Fumitada Itakura
Research Subjects
Fumitada Itakura has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Hiroshi Saruwatari
Graduate School of Information Science, Nara Institute of Science and Technology
1 shared publication - Kazuya Takeda
Center for Integrated Acoustic Information Research (CIAIR), Nagoya University
1 shared publication - Kazuya Takeda
Nagoya University
1 shared publication - Kiyohiro Shikano
Graduate School of Information Science, Nara Institute of Science and Technology
1 shared publication Satoshi Kurita
Center for Integrated Acoustic Information Research (CIAIR), Nagoya University
1 shared publication- Tsuyoki Nishikawa
Graduate School of Information Science, Nara Institute of Science and Technology
1 shared publication
Latest Publications
- 21 March 2005
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 12 (4) , 340-343
Adaptive log-spectral regression for in-car speech recognition using multiple distributed microphones
This letter addresses issues in improving hands-free speech recognition performance in different car environments. We propose a new speech-enhancement approach based on optimizing regression of the log-spectra, which is used to estimate the log-spectra of speech at a close-talking microphone by using multiple spatially distributed microphones. The regression weights can be adapted automatically for different noise environments. Compared to the nearest distant microphone and adaptive beamformer generalized sidelobe canceller (GSC), the proposed approach shows an advantage in the average relative word error rate (WER) reduction of 58.5 and 10.3%, respectively, for isolated word recognition under 15 real-car environments.
- 21 March 2005
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 12 (4) , 340-343
Adaptive log-spectral regression for in-car speech recognition using multiple distributed microphones
This letter addresses issues in improving hands-free speech recognition performance in different car environments. We propose a new speech-enhancement approach based on optimizing regression of the log-spectra, which is used to estimate the log-spectra of speech at a close-talking microphone by using multiple spatially distributed microphones. The regression weights can be adapted automatically for different noise environments. Compared to the nearest distant microphone and adaptive beamformer generalized sidelobe canceller (GSC), the proposed approach shows an advantage in the average relative word error rate (WER) reduction of 58.5 and 10.3%, respectively, for isolated word recognition under 15 real-car environments.
- Open Access
- 5 October 2003
- Published by Springer Nature in EURASIP Journal on Advances in Signal Processing
- Vol. 2003 (11) , 569270
Blind Source Separation Combining Independent Component Analysis and Beamforming
- 5 October 2003
- Published by Springer Nature in EURASIP Journal on Advances in Signal Processing
- Vol. 2003 (11) , 569270
Open AccessBlind Source Separation Combining Independent Component Analysis and Beamforming