Tomohiro NAKATANI


Integration of Spatial Cue-Based Noise Reduction and Speech Model-Based Source Restoration for Real Time Speech Enhancement
Tomoko KAWASE Kenta NIWA Masakiyo FUJIMOTO Kazunori KOBAYASHI Shoko ARAKI Tomohiro NAKATANI 
Publication:   
Publication Date: 2017/05/01
Vol. E100-A  No. 5  pp. 1127-1136
Type of Manuscript:  PAPER
Category: Digital Signal Processing
Keyword: 
microphone arraybeamforming (BF)power spectral density (PSD) estimationGaussian mixture modelWiener filtering
 Summary | Full Text:PDF(2.1MB)

Acoustic Event Detection in Speech Overlapping Scenarios Based on High-Resolution Spectral Input and Deep Learning
Miquel ESPI Masakiyo FUJIMOTO Tomohiro NAKATANI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2015/10/01
Vol. E98-D  No. 10  pp. 1799-1807
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
acoustic event detection/recognitionhigh-resolution featurespectrogram patchcommunication scene understanding
 Summary | Full Text:PDF(1.5MB)

Harmonicity Based Dereverberation for Improving Automatic Speech Recognition Performance and Speech Intelligibility
Keisuke KINOSHITA Tomohiro NAKATANI Masato MIYOSHI 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2005/07/01
Vol. E88-A  No. 7  pp. 1724-1731
Type of Manuscript:  Special Section PAPER (Special Section on Multi-channel Acoustic Signal Processing)
Category: Speech Enhancement
Keyword: 
dereverberationspeech harmonicityautomatic speech recognitionspeech intelligibility
 Summary | Full Text:PDF(559.2KB)