Publications

[Books/book chapters]

  1. Takaaki Hori and Atsushi Nakamura, "SPEECH RECOGNITION ALGORITHMS BASED ON WEIGHTED FINITE-STATE TRANSDUCERS," Synthesis Lectures on Speech and Audio Processing (Biing-Hwang Juang, Series Ed.), ISBN: 978-1608454730, Morgan & Claypool (2013.1)


[Journal papers/letters]

  1. Atsushi Nakamura, "A GARBAGE MODEL TRAINING FOR KEYWORD SPOTTER WITH ARTIFICIALLY GENERATED TRAINING DATA," IEICE Transactions on Information and Systems, J82-D-II, 4, pp. 712-720 (1999.4) [in Japanese]
  2. Atsushi Nakamura, "ACOUSTIC MODELING FOR SPEECH RECOGNITION BASED ON A GENERALIZED LAPLACIAN MIXTURE DISTRIBUTION," IEICE Transactions on Information and Systems, J83-D-II, 11, pp. 2118-2127 (2000.11) [in Japanese]
  3. Masaki Naito, Hirofumi Yamamoto, Harald Singer, Hideharu Nakajima, Atsushi Nakamura and Yoshinori Sagisaka, "A CONTINUOUS SPEECH RECOGNITION SYSTEM FOR CONVERSATIONAL SPEECH," IEICE Transactions on Information and Systems, J84-D-II, 1, pp. 31-40 (2001.1) [in Japanese]
  4. Atsushi Nakamura, Masaki Naito, Hajime Tsukada, Gruhn Rainer, Eiichiro Sumita, Hideki Kashioka, Hideharu Nakajima, Tohru Shimizu and Yoshinori Sagisaka, "A SPEECH TRANSLATION SYSTEM APPLIED TO A REAL-WORLD TASK/DOMAIN AND ITS EVALUATION USING REAL-WORLD SPEECH DATA," IEICE Transactions on Information and Systems, E84-D, 1, pp. 142-154 (2001.1)
  5. Atsushi Nakamura, "RESTRUCTURING GAUSSIAN MIXTURE DENSITY FUNCTIONS IN SPEAKER-INDEPENDENT ACOUSTIC MODELS," Speech Communication, 36, 3-4, pp. 277-289, Elsevier (2002.3)
  6. Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura and Naonori Ueda, "SELECTION OF SHARED-STATES HIDDEN MARKOV MODEL STRUCTURE USING BAYESIAN CRITERION," IEICE Transactions on Information and Systems, J86-D-II, 6, pp. 776-786 (2003.6) [in Japanese]
  7. Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura and Naonori Ueda, "VARIATIONAL BAYESIAN ESTIMATION AND CLUSTERING FOR SPEECH RECOGNITION," IEEE Transactions on Speech and Audio Processing, 12, 4, pp. 365-381 (2004.7)
  8. Shinji Watanabe and Atsushi Nakamura, "ACOUSTIC MODEL ADAPTATION BASED ON COARSE/FINE TRAINING OF TRANSFER VECTORS," Information Technology Letters, 3, pp. 133-134 (2004.8) [in Japanese]
  9. Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura and Naonori Ueda, "SELECTION OF SHARED-STATE HIDDEN MARKOV MODEL STRUCTURE USING BAYESIAN CRITERION," IEICE Transactions on Information and Systems, E88-D, 1, pp. 1-9 (2005.1)
  10. Shinji Watanabe and Atsushi Nakamura, "SPEECH RECOGNITION BASED ON STUDENT'S T-DISTRIBUTION DERIVED FROM TOTAL BAYESIAN FRAMEWORK," IEICE Transactions on Information and Systems, E89-D, 3, pp. 970-980 (2006.3)
  11. Erik McDermott and Atsushi Nakamura, "PRODUCTION-ORIENTED MODELS FOR SPEECH RECOGNITION," IEICE Transactions on Information and Systems, E89-D, 3, pp. 1006-1014 (2006.3)
  12. Shinji Watanabe, Atsushi Sako and Atsushi Nakamura, "AUTOMATIC DETERMINATION OF ACOUSTIC MODEL TOPOLOGY USING VARIATIONAL BAYESIAN ESTIMATION AND CLUSTERING FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION," IEEE Transactions on Audio, Speech, and Language Processing, 14, 3, pp. 855-872 (2006.5)
  13. Atsushi Nakamura, Shinji Watanabe, Takaaki Hori, Erik McDermott and Shigeru Katagiri, "ADVANCED COMPUTATIONAL MODELS AND LEARNING THEORIES FOR SPOKEN LANGUAGE PROCESSING," IEEE Computational Intelligence Magazine, 1, 2, pp. 5-9 & 26 (2006.5)
