International Conferences

  1. Y. Itoh, H. Nishizaki, X. Hu, H. Nanjo, T. Akiba, T. Kawahara, S. Nakagawa, T. Matsui, Y. Yamashita and K. Aikawa, "Constructing Japanese Test Collections for Spoken Term Detection", 11th International Congress on Spoken Language Processing (INTERSPEECH 2010 ICSLP), pp.677-680, 2010.
  2. M. Yamada, M. Sugiyama, G. Wichern, and T. Matsui (2010). Acceleration of Sequence Kernel Computation for Real-time Speaker Identification, Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing.
  3. Tomoko Matsui, Shin'ichi Sato, Yuji Uchiyama (2009). ISM TRECVID2009 High-level Feature Extraction, Proc. TRECVID Workshop.
  4. Makoto Yamada, Masashi Sugiyama, Tomoko Matsui (2009). Covariate Shift Adaptation for Semi-Supervised Speaker Identification, Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing.
  5. Jean-Philippe Vert, Tomoko Matsui, Shin'ichi Satoh, Yuji Uchiyama (2009). High-Level Feature Extraction Using SVM with Walk Based Graph Kernel, Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing.
  6. Kimiko Yamakawa, Hideaki Kikiuchi, Tomoko Matsui,  and Shuichi Itahashi (2009). Utilization of Acoustical Feature in Visualization of Multiple Speech Corpora, Proc. Oriental COCOSDA 2009.
  7. Tomoko Matsui, Jean-Philippe Vert, Shin'ichi Sato, Yuji Uchiyama (2008). ISM TRECVID2008 High-level Feature Extraction, Proc. TRECVID Workshop.
  8. Hideki Okamoto, Tomoko Matsui, Hiromichi Kawanami, Hiroshi Saruwatari,Kiyohiro Shikano (2008). Speaker Verification with Non-Audible Murmur Segments by Combining Global Alignment Kernel and Penalized Logistic Regression Machine,　Proc. International Conference on Spoken Language Processing.
  9. Kimiko Yamakawa, Tomoko Matsui, Shuichi Itahashi (2008). MDS-Based Visualization Method for Multiple Speech Corpora, Proc. International Conference on Spoken Language Processing.
  10. M. Yamada and T. Matsui, "A fast sequence kernel for sequential data classification," Proc. Asian Workshop on Speech Science and Technology, 2008.
  11. K. Yamakawa, T. Matsui and S. Itahashi, "Visualization of various speech corpora by multidimensional scaling," Proc. Oriental COCOSDA, 2007.
  12. H. D. Le, S. Satoh, and T. Matsui, "NII-ISM, Japan at TRECVID 2007: high level feature extraction," Proc. TRECVID Workshop, Washington, 2007.
  13. H. Okamoto, M. Kojima, T. Matsui, H. Kawanami, H. Saruwatari, K. Shikano, "Study on speaker verification with non-audible murmur segments," Proc. Interspeech, pp. 2017-2020, 2007.
  14. M. Cuturi, J. –P. Vert, O. Birkenes, and T. Matsui, "A kernel for time series based on global alignments," Proc. ICASSP, Hawaii, 2007.
  15. O. Birkenes, T. Matsui, K. Tanabe, and T. A. Myrvoll, "N-Best Rescoring For Speech Recognition Using Penalized Logistic Regression Machines with Garbage Class," Proc. ICASSP, Hawaii, 2007.
  16. M. Kojima, T. Matsui, H. Kawanami, H. Saruwatari, and K. Shikano, "Study on nonaudible murmur speaker verification using multiple session data," Proc. ASA/ASJ Joint Meeting, Hawaii, 2006.
  17. M. Naito, K. Matsumoto, M. Shishibori, K. Kita, M. Cuturi, T. Matsui, S. Sato, K. Hoashi, F. Sugaya, and Y. Nakajima, "Shot Boundary Detection and High-Level Feature Extraction Experiments for TRECVID 2006," Proc. TRECVID Workshp, Washington, 2006.
