The Graduate School of Information Science and Technology
Job title
Professor
Degree
Ph.D.(Nagoya Univ.)
Research funding number
30324974
Profile
RESEARCH TOPICS: Statistical signal processing, Speech and Acousitic signal processing, Machine learning
SHORT BIO
Hiroshi Saruwatari received Ph.D. degrees from Nagoya University, Japan, in 2000, where he consistently engaged in researches on multichannel signal processing with Prof. Fumitada Itakura. His research interests include statistical speech signal processing, blind source separation (BSS), and audio enhancement. He has successfully achieved his carrier, especially on BSS researches including theoretical bridge between unsupervised learning and spatial signal processing, and development of the real-time algorithm. He has put his research into the world's first commercially available Independent-Component-Analysis-based BSS microphone in 2007. He received paper awards from IEICE in 2001 and 2006, from Telecommunications Advancement Foundation in 2004 and 2009, from IEEE-IROS2005 in 2006, and from APSIPA in 2013. He received DOCOMO Mobile Science Award in 2011, and Ichimura Award in 2013. He won the first prize in IEEE MLSP2007 BSS Competition. He has been professionally involved in various volunteer works for IEEE, IEICE, and ASJ, including chair posts of international conferences and associate editor of journals.
On a real environment speech-oriented information guidance system, a valid and invalid input discrimination is important as invalid inputs such as noise, laugh, cough and utterances between users lead to unpredictable system responses. Generally, ...
Comparison of methods for topic classification of spoken inquiries
Rafael Torres, Hiromichi Kawanami, Tomoko Matsui, Hiroshi Saruwatari, Kiyohiro Shikano
A new complemental back-off algorithm for merging two N-gram language models is proposed. By merging several topic-dependent or style-dependent models, we can construct a general model that covers wider range of topics easily. However, a conventio...
The 22nd International Congress on Acoustics (ICA2016) Sep 2016
Statistical-model-based speech enhancement with musical-noise-free properties[Invited]
SARUWATARI Hiroshi
2015 IEEE International Conference on Digital Signal Processing (DSP2015) Jul 2015
Information-geometric optimization in nonlinear noise reduction systems[Invited]
Hiroshi Saruwatari
2013 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS2013) Nov 2013
Sound-localization-preserved binaural MMSE STSA estimator with explicit and implicit binaural cues[Invited]
SARUWATARI Hiroshi
20th European Signal Processing Conference (EUSIPCO2012) Aug 2012
Recent advances on noise reduction and source separation technology for robot audition[Invited]
SARUWATARI Hiroshi
2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2011) Sep 2011
Blind speech extraction combining ICA-based noise estimation and less-musical-noise nonlinear post processing[Invited]
SARUWATARI Hiroshi
2010 Asilomar Conference on Signals, Systems, and Computers, California Nov 2010
Improvement of speech recognition performance for spoken-oriented robot dialog system using end-fire array[Invited]
SARUWATARI Hiroshi
2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2010), Oct 2010
Source adaptive blind signal extraction using closed-form ICA for hands-free robot spoken dialogue system[Invited]
SARUWATARI Hiroshi
2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2009) Apr 2009
Hnds-free speech recognition challenge for real-world speech dialogue systems[Invited]
SARUWATARI Hiroshi
2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2009) Apr 2009
Directivity-dependency-reduced blind source separation integrating ICA, beamforming and binary masking[Invited]
SARUWATARI Hiroshi
2007 IEEE International Conference on Intelligent Robots and Systems (IROS2007) Oct 2007
MLSP 2007 data analysis competition: two-stage blind source separation combining SIMO-model-based ICA and binary masking[Invited]
SARUWATARI Hiroshi
2007 IEEE International workshops on Machine Learning for Signal Processing (MLSP2007) Aug 2007
Beyond the ICA: new blind acoustic sound separation in real world via SIMO-ICA[Invited]
SARUWATARI Hiroshi
2006 Acoustic Society of America/Japan Joint Meeting Nov 2006
Real-time blind separation of acoustic signals using SIMO-model-based independent component analysis[Invited]
SARUWATARI Hiroshi
Joint 3rd International Conference on Soft Computing and Intelligent Systems and 7th International Symposium on advanced Intelligent Systems (SCIS & ISIS 2006) Sep 2006
Robust sound field reproduction using multi-channel inverse filtering with secondary source selection and enhancement[Invited]
SARUWATARI Hiroshi
9th Western Pacific Acoustics Conference (WESPAC IX 2006) Jun 2006
Blind separation and deconvolution of MIMO-FIR system with colored inputs based on SIMO-model-based ICA[Invited]
SARUWATARI Hiroshi
2005 IEEE AP-S International Symposium on Antennas and Propagation Jul 2005
Speech enhancement based on blind source separation in car environments[Invited]
SARUWATARI Hiroshi
2005 International Workshop on Realworld Multimedia Corpora in Mobile Environment (RWCinME2005) Apr 2005
SIMO-model-based ICA - concept and its applications -[Invited]
SARUWATARI Hiroshi
18th International Congress on Acoustics (ICA2004) Apr 2004
Pitch recognition for successive musical cords using short-term estimation method for peak frequencies[Invited]
SARUWATARI Hiroshi
2004 International Symposium on Musical Acoustics (ISMA2004) Apr 2004
SIMO-model-based blind acoustic signal separation: concept and its application[Invited]
SARUWATARI Hiroshi
Special Workshop in MAUI (SWIM) Jan 2004
Blind source separation of acoustic signals based on multistage independent component analysis[Invited]
SARUWATARI Hiroshi
2002 Summer Meeting of Acoustical Society of Korea Aug 2002
Evaluation of noise adaptive nonlinear microphone array under reverberant conditions[Invited]
SARUWATARI Hiroshi
VII West Pacific Regional Acoustics Conference (WESTPRAC VII 2000) Oct 2000
Latent Variable Analysis and Signal Separation - 13th International Conference, LVA/ICA 2017, Grenoble, France, February 21-23, 2017, Proceedings 141-151 Feb 2017 [Refereed]
2017 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2017, New Orleans, LA, USA, March 5-9, 2017 21-25 Mar 2017 [Refereed]
[ICASSP2017 Student Paper Contest Finalist], [IEEE SPS Japan Student Best Paper Award]
2017 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2017, New Orleans, LA, USA, March 5-9, 2017 111-115 Mar 2017 [Refereed]
Assisting technologies for hearing impaired and esophageal speech and augmentation technologies for voice conversion and manipulation were introduced as the accomplishment of this project, which are constructed by integrating our advanced speech a...
Two invented new speech media, Non-Audible Murmur (NAM) and High fidelity Blind Source Separation (SIMO-ICA), have been theoretically and practically developed. These new media technologies have been transferred to industries. As for speech recogn...
The research plan includes the following topics,1. Noise reduction signal processing, accurate phoneme modeling, and speaker and environment adaptation.2. Task adapted language model for accepting spontaneous utterances.3. Hands-free speech recogn...
In this research, we resolve a source separation problem, which was considered within acoustics problem, by combining information theory and acoustic signal processing theory. Also we mainly aim to construct a general system consisting of "sound s...
In recent years, an accuracy in the speech recognition system can be remarkably improved by using Hidden Markov Model and Neural Networks. However, in real environments, there still exists the significant problems that the speech recognition perfo...