  14. Parham Zolfaghari, Hiroko Kato, Yasuhiro Minami, Atsushi Nakamura, Shigeru Katagiri and Roy Patterson, "DYNAMIC ASSIGNMENT OF GAUSSIAN COMPONENTS IN MODELLING SPEECH SPECTRA," The Journal of VLSI Signal Processing, 45, 1-2, pp. 7-19, Springer (2006.11)
  15. Erik McDermott, Timothy J. Hazen, Jonathan Le Roux, Atsushi Nakamura and Shigeru Katagiri, "DISCRIMINATIVE TRAINING FOR LARGE VOCABULARY SPEECH RECOGNITION USING MINIMUM CLASSIFICATION ERROR," IEEE Transactions on Audio, Speech, and Language Processing, 15, 1, pp. 203-223 (2007.1)
  16. Takaaki Hori, Chiori Hori, Yasuhiro Minami and Atsushi Nakamura, "EFFICIENT WFST-BASED ONE-PASS DECODING WITH ON-THE-FLY HYPOTHESIS RESCORING IN EXTREMELY LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION," IEEE Transactions on Audio, Speech, and Language Processing, 15, 4, pp. 1352-1365 (2007.5)
  17. Takanobu Oba, Takaaki Hori and Atsushi Nakamura, "SEQUENTIAL DEPENDENCY ANALYSIS FOR ONLINE SPONTANEOUS SPEECH PROCESSING," Speech Communication, 50, 7, pp. 616-625, Elsevier (2008.7)
  18. Shinji Watanabe and Atsushi Nakamura, "PREDICTOR-CORRECTOR ADAPTATION BY USING TIME EVOLUTION SYSTEM WITH MACROSCOPIC TIME SCALE," IEEE Transactions on Audio, Speech, and Language Processing, 18, 2, pp. 395-406 (2010.2)
  19. Takanobu Oba, Takaaki Hori and Atsushi Nakamura, "IMPROVED SEQUENTIAL DEPENDENCY ANALYSIS INTEGRATING LABELING-BASED SENTENCE BOUNDARY DETECTION," IEICE Transactions on Information and Systems, E93-D, 5, pp. 1272-1281 (2010.5)
  20. Yotaro Kubo, Shinji Watanabe, Atsushi Nakamura, Erik McDermott and Tetsunori Kobayashi, "A SEQUENTIAL PATTERN CLASSIFIER BASED ON HIDDEN MARKOV KERNEL MACHINE AND ITS APPLICATION TO PHONEME CLASSIFICATION," IEEE Journal of Selected Topics in Signal Processing, 4, 6, pp. 974-984 (2010.12)
  21. David Cournapeau, Shinji Watanabe, Atsushi Nakamura and Tatsuya Kawahara, "ONLINE UNSUPERVISED CLASSIFICATION WITH MODEL COMPARISON IN THE VARIATIONAL BAYES FRAMEWORK FOR VOICE ACTIVITY DETECTION," IEEE Journal of Selected Topics in Signal Processing, 4, 6, pp. 1071-1083 (2010.12)
  22. Atsunori Ogawa, Satoshi Takahashi and Atsushi Nakamura, "EFFICIENT COMBINATION OF LIKELIHOOD RECYCLING AND BATCH CALCULATION FOR FAST ACOUSTIC LIKELIHOOD CALCULATION," IEICE Transactions on Information and Systems, E94-D, 3, pp. 648-658 (2011.3)
  23. Hideyuki Watanabe, Shinichi Taniguchi, Shigeru Katagiri, Kouta Yamada, Atsushi Nakamura, Erik McDermott, Shinji Watanabe and Miho Ohsaki, "INCREMENTAL MINIMUM CLASSIFICATION ERROR TRAINING FOR PATTERN RECOGNITION," IEICE Transactions on Information and Systems, J94-D, 4, pp. 702-711 (2011.4) [in Japanese]
  24. Hideyuki Watanabe, Shigeru Katagiri, Kouta Yamada, Erik McDermott, Atsushi Nakamura, Shinji Watanabe and Miho Ohsaki, "MINIMUM CLASSIFICATION ERROR TRAINING USING GEOMETRIC-MARGIN-BASED MISCLASSIFICATION MEASURE," IEICE Transactions on Information and Systems, J94-D, 10, pp. 1664-1675 (2011.10) [in Japanese]
  25. Takaaki Hori, Shoko Araki, Takuya Yoshioka, Masakiyo Fujimoto, Shinji Watanabe, Takanobu Oba, Atsunori Ogawa, Kazuhiro Otsuka, Dan Mikami, Keisuke Kinoshita, Tomohiro Nakatani, Atsushi Nakamura and Junji Yamato, "LOW-LATENCY REAL-TIME MEETING RECOGNITION AND UNDERSTANDING USING DISTANT MICROPHONES AND OMNI-DIRECTIONAL CAMERA," IEEE Transactions on Audio, Speech, and Language Processing, 20, 2, pp. 499-513 (2012.2)
  26. Yumi Ansai, Shoko Araki, Shoji Makino, Tomohiro Nakatani, Takeshi Yamada, Atsushi Nakamura and Nobuhiko Kitawaki, "CEPSTRAL SMOOTHING OF SEPARATED SIGNALS FOR UNDERDETERMINED SPEECH SEPARATION," The Journal of the Acoustical Society of Japan, 68, 2, pp. 74-85 (2012.2) [in Japanese]
