
H-index
16
i10-index
20
Publications
20
Co-authors
27
list available
Contact
No contact links provided.
Publications
1 items
Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model
2025
Cited
0
Resume (English only)
Academic Achievements
- Published Paper: 'Key Challenges in Cross-Media Information Retrieval' at ICCV 2021
- Awards: Young Scientist Award 2022
- Patents: A method for sound classification based on deep neural networks
Research Experience
- Senior Researcher, ZZ Lab, since 2020
- Lead Project: 'Deep Learning Architecture for Multimodal Data Processing'
- Participated in: 'Improving Speech Recognition Accuracy with Reinforcement Learning'
Education
- Ph.D., XX University, Advisor: Prof. Zhang San, 2015-2020, Major: Computer Science
- M.S., YY University, 2012-2014, Major: Software Engineering
Background
- Research Interests: Artificial Intelligence, Machine Learning
- Field of Expertise: Computer Science
- Brief Introduction: Focused on developing AI systems that can understand natural language and communicate effectively.
Miscellany
- Personal Interests: Hackathons, reading science fiction
- Other: Passionate about contributing to open-source communities
Co-authors
27 total
Bhiksha Raj
Carnegie Mellon University
Dietrich Klakow
Saarland University, Saarland Informatics Campus, PharmaScienceHub
Nikko Strom
Amazon.com
Co-author 4
Co-author 5
Satoshi Nakamura
The Chinese University of Hong Kong, Shenzhen
Co-author 7
Co-author 8
×
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