Hiroshi Saruwatari
Nara Institute of Science and Technology, The University of Tokyo, Bunkyo University
Papers
22
Total Citations
232
H-Index
9
About
Hiroshi Saruwatari is a leading figure in robot audition, pioneering technologies that allow robots to hear, understand, and converse in real-world environments. His core research spans blind source separation, speech enhancement, and hands-free spoken dialogue systems. A standout contribution is the development of a two-stage blind source separation framework that combines independent component analysis with binary masking, enabling humanoid robots to isolate a speaker’s voice from background noise and reverberation—a critical step toward practical robot audition. His work on the ASKA receptionist robot demonstrated the integration of speech recognition, gesture, and dialogue into a functional human-robot interface. Saruwatari has also advanced noise suppression for rescue robots and improved voice activity detection for hands-free interaction. With multiple papers exceeding 30 citations and a sustained record of innovation in real-time, low-latency speech processing, his research has laid the groundwork for robots that can operate in noisy, dynamic settings. His contributions are essential reading for anyone working at the intersection of signal processing, robotics, and human-computer interaction.
Research Focus
Key Achievements
Top Papers
- 1ASKA: receptionist robot with speech dialogue system35 citations · 2003
- 2Robots that can hear, understand and talk35 citations · 2004
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10