  27. Takanobu Oba, Takaaki Hori, Atsushi Nakamura and Akinori Ito, "MODEL SHRINKAGE FOR DISCRIMINATIVE LANGUAGE MODELS," IEICE Transactions on Information and Systems, E95-D, 5, pp. 1465-1474 (2012.5)
  28. Takanobu Oba, Takaaki Hori and Atsushi Nakamura, "ROUND-ROBIN DUEL DISCRIMINATIVE LANGUAGE MODELS," IEEE Transactions on Audio, Speech, and Language Processing, 20, 4, pp. 1244-1255 (2012.5)
  29. Takanobu Oba, Takaaki Hori and Atsushi Nakamura, "EFFICIENT TRAINING OF DISCRIMINATIVE LANGUAGE MODELS BY SAMPLE SELECTION," Speech Communication, 54, 6, pp. 791-800, Elsevier (2012.7)
  30. Daisuke Saito, Shinji Watanabe, Atsushi Nakamura and Nobuaki Minematsu, "STATISTICAL VOICE CONVERSION BASED ON NOISY CHANNEL MODEL," IEEE Transactions on Audio, Speech, and Language Processing, 20, 6, pp. 1784-1794 (2012.8)
  31. Yotaro Kubo, Shinji Watanabe, Takaaki Hori and Atsushi Nakamura, "STRUCTURAL CLASSIFICATION METHODS BASED ON WEIGHTED FINITE-STATE TRANSDUCERS FOR AUTOMATIC SPEECH RECOGNITION," IEEE Transactions on Audio, Speech, and Language Processing, 20, 8, pp. 2240-2251 (2012.10)
  32. Atsunori Ogawa and Atsushi Nakamura, "JOINT ESTIMATION OF CONFIDENCE AND ERROR CAUSES IN SPEECH RECOGNITION," Speech Communication, 54, 9, pp. 1014-1028, Elsevier (2012.11)
  33. Marc Delcroix, Shinji Watanabe, Tomohiro Nakatani and Atsushi Nakamura, "CLUSTER-BASED DYNAMIC VARIANCE ADAPTATION FOR INTERCONNECTING SPEECH ENHANCEMENT PRE-PROCESSOR AND SPEECH RECOGNIZER," Computer Speech and Language, 27, 1, pp. 350-368, Elsevier (2013.1)
  34. Shinji Watanabe and Atsushi Nakamura, "BAYESIAN APPROACHES TO ACOUSTIC MODELING: A REVIEW," APSIPA Transactions on Signal and Information Processing, 1, e5, Cambridge University Press (2013.1)
  35. Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki, Atsunori Ogawa, Takaaki Hori, Shinji Watanabe, Masakiyo Fujimoto, Takuya Yoshioka, Takanobu Oba, Yotaro Kubo, Mehrez Souden, Seong-Jun Hahm and Atsushi Nakamura, "SPEECH RECOGNITION IN LIVING ROOMS: INTEGRATED SPEECH ENHANCEMENT AND RECOGNITION SYSTEM BASED ON SPATIAL, SPECTRAL & TEMPORAL MODELING OF SOUNDS," Computer Speech and Language (To be published)
  36. Seong-Jun Hahm, Shinji Watanabe, Atsunori Ogawa, Masakiyo Fujimoto, Takaaki Hori and Atsushi Nakamura, "PRIOR-SHARED FEATURE AND MODEL SPACE SPEAKER ADAPTATION BY CONSISTENTLY EMPLOYING MAP ESTIMATION," Speech Communication (To be published)


[International conferences/workshops (refereed)]

  1. Atsushi Nakamura, Toshiro Tanaka and Hisakazu Uesaka, "SCP ARCHITECTURE WITH PERFORMANCE FLEXIBILITY," Proc. IEEE GLOBECOM'91, 3, pp. 1680-1684, Phoenix, USA (1991.12)
  2. Atsushi Nakamura and Toshiro Tanaka, "SCP ARCHITECTURE WITH HIGH AVAILABILITY," Proc. IEEE GLOBECOM'92, 3, pp. 1741-1745, Orlando, USA (1992.12)
  3. Tsuyoshi Morimoto, Noriyoshi Uratani, Toshiyuki Takezawa, Osamu Furuse, Yasuhiro Sobashima, Hitoshi Iida, Atsushi Nakamura, Yoshinori Sagisaka, Norio Higuchi and Yasuhiro Yamazaki, "A SPEECH AND LANGUAGE DATABASE FOR SPEECH TRANSLATION RESEARCH," Proc. ICSLP'94, 4, pp. 1791-1794, Yokohama, Japan (1994.9)
  4. Atsushi Nakamura, "A MINIMUM ERROR TRAINING OF GARBAGE MODEL FOR KEYWORD SPOTTER WITH ARTIFICIALLY GENERATED TRAINING DATA," Proc. Eurospeech'95, 3, pp. 1641-1644, Madrid, Spain (1995.9)
  5. Atsushi Nakamura, Shoichi Matsunaga, Tohru Shimizu, Masahiro Tonomura and Yoshinori Sagisaka, "JAPANESE SPEECH DATABASES FOR ROBUST SPEECH RECOGNITION," Proc. ICSLP'96, 4, pp. 2199-2202, Philadelphia, USA (1996.10)
  6. Kazuhiro Takahashi and Atsushi Nakamura, "SPEECH RECOGNITION BASED ON SENTENCE GENERATION," Proc. ICSP'97, 2, pp. 459-464, Seoul, Korea (1997.8)
  7. Atsushi Nakamura, "PREDICTING SPEECH RECOGNITION PERFORMANCE," Proc. Eurospeech'97, 3, pp. 1567-1570, Rhodes, Greece (1997.9)
  8. Atsushi Nakamura, Harald Singer and Yoshinori Sagisaka, "ACOUSTIC MODELS FOR SPEECH RECOGNITION - HIDDEN MARKOV NETWORK -," Proc. ISCIE SSS'97, pp. 139-144, Tokyo, Japan (1997.11)
  9. Atsushi Nakamura, "RESTRUCTURING GAUSSIAN MIXTURE DENSITY FUNCTIONS IN SPEAKER-INDEPENDENT ACOUSTIC MODELS," Proc. IEEE ICASSP'98, 2, pp. 649-652, Seattle, USA (1998.5)
  10. Atsushi Nakamura and Tomoko Matsui, "ACOUSTIC MODELING BASED ON A GENERALIZED LAPLACIAN DISTRIBUTION," Proc. Eurospeech'99, 3, pp. 1347-1350, Budapest, Hungary (1999.9)
  11. Tomoko Matsui, Masaki Naito, Harald Singer, Atsushi Nakamura and Yoshinori Sagisaka, "JAPANESE SPONTANEOUS SPEECH DATABASE WITH WIDE REGIONAL AND AGE DISTRIBUTION," Proc. Eurospeech'99, 5, pp. 2251-2254, Budapest, Hungary (1999.9)
  12. Harald Singer and Atsushi Nakamura, "UNIFIED FRAMEWORK FOR ACOUSTIC TOPOLOGY MODELLING: ML-SSS AND QUESTION-BASED DECISION TREES," Proc. Eurospeech'99, 3, pp. 1355-1358, Budapest, Hungary (1999.9)
  13. Rainer Gruhn, Harald Singer, Hajime Tsukada, Atsushi Nakamura, Masaki Naito, Atsushi Nishino, Yoshinori Sagisaka and Satoshi Nakamura, "CELLULAR PHONE BASED SPEECH-TO-SPEECH TRANSLATION SYSTEM ATR-MATRIX," Proc. ICSLP'00, pp. 448-451, Beijing, China (2000.10)
  14. Yasuhiro Minami, Erik McDermott, Atsushi Nakamura and Shigeru Katagiri, "A RECOGNITION METHOD USING SYNTHESIS-BASED SCORING THAT INCORPORATES DIRECT RELATIONS BETWEEN STATIC AND DYNAMIC FEATURE VECTOR TIME SERIES," Proc. CRAC'01, Aalborg, Denmark (2001.9)
  15. Yasuhiro Minami, Erik McDermott, Atsushi Nakamura and Shigeru Katagiri, "A RECOGNITION METHOD WITH PARAMETRIC TRAJECTORY SYNTHESIZED USING DIRECT RELATIONS BETWEEN STATIC AND DYNAMIC FEATURE VECTOR TIME SERIES," Proc. IEEE ICASSP'02, 1, pp. 957-960, Orlando, USA (2002.5)
  16. Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura and Naonori Ueda, "CONSTRUCTING SHARED-STATE HIDDEN MARKOV MODELS BASED ON A BAYESIAN APPROACH," Proc. ICSLP'02, 4, pp. 2669-2672, Denver, USA (2002.9)
  17. Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura and Naonori Ueda, "APPLICATION OF VARIATIONAL BAYESIAN APPROACH TO SPEECH RECOGNITION," Proc. NIPS15, pp. 1261-1268, Vancouver, Canada (2002.12)
  18. Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura and Naonori Ueda, "BAYESIAN ACOUSTIC MODELING FOR SPONTANEOUS SPEECH RECOGNITION," Proc. IEEE SSPR'03, pp. 47-50, Tokyo, Japan (2003.4)
  19. Yasuhiro Minami, Erik McDermott, Atsushi Nakamura and Shigeru Katagiri, "RECOGNITION METHOD WITH PARAMETRIC TRAJECTORY GENERATED FROM MIXTURE DISTRIBUTION HMMS," Proc. IEEE ICASSP'03, 1, pp. 124-127, Hong Kong, China (2003.5)
  20. Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura and Naonori Ueda, "APPLICATION OF VARIATIONAL BAYESIAN ESTIMATION AND CLUSTERING TO ACOUSTIC MODEL ADAPTATION," Proc. IEEE ICASSP'03, 1, pp. 568-571, Hong Kong, China (2003.5)
  21. Yasuhiro Minami, Erik McDermott, Atsushi Nakamura and Shigeru Katagiri, "RECOGNITION METHOD WITH PARAMETRIC TRAJECTORY SYNTHESIZED USING HMMS," Proc. SWIM, paper 263, Maui, USA (2004.1)
  22. Toshiyuki Takezawa, Genichiro Kikui, Atsushi Nakamura, Yoshinori Sagisaka and Seiichi Yamamoto, "SPOKEN LANGUAGE CORPORA DEVELOPMENT AT ATR," Proc. ICA'04, 1, pp. 401-404, Kyoto, Japan (2004.4)
  23. Parham Zolfaghari, Shinji Watanabe, Atsushi Nakamura and Shigeru Katagiri, "BAYESIAN MODELLING OF THE SPEECH SPECTRUM USING MIXTURE OF GAUSSIANS," Proc. IEEE ICASSP'04, 1, pp. 553-556, Montreal, Canada (2004.5)
  24. Shinji Watanabe, Atsushi Sako and Atsushi Nakamura, "AUTOMATIC DETERMINATION OF ACOUSTIC MODEL TOPOLOGY USING VARIATIONAL BAYESIAN ESTIMATION AND CLUSTERING," Proc. IEEE ICASSP'04, 1, pp. 813-816, Montreal, Canada (2004.5)
  25. Parham Zolfaghari, Hiroko Kato, Yasuhiro Minami, Atsushi Nakamura and Shigeru Katagiri, "MODEL SELECTION FOR MIXTURE OF GAUSSIAN BASED SPECTRAL MODELLING," Proc. IEEE MLSP'04, pp. 325-334, São Luís, Brazil (2004.9)
  26. Yasuhiro Minami, Erik McDermott, Atsushi Nakamura and Shigeru Katagiri, "A THEORETICAL ANALYSIS OF SPEECH RECOGNITION BASED ON FEATURE TRAJECTORY MODELS," Proc. ICSLP'04, 1, pp. 549-552, Jeju Island, Korea (2004.10)
  27. Shinji Watanabe and Atsushi Nakamura, "ACOUSTIC MODEL ADAPTATION BASED ON COARSE-FINE TRAINING OF TRANSFER VECTORS AND ITS APPLICATION TO A SPEAKER ADAPTATION TASK," Proc. ICSLP'04, 4, pp. 2933-2936, Jeju Island, Korea (2004.10)
  28. Shinji Watanabe and Atsushi Nakamura, "ROBUSTNESS OF ACOUSTIC MODEL TOPOLOGY DETERMINED BY VBEC FOR DIFFERENT SPEECH DATA SETS," Proc. Workshop on Statistical Modeling Approach for Speech Recognition - Beyond HMM, SP2004-90/NLC2004-50, pp. 55-60, Kyoto, Japan (2004.12)
  29. Mike Schuster, Takaaki Hori and Atsushi Nakmaura, "MIXTURES OF PROBABILISTIC PRINCIPAL COMPONENT ANALYZERS IN SPEECH RECOGNITION," Proc. Workshop on Statistical Modeling Approach for Speech Recognition - Beyond HMM, SP2004-92/2004-SLP-54/NLC2004-52, pp. 67-71, Kyoto, Japan (2004.12)
  30. Takaaki Hori and Atsushi Nakamura, "GENERALIZED FAST ON-THE-FLY COMPOSITION ALGORITHM FOR WFST-BASED SPEECH RECOGNITION," Proc. Interspeech'05 (Eurospeech), pp. 557-560, Lisbon, Portugal (2005.9)
  31. Shinji Watanabe and Atsushi Nakamura, "EFFECTS OF BAYESIAN PREDICTIVE CLASSIFICATION USING VARIATIONAL BAYESIAN POSTERIORS FOR SPARSE TRAINING DATA IN SPEECH RECOGNITION," Proc. Interspeech'05 (Eurospeech), pp. 1105-1109, Lisbon, Portugal (2005.9)
  32. Mike Schuster, Takaaki Hori and Atsushi Nakamura, "EXPERIMENTS WITH PROBABILISTIC PRINCIPAL COMPONENT ANALYSIS IN LVCSR," Proc. Interspeech'05 (Eurospeech), pp. 1685-1688, Lisbon, Portugal (2005.9)
  33. Takanobu Oba, Takaaki Hori and Atsushi Nakamura, "SEQUENTIAL DEPENDENCY ANALYSIS FOR SPONTANEOUS SPEECH UNDERSTANDING," Proc. IEEE ASRU'05, pp. 284-289, Cancún, Mexico (2005.11)
  34. Takaaki Hori and Atsushi Nakamura, "AN EXTREMELY LARGE VOCABULARY APPROACH TO NAMED ENTITY EXTRACTION FROM SPEECH," Proc. IEEE ICASSP'06, 1, pp. 973-976, Toulouse, France (2006.5)
  35. Shinji Watanabe and Atsushi Nakamura, "ACOUSTIC MODEL ADAPTATION BASED ON COARSE/FINE TRAINING OF TRANSFER VECTORS USING DIRECTIONAL STATISTICS," Proc. IEEE ICASSP'06, 1, pp. 1005-1008, Toulouse, France (2006.5)
  36. Takanobu Oba, Takaaki Hori and Atsushi Nakamura, "SENTENCE BOUNDARY DETECTION USING SEQUENTIAL DEPENDENCY ANALYSIS COMBINED WITH CRF-BASED CHUNKING," Proc. ICSLP'06, pp. 1153-1156, Pittsburgh, USA (2006.9)
  37. Erik McDermott and Atsushi Nakamura, "LARGE-SCALE CONTINUOUS SPEECH RECOGNITION SYSTEM DESIGN USING DISCRIMINATIVE TRAINING," Proc. Joint Meeting of ASA/ASJ, 1pSC31, Hawaii, USA (2006.11)
  38. Shinji Watanabe and Atsushi Nakamura, "INCREMENTAL ADAPTATION BASED ON A MACROSCOPIC TIME EVOLUTION SYSTEM," Proc. IEEE ICASSP'07, 4, pp. 769-762, Hawai, USA (2007.4)
  39. Takanobu Oba, Takaaki Hori and Atsushi Nakamura, "AN APPROACH TO EFFICIENT GENERATION OF HIGH-ACCURACY AND COMPACT ERROR-CORRECTIVE MODELS FOR SPEECH RECOGNITION," Proc. Interspeech'07 (Eurospeech), pp. 1753-1756, Antwerp, Belgium (2007.8)
  40. Erik McDermott and Atsushi Nakamura, "STRING AND LATTICE BASED DISCRIMINATIVE TRAINING FOR THE CORPUS OF SPONTANEOUS JAPANESE LECTURE TRANSCRIPTION TASK," Proc. Interspeech'07 (Eurospeech), pp. 2081-2084, Antwerp, Belgium (2007.8)
  41. Yasuhiro Minami, Minako Sawaki, Kohji Dohsaka, Ryuichiro Higashinaka, Kentaro Ishizuka, Hideki Isozaki, Tatsushi Matsubayashi, Masato Miyoshi, Atsushi Nakamura, Takanobu Oba, Hiroshi Sawada, Takeshi Yamada and Eisaku Maeda, "THE WORLD OF MUSHROOMS: HUMAN-COMPUTER INTERACTION PROTOTYPE SYSTEMS FOR AMBIENT INTELLIGENCE," Proc. ACM ICMI'07, pp. 366-373, Nagoya, Japan (2007.11)
  42. Shinji Watanabe and Atsushi Nakamura, "A UNIFIED INTERPRETATION OF ADAPTATION APPROACHES BASED ON A MACROSCOPIC TIME EVOLUTION SYSTEM AND INDIRECT/DIRECT ADAPTATION APPROACHES," Proc. IEEE ICASSP'08, pp. 4285-4288, Las Vegas, USA (2008.3)
  43. Takanobu Oba, Takaaki Hori and Atsushi Nakamura, "EFFICIENT DISCRIMINATIVE TRAINING OF ERROR CORRECTIVE MODELS USING HIGH-WER COMPETITORS," Proc. Asian Workshop on Speech Science and Technology, SP2007-203, pp. 99-104, Tokyo, Japan (2008.3)
  44. Erik McDermott and Atsushi Nakamura, "FLEXIBLE DISCRIMINATIVE TRAINING BASED ON EQUAL ERROR GROUP SCORES OBTAINED FROM AN ERROR-INDEXED FORWARD-BACKWARD ALGORITHM," Proc. Interspeech'08, pp. 2398-2401, Brisbane, Australia (2008.9)
  45. Shinji Watanabe and Atsushi Nakamura, "ON-LINE ADAPTATION AND BAYESIAN DETECTION OF ENVIRONMENTAL CHANGES BASED ON A MACROSCOPIC TIME EVOLUTION SYSTEM," Proc. IEEE ICASSP'09, pp. 4373-4376, Taipei, Taiwan (2009.4)
  46. Atsunori Ogawa, Satoshi Takahashi and Atsushi Nakamura, "EFFICIENT COMBINATION OF LIKELIHOOD RECYCLING AND BATCH CALCULATION BASED ON CONDITIONAL FAST PROCESSING AND ACOUSTIC BACK-OFF," Proc. IEEE ICASSP'09, pp. 4161-4164, Taipei, Taiwan (2009.4)
  47. Atsushi Nakamura, Erik McDermott, Shinji Watanabe and Shigeru Katagiri, "A UNIFIED VIEW FOR DISCRIMINATIVE OBJECTIVE FUNCTIONS BASED ON NEGATIVE EXPONENTIAL OF DIFFERENCE MEASURE BETWEEN STRINGS," Proc. IEEE ICASSP'09, pp. 1633-1636, Taipei, Taiwan (2009.4)
  48. Erik McDermott, Shinji Watanabe and Atsushi Nakamura, "MARGIN-SPACE INTEGRATION OF MPE LOSS VIA DIFFERENCING OF MMI FUNCTIONALS FOR GENERALIZED ERROR-WEIGHTED DISCRIMINATIVE TRAINING," Proc. Interspeech'09, pp. 224-227, Brighton, UK (2009.9)
  49. Atsunori Ogawa and Atsushi Nakamura, "SIMULTANEOUS ESTIMATION OF CONFIDENCE AND ERROR CAUSE IN SPEECH RECOGNITION USING DISCRIMINATIVE MODEL," Proc. Interspeech'09, pp. 1199-1202, Brighton, UK (2009.9)
  50. Naoki Yasuraoka, Takuya Yoshioka, Tomohio Nakatani, Atsushi Nakamura and Hiroshi G. Okuno, "MUSIC DEREVERBERATION USING HARMONIC STRUCTURE SOURCE MODEL AND WIENER FILTER," Proc. IEEE ICASSP'10, pp. 53-56, Dallas, USA (2010.3)
  51. Takanobu Oba, Takaaki Hori and Atsushi Nakamura, "A COMPARATIVE STUDY ON METHODS OF WEIGHTED LANGUAGE MODEL TRAINING FOR RERANKING LVCSR N-BEST HYPOTHESES," Proc. IEEE ICASSP'10, pp. 5126-5129, Dallas, USA (2010.3)
  52. Takaaki Hori, Shinji Watanabe and Atsushi Nakamura, "SEARCH ERROR RISK MINIMIZATION IN VITERBI BEAM SEARCH FOR SPEECH RECOGNITION," Proc. IEEE ICASSP'10, pp. 4934-4937, Dallas, USA (2010.3)
