 2011  2010  2009  2008  2007  2006  2005  2004  2003  2002  2001  2000 
Publications
2004
Journal Papers
 R. Mukai, S. Araki, H. Sawada, S. Makino,
“Evaluation of Separation and Dereverberation Performance in Frequency Domain Blind Source Separation,”
Acoustical Science and Technology, Vol.25, No.2, pp.119126, March. 2004.
 H. Sawada, R. Mukai, S. Araki, S. Makino,
“Convolutive Blind Source Separation for more than Two Sources in the Frequency Domain,”
Acoustical Science and Technology, the Acoustical Society of Japan, vol.25, no.4, pp. 296298, July 2004.
 R. Mukai, H. Sawada, S. Araki, S. Makino,
“Blind Source Separation for Moving Speech Signals using Blockwise ICA and Residual Crosstalk Subtraction,”
IEICE Trans. Fundamentals, Special Section on Digital Signal Processing, vol.E87A, no.8, pp.19411948, August, 2004.
 H. Sawada, R. Mukai, S. Araki, S. Makino,
“A Robust and Precise Method for Solving the Permutation Problem of FrequencyDomain Blind Source Separation,”
IEEE Trans. Speech and Audio Processing, vol.12, no.5, pp.530538, September 2004.
 S. Watanabe, Y. Minami, A. Nakamura and N. Ueda,
“Variational Bayesian Estimation and Clustering for Speech Recognition,”
IEEE Transactions on Speech and Audio Processing, vol. 12, pp. 365381, 2004.
Book Chapter, Tutorial Papers
Peerreviewed Conference Papers
 S. Araki, S. Makino, A. Blin, R. Mukai, and H. Sawada,
“Underdetermined Blind Separation for Speech in Real Environments with Sparseness and ICA,”
ICASSP2004, vol. III, pp. 881884, May 2004 (invited).
 A. Blin, S. Araki and S. Makino,
“A SparsenessMixing Matrix Estimation (SMME) Solving the Underdetermined BSS for Convolutive Mixtures,”
ICASSP2004, vol. IV, pp. 8588, May 2004.
 R. Mukai, H. Sawada, S. Araki, S. Makino,
“NearField Frequency Domain Blind Source Separation for Convolutive Mixtures,”
ICASSP2004, vol. IV, pp. 4952, May 2004.
 H. Sawada, R. Mukai, S. Araki, S. Makino,
“Convolutive Blind Source Separation for more than Two Sources in the Frequency Domain,”
ICASSP2004, vol. III, pp. 885888, May 2004 (invited).
 S. Makino, S. Araki, R. Mukai, and H. Sawada,
“Audio source separation based on independent component analysis,”
in Proc. ISCAS2004 (International Symposium on Circuits and Systems), vol. V, pp. 668671, May 2004 (invited).
 R. Mukai, H. Sawada, S. Araki and S. Makino,
“Frequency Domain Blind Source Separation using Small and Large Spacing Sensor Pairs,”
ISCAS2004, vol. V, pp. 14, May 2004.
 S. Araki, S. Makino, H. Sawada and R. Mukai,
“Underdetermined Blind Speech Separation with Directivity Pattern based Continuous Mask and ICA,”
EUSIPCO2004, pp.19911994, September 2004.
 S. Araki, S. Makino, H. Sawada and R. Mukai,
“Underdetermined Blind Separation of Convolutive Mixtures of Speech with Directivity Pattern based Mask and ICA,”
ICA2004, pp.898905, September 2004.
 H. Sawada, S. Winter, S. Araki, R. Mukai, S. Makino,
“Estimating the Number of Sources for FrequencyDomain Blind Source Separation,”
ICA2004 (5th International Conference on Independent Component Analysis and Blind Signal Separation), pp.610617, September 2004.
 S. Winter, H. Sawada, S. Araki, S. Makino,
“Overcomplete BSS for convolutive mixtures based on hierarchical clustering,”
ICA2004, pp.652660, September 2004.
 R. Mukai, H. Sawada, S. Araki, S. Makino,
“Frequency Domain Blind Source Separation for Many Speech Signals,”
ICA2004, pp.461469, September 2004.
 S. Winter, H. Sawada, S. Araki, S. Makino,
“Hierarchical Clustering Applied to Overcomplete BSS for Convolutive Mixtures,”
SAPA2004 (ISCA Tutorial and Research Workshop on Statistical and Perceptual Audio Processing), Session I3, October 2004.
 A. Blin, S. Araki, and S. Makino,
“Underdetermined blind source separation for convolutive mixtures exploiting a sparsenessmixing matrix estimation (SMME),”
in Proc. ICA2004 (International Congress on Acoustics), vol. IV, pp. 31393142, 2004.
 H. Sawada, R. Mukai, S. Araki, S. Makino,
“Solving the Permutation and the Circularity Problem of FrequencyDomain Blind Source Separation,”
ICA2004 (International Congress on Acoustics), vol. I, pp. 8992, 2004 (invited).
 K. Ishizuka and N. Miyazaki,
“Speech feature extraction method representing periodicity and aperiodicity in sub bands for robust speech recognition,”
Proceedings of the 29th International Conference on Acoustics, Speech, and Signal Processing (ICASSP2004), Vol.1, pp.141144, 2004.
 K. Ishizuka and N. Miyazaki,
“Speech feature extraction method representing periodicity and aperiodicity in sub bands for robust speech recognition,”
The 2nd NTT Workshop on Communication Scene Analysis (CSA2004) Poster presentation, 2004.
 K. Ishizuka, N. Miyazaki, T. Nakatani and Y. Minami,
“Improvement in robustness of speech feature extraction method using subband based periodicity and aperiodicity decomposition,”
Proceedings of the 8th International Conference on Spoken Language Processing (Interspeech2004  ICSLP), Vol.2, pp.937940, 2004.
 P. Zolfaghari, H. Kato, S. Watanabe and S. Katagiri,
“Speech Spectral Modelling using Mixture of Gaussians,”
Proc. SWIM , 2004
 P. Zolfaghari, S. Watanabe, A. Nakamura and S. Katagiri,
“Bayesian Modelling of the Speech Spectrum Using Mixture of Gaussians,”
Proc. ICASSP'04, vol. 1, pp. 553556, 2004.
 R. Mukai, H. Sawada, S. Araki, S. Makino,
“A Solution for the Permutation Problem in Frequency Domain BSS using Near and Farfield Models,”
ICA2004 (International Congress on Acoustics), vol. IV, pp. 31353138, 2004.
 S. Araki, S. Makino, A. Blin, R. Mukai, and H. Sawada,
“Underdetermined blind separation of convolutive mixtures of speech by combining timefrequency masks and ICA,”
in Proc. ICA2004 (International Congress on Acoustics), vol. I, pp.321324, 2004.
 S. Watanabe and A. Nakamura,
“Acoustic model adaptation based on coarsefine training of transfer vectors and its application to speaker adaptation task,”
Proc. ICSLP'04 , vol. 4, 29332936, 2004.
 S. Watanabe and A. Nakamura,
“Robustness of acoustic model topology determined by Variational Bayesian Estimation and Clustering for speech recognition for different speech data sets,”
Proc. Workshop on statistical modeling approach for speech recognition  Beyond HMM, pp. 5560, 2004.
 S. Watanabe, A. Sako (Ryukoku Univ.) and A. Nakamura,
“Automatic Determination of Acoustic Model Topology using Variational Bayesian Estimation and Clustering,”
Proc. ICASSP'04, vol. 1, pp. 813816, 2004.
 T. Hori, C. Hori, and Y. Minami,
“Fast onthefly composition for weighted finitestate transducers in 1.8 millionword vocabulary continuousspeech recognition,”
in Proc. ICSLP2004, Vol. 1, pp. 289292, 2004.
Other Conference Papers
 H. Sawada, R. Mukai, S. Araki, S. Makino,
“Blind Source Separation for Convolutive Mixtures in the Frequency Domain,”
CSA2004.
 K. Kinoshita, T. Nakatani and M. Miyoshi,
“Improving automatic speech recognition performance and speech intelligibility with harmonicity based dereverberation,”
Proc. Of Interspeech, 2004
 K. Kinoshita, T. Nakatani and M. Miyoshi,
“Speech dereverberation based on harmonic structure using a single microphone,”
Poster presentation at 2004 NTT Workshop on Communication Scene Analysis, 2004
 R. Mukai, H. Sawada, S. Araki, S. Makino,
“A Solution for the Permutation Problem in Frequency Domain BSS using Near and Farfield Models,”
CSA2004.
 S. Araki, S. Makino, H. Sawada and R. Mukai,
“Blind Separation of More Speech than Sensors using Timefrequency Masks and ICA,”
Proceedings of 2004 NTT Workshop on Communication Scene Analysis (CSA2004), (invited)
 S. Winter, H. Sawada,S. Araki, S. Makino,
“Underdetermined Blind Source Separation for Convolutive Mixtures of Sparse Signals,”
CSA2004
