Masato AKAGI

A Two-Stage Phase-Aware Approach for Monaural Multi-Talker Speech Separation
Lu YIN Junfeng LI Yonghong YAN Masato AKAGI 
Publication:   
Publication Date: 2020/07/01
Vol. E103-D  No. 7  pp. 1732-1743
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
speech separation, phase recovery, amplitude estimation, deep learning, mask estimation, 
 Summary | Full Text:PDF
Mimicking Lombard Effect: An Analysis and Reconstruction
Thuan Van NGO Rieko KUBO Masato AKAGI 
Publication:   
Publication Date: 2020/05/01
Vol. E103-D  No. 5  pp. 1108-1117
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
Lombard speech, perceptual mimicking, rule-based methods, 
 Summary | Full Text:PDF
Binaural Sound Source Localization in Noisy Reverberant Environments Based on Equalization-Cancellation Theory
Thanh-Duc CHAU Junfeng LI Masato AKAGI 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2014/10/01
Vol. E97-A  No. 10  pp. 2011-2020
Type of Manuscript:  PAPER
Category: Engineering Acoustics
Keyword: 
binaural sound localization, equalization-cancellation model, noisy reverberant environments, humanoid robot, 
 Summary | Full Text:PDF
Improving Naturalness of HMM-Based TTS Trained with Limited Data by Temporal Decomposition
Trung-Nghia PHUNG Thanh-Son PHAN Thang Tat VU Mai Chi LUONG Masato AKAGI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2013/11/01
Vol. E96-D  No. 11  pp. 2417-2426
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
text to speech, HMM-based TTS, hybrid TTS, limited data, temporal decomposition, 
 Summary | Full Text:PDF
A Hybrid Speech Emotion Recognition System Based on Spectral and Prosodic Features
Yu ZHOU Junfeng LI Yanqing SUN Jianping ZHANG Yonghong YAN Masato AKAGI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/10/01
Vol. E93-D  No. 10  pp. 2813-2821
Type of Manuscript:  PAPER
Category: Human-computer Interaction
Keyword: 
speech emotion recognition, non-uniform subband processing, spectral feature, prosodic feature, 
 Summary | Full Text:PDF
A Two-Microphone Noise Reduction Method in Highly Non-stationary Multiple-Noise-Source Environments
Junfeng LI Masato AKAGI Yoiti SUZUKI 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2008/06/01
Vol. E91-A  No. 6  pp. 1337-1346
Type of Manuscript:  Special Section PAPER (Special Section on Acoustic Scene Analysis and Reproduction)
Category: 
Keyword: 
noise reduction, non-stationary noise, multiple-noise-source environments, virtually integrated sound source, 
 Summary | Full Text:PDF
Fundamental Frequency Estimation for Noisy Speech Using Entropy-Weighted Periodic and Harmonic Features
Yuichi ISHIMOTO Kentaro ISHIZUKA Kiyoaki AIKAWA Masato AKAGI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2004/01/01
Vol. E87-D  No. 1  pp. 205-214
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
fundamental frequency estimation, entropy, instantaneous amplitude, periodic feature, harmonic feature, 
 Summary | Full Text:PDF
Modified Restricted Temporal Decomposition and Its Application to Low Rate Speech Coding
Phu Chien NGUYEN Takao OCHI Masato AKAGI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2003/03/01
Vol. E86-D  No. 3  pp. 397-405
Type of Manuscript:  Special Section PAPER (Special Issue on Speech Information Processing)
Category: Speech and Audio Coding
Keyword: 
temporal decomposition, LSF, STRAIGHT, speech coding, 
 Summary | Full Text:PDF