  53. Shinji Watanabe, Takaaki Hori, Erik McDermott and Atsushi Nakamura, "A DISCRIMINATIVE MODEL FOR CONTINUOUS SPEECH RECOGNITION BASED ON WEIGHTED FINITE STATE TRANSDUCERS," Proc. IEEE ICASSP'10, pp. 4922-4925, Dallas, USA (2010.3)
  54. David Cournapeau, Shinji Watanabe, Atsushi Nakamura and Tatsuya Kawahara, "USING ONLINE MODEL COMPARISON IN THE VARIATIONAL BAYES FRAMEWORK FOR ONLINE UNSUPERVISED VOICE ACTIVITY DETECTION," Proc. IEEE ICASSP'10, pp. 4462-4465, Dallas, USA (2010.3)
  55. Atsunori Ogawa and Atsushi Nakamura, "DISCRIMINATIVE CONFIDENCE AND ERROR CAUSE ESTIMATION FOR EXTENDED SPEECH RECOGNITION FUNCTION," Proc. IEEE ICASSP'10, pp. 4454-4457, Dallas, USA (2010.3)
  56. Erik McDermott, Shinji Watanabe and Atsushi Nakamura, "DISCRIMINATIVE TRAINING BASED ON AN INTEGRATED VIEW OF MPE AND MMI IN MARGIN AND ERROR SPACE," Proc. IEEE ICASSP'10, pp. 4894-4897, Dallas, USA (2010.3)
  57. Hideyuki Watanabe, Shigeru Katagiri, Kouta Yamada, Erik McDermott, Atsushi Nakamura, Shinji Watanabe and Miho Ohsaki, "MINIMUM ERROR CLASSIFICATION WITH GEOMETRIC MARGIN CONTROL," Proc. IEEE ICASSP'10, pp. 2170-2173, Dallas, USA (2010.3)
  58. Yumi Ansai, Shoko Araki, Soji Makino, Tomohiro Nakatani, Takeshi Yamada, Atsushi Nakamura and Nobuhiko Kitawaki, "CEPSTRAL SMOOTHING OF SEPARATED SIGNALS FOR UNDERDETERMINED SPEECH SEPARATION," Proc. IEEE ISCAS'10, pp. 2506- 2509, Paris, France (2010.5)
  59. Shoko Araki, Takaaki Hori, Masakiyo Fujimoto, Shinji Watanabe, Takuya Yoshioka, Tomohiro Nakatani and Atsushi Nakamura, "ONLINE MEETING RECOGNIZER WITH MULTICHANNEL SPEAKER DIARIZATION," Proc. IEEE Asilomar'10, pp. 1697-1701, California, USA (2010.7)
  60. Shinji Watanabe, Takaaki Hori and Atsushi Nakamura, "LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION USING WFST-BASED LINEAR CLASSIFIER FOR STRUCTURED DATA," Proc. Interspeech'10, pp. 346-349, Makuhari, Japan (2010.9)
  61. Yotaro Kubo, Shinji Watanabe, Atsushi Nakamura and Tetsunori Kobayashi, "A REGULARIZED DISCRIMINATIVE TRAINING METHOD OF ACOUSTIC MODELS DERIVED BY MINIMUM RELATIVE ENTROPY DISCRIMINATION," Proc. Interspeech'10, pp. 2954-2957, Makuhari, Japan (2010.9)
  62. Takanobu Oba, Takaaki Hori and Atsushi Nakamura, "ROUND-ROBIN DISCRIMINATION MODEL FOR RERANKING ASR HYPOTHESES," Proc. Interspeech'10, pp. 2446-2449, Makuhari, Japan (2010.9)
  63. Atsunori Ogawa and Atsushi Nakamura, "A NOVEL CONFIDENCE MEASURE BASED ON MARGINALIZATION OF JOINTLY ESTIMATED ERROR CAUSE PROBABILITIES," Proc. Interspeech'10, pp. 242-245, Makuhari, Japan (2010.9)
  64. Takaaki Hori, Shinji Watanabe and Atsushi Nakamura, "IMPROVEMENTS OF SEARCH ERROR RISK MINIMIZATION IN VITERBI BEAM SEARCH FOR SPEECH RECOGNITION," Proc. Interspeech'10, pp. 1962-1965, Makuhari, Japan (2010.9)
  65. Daisuke Saito, Shinji Watanabe, Atsushi Nakamura and Nobuaki Minematsu, "PROBABILISTIC INTEGRATION OF JOINT DENSITY MODEL AND SPEAKER MODEL FOR VOICE CONVERSION," Proc. Interspeech'10, pp. 1728-1731, Makuhari, Japan (2010.9)
  66. Takaaki Hori, Shoko Araki, Takuya Yoshioka, Masakiyo Fujimoto, Shinji Watanabe, Takanobu Oba, Atsunori Ogawa, Kazuhiro Otsuka, Dan Mikami, Keisuke Kinoshita, Tomohiro Nakatani, Atsushi Nakamura and Junji Yamato, "REAL-TIME MEETING RECOGNITION AND UNDERSTANDING USING DISTANT MICROPHONES AND OMNI-DIRECTIONAL CAMERA," Proc. IEEE SLT'10, pp. 424-429, Berkeley, California, USA (2010.12)
  67. Yotaro Kubo, Simon Wiesler, Ralf Schlueter, Hermann Ney, Shinji Watanabe, Atsushi Nakamura and Tetsunori Kobayashi, "SUBSPACE PURSUIT METHOD FOR KERNEL-LOG-LINEAR MODELS," Proc. IEEE ICASSP'11, pp. 4500-4503, Prague, Czech Republic (2011.5)