  18. M. Kojima, T. Matsui, H. Kawanami, H. Saruwatari, and K. Shikano, "Speaker Verification with Non-Audible Murmur Segments,"  Proc. Interspeech, Pittsburgh, 2006.
  19. T. A. Myrvoll and T. Matsui, "On a greedy learning algorithm for dPLRM with applications to phonetic feature detection," Proc. Interspeech, Pittsburgh, 2006.
  20. T. A. Myrvoll and T. Matsui, "On a Greedy Learning Algorithm for dPLRM with Applications to Phonetic Feature Detection," Proc. Norsig, 2006.
  21. O. Birkenes, T. Matsui, K. Tanabe and T. A. Myrvoll, "Continuous Speech Recognition with Penalized Logistic Regression Machines," Proc. Norsig, 2006.
  22. O. Birkenes, T. Matsui and K. Tanabe, "Isolated-Word Recognition with Penalized Logistic Regression Machines," Proc. ICASSP, 2006.
  23. T. Matsui and K. Tanabe, "dPLRM-Based Speaker Identification with Log Power Spectrum," Proc. Interspeech, pp. 2017-2020, 2005.
  24. A. Doucet, S. Senecal and T. Matsui, "Space Alternating Data Augmentation: Application to Finite Mixture of Gaussians and Speaker Recognition," Proc. ICASSP, pp. IV-713-716, 2005.
  25. T. Matsui and K. Tanabe, "dPLRM: Application to Speaker Identification," Proc. International Symposium on The Art of Statistical Metaware, pp. 171-178, 2005.
  26. T. Matsui and K. Tanabe, "Speaker Recognition without Feature Extraction Process," Proc. Workshop on Statistical Modeling Approach for Speech Recognition, pp. 79-84, 2004.
  27. T. Matsui and K. Tanabe, "Probabilistic Speaker Identification with dual Penalized Logistic Regression Machine," Proc. ICSLP, pp. III-1797-1800, 2004.
  28. T. Matsui and K. Tanabe, "Speaker identification with dual penalized logistic regression machine," Proc. Odyssey, pp. 363-368, 2004.
  29. I. R. Lane, T. Kawahara, T. Matsui, and S. Nakamura, "Out-of-domain detection based on confidence measures from multiple topic classification," Proc. ICASSP, pp. I-757-760, 2004.
  30. I. R. Lane, T. Kawahara, T. Matsui and S. Nakamura, "Hierarchical topic classification for dialog speech recognition," Proc. Eurospeech, pp. I-429-432, 2003.
  31. T. Jitsuhiro, T. Matsui and S. Nakamura, "Automatic generation of non-uniform context-dependent HMM topologies based on the MDL criterion," Proc. Eurospeech, pp. IV-2721-2724, 2003.
  32. T. Jitsuhiro, T. Matsui and S. Nakamura, "A successive state splitting algorithm based on the MDL criterion by data-driven and decision tree clustering," Proc. SSPR, 2003.
  33. I. R. Lane, T. Kawahara, T. Matsui and S. Nakamura, "Language model switching based on topic detection for dialog speech recognition," Proc. ICASSP, 2003.
  34. T. Matsui, F. K. Soong and B. -H. Juang, "Classifier design for verification of multi-class recognition decision," Proc. ICASSP, 2002.
  35. T. Matsui, F. K. Soong and B. -H. Juang, "Verification of multi-class recognition decision using classification approach," Proc. ASRU workshop, 2001.
  36. K. Okuda, T. Matsui and S. Nakamura, "Towards the creation of acoustic models for stressed Japanese speech," Proc. Eurospeech, pp. 1653-1656, 2001.
  37. K. Okuda, T. Matsui and S. Nakamura, "Acoustic modeling method for stressed Japanese speech," Proc. ICSP, 2001.
  38. K. Okuda, T. Matsui and S. Nakamura, "Acoustic model for robust speech recognition of stressed Japanese speech," Proc. HSC workshop, pp. 127-130, 2001.
  39. T. Matsui, M. Naito, Y. Sagisaka, K. Okuda and S. Nakamura, "Analysis of acoustic models trained on a large-scale Japanese speech database," Proc. ICSLP, pp. II-503-507, 2000.