  68. Shinji Watanabe, Daichi Mochihashi, Takaaki Hori and Atsushi Nakamura, "GIBBS SAMPLING BASED MULTI-SCALE MIXTURE MODEL FOR SPEAKER CLUSTERING," Proc. IEEE ICASSP'11, pp. 4524-4527, Prague, Czech Republic (2011.5)
  69. Daisuke Saito, Shinji Watanabe, Atsushi Nakamura and Nobuaki Minematsu, "HIGH ACCURATE MODEL-INTEGRATION-BASED VOICE CONVERSION USING DYNAMIC FEATURES AND MODEL STRUCTURE OPTIMIZATION," Proc. IEEE ICASSP'11, pp. 4576-4579, Prague, Czech Republic (2011.5)
  70. Atsunori Ogawa, Satoshi Takahashi and Atsushi Nakamura, "MACHINE AND ACOUSTICAL CONDITION DEPENDENCY ANALYSES FOR FAST ACOUSTIC LIKELIHOOD CALCULATION TECHNIQUES," Proc. IEEE ICASSP'11, pp. 5156-5159, Prague, Czech Republic (2011.5)
  71. Takanobu Oba, Takaaki Hori, Akinori Ito and Atsushi Nakamura, "ROUND-ROBIN DUEL DISCRIMINATIVE LANGUAGE MODELS IN ONE-PASS DECODING WITH ON-THE-FLY ERROR CORRECTION," Proc. IEEE ICASSP'11, pp. 5588-5591, Prague, Czech Republic (2011.5)
  72. Marc Delcroix, Shinji Watanabe, Tomohio Nakatani and Atsushi Nakamura, "DISCRIMINATIVE APPROACH TO DYNAMIC VARIANCE ADAPTATION FOR MOISY SPEECH RECOGNITION," Proc. IEEE HSCMA'11, pp. 7-12, Edinburgh, UK (2011.5)
  73. Shoko Araki, Takaaki Hori, Takuya Yoshioka, MasakiyoFujimoto, Shinji Watanabe, Takanobu Oba, Atsunori Ogawa, Kazuhiro Otsuka, Dan Mikami, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Atsushi Nakamura and Junji Yamato, "LOW-LATENCY MEETING RECOGNITION AND UNDERSTANDING USING DISTANT MICROPHONES," Proc. IEEE HSCMA'11, pp. 151-152, Edinburgh, UK (2011.5)
  74. Keiju Iso, Shoko Araki, Shoji Makino, Tomohiro Nakatani, Hiroshi Sawada, Takeshi Yamada and Atsushi Nakamura, "BLIND SOURCE SEPARATION OF MIXED SPEECH IN A HIGH REVERBERATION ENVIRONMENT," Proc. IEEE HSCMA'11, pp. 36-39, Edinburgh, UK (2011.5)
  75. Shinji Wtanabe, Atsushi Nakamura and Biing-Hwang Juang, "MODEL ADAPTATION FOR AUTOMATIC SPEECH RECOGNITION BASED ON MULTIPLE TIME SCALE EVOLUTION," Proc. Interspeech'11, pp. 1081-1084, Florence, Italy (2011.8)
  76. Marc Delcroix, Keisuke Kinoshita, Tomohio Nakatani, Shoko Araki, Atsunori Ogawa, Takaaki Hori, Shinji Watanabe, Masakiyo Fujimoto, Takuya Yoshioka, Takanobu Oba, Yotaro Kubo, Mehrez Souden, Seong-Jun Hahm and Atsushi Nakamura, "SPEECH RECOGNITION IN THE PRESENCE OF HIGHLY NON-STATIONARY NOISE BASED ON SPATIAL, SPECTRAL AND TEMPORAL SPEECH/NOISE MODELING COMBINED WITH DYNAMIC VARIANCE ADAPTATION," Proc. CHiME'11 Workshop, pp. 12-17, Florence, Italy (2011.9)
  77. Shinji Watanabe, Atsushi Nakamura and Biing-Hwang Juang, "BAYESIAN LINEAR REGRESSION FOR HIDDEN MARKOV MODEL BASED ON OPTIMIZING VARIATIONAL BOUNDS," Proc. IEEE MLSP'11, pp. 1-6, Beijing, China (2011.9)
  78. Takuro Maruyama, Shoko Araki, Tomohiro Nakatani, Shigeki Miyabe, Takeshi Yamada, Shoji Makino and Atsushi Nakamura, "NEW ANALYTICAL UPDATE RULE FOR TDOA INFERENCE FOR UNDERDETERMINED BSS IN NOISY ENVIRONMENTS," Proc. IEEE ICASSP'12, pp. 269-272, Kyoto, Japan (2012.3)
  79. Yotaro Kubo, Shinji Watanabe, Atsushi Nakamura, Simon Wiesler, Ralf Schlueter and Hermann Ney, "BASIS VECTOR ORTHOGONALIZATION FOR AN IMPROVED KERNEL GRADIENT MATCHING PURSUIT METHOD," Proc. IEEE ICASSP'12, pp. 1909-1912, Kyoto, Japan (2012.3)
  80. Yotaro Kubo, Shinji Watanabe and Atsushi Nakamura, "DECODING NETWORK OPTIMIZATION USING MINIMUM TRANSITION ERROR TRAINING," Proc. IEEE ICASSP'12, pp. 4197-4200, Kyoto, Japan (2012.3)
  81. Shinji Watanabe, Yotaro Kubo, Takanobu Oba, Takaaki Hori and Atsushi Nakamura, "BAG OF ARCS: NEW REPRESENTATION