  40. T. Matsui, M. Naito, H. Singer, A. Nakamura and Y. Sagisaka, "Japanese spontaneous speech database with wide regional and age distribution," Proc. Eurospeech, pp. V-2251-2254, 1999.
  41. A. Nakamura and T. Matsui, "Acoustic modeling based on a generalized Laplacian distribution," Proc. Eurospeech, pp. III-1347-1350, 1999.
  42. T. Matsui and K. Aikawa, "Robust speaker verification insensitive to session-dependent utterance variation and handset-dependent distortion," Proc. ICSLP, pp. I-246-249, 1998.
  43. T. Matsui and K. Aikawa, "Robust model for speaker verification against session-dependent utterance variation," Proc. ICASSP, pp. I-117-120, 1998.
  44. T. Matsui, T. Matsuoka and S. Furui, "Smoothed N-best-based speaker adaptation for speech recognition," Proc. ICASSP, pp. II-1015-1018, 1997.
  45. S. Furui and T. Matsui, "Model-based unsupervised instantaneous speaker adaptation,"  J. Acoust. Soc. Amer., 100, 4 (pt. 2), 4pSC25, 1996.
  46. S. Furui and T. Matsui, "Relationships between individual and phonetic information in speech waves: Their application to automatic speech recognition," J. Acoust. Soc. Amer., 100, 4 (pt. 2), 1pSC9, 1996.
  47. T. Matsui and S. Furui, "N-best-based instantaneous speaker adaptation method for speech recognition," Proc. ICSLP, pp. II-973-976, 1996.
  48. T. Matsui, T. Nishitani and S. Furui, "Robust methods of updating model and a priori threshold in speaker verification," Proc. ICASSP, pp. I-97-100, 1996.
  49. T. Matsuoka, N. Uemoto, T. Matsui and S. Furui, "Elaborate acoustic modeling for Japanese connected digit recognition," Proc. IEEE Automatic Speech Recognition Workshop, Snowbird, pp. 169-170, 1995.
  50. T. Matsui and S. Furui, " A study of speaker adaptation based on minimum classification error training," Proc. Eurospeech, pp. I-81-84, 1995.
  51. T. Matsui, T. Kanno and S. Furui, "Speaker recognition using HMM composition in noisy environments," Proc. Eurospeech, pp. I-621-624, 1995.
  52. S. Furui and T. Matsui, "Phoneme-level voice individuality used in speaker recognition," Proc. ICSLP, pp. III-1463-1466, 1994.
  53. T. Matsui and S. Furui, " A similarity normalization method for speaker verification based on a posteriori probability," ESCA Tutorial and Research Workshop on Automatic Speaker Recognition Identification Verification, pp. 59-62, 1994.
  54. T. Matsui, S. Furui, " Speaker adaptation of tied-mixture-based phoneme models for text-prompted speaker recognition," Proc. ICASSP, pp. I-125-128, 1994.
  55. C. Griffin, T. Matsui and S. Furui, "Distance measures for text-independent speaker recognition based on MAR model," Proc. ICASSP, pp. I-309-312, 1994.
  56. T. Matsui and S. Furui, " Concatenated phoneme models for text-variable speaker recognition," Proc. ICASSP, pp. II-391-394, 1993.
  57. S. Furui and T. Matsui, "Free-text speaker recognition methods using phoneme class models," IEEE Workshop o Interactive Voice Technology for Telecommunication Applications, 1992.
  58. T. Matsui and S. Furui, "Speaker recognition using concatenated phoneme models," Proc. ICSLP, pp. I-603-606, 1992.
  59. T. Matsui and S. Furui, " Comparison of text-independent speaker recognition methods using VQ-distortion and discrete/continuous HMMs," Proc. ICASSP, pp. II-157-160, 1992.
  60. T. Matsui and S. Furui, "A text-independent speaker recognition method robust against utterance variations," Proc. ICASSP, pp. 377-380, 1991.
  61. T. Matsui and S. Furui, "Text-independent speaker recognition using vocal tract and pitch information," Proc. ICSLP, pp. 137-140, 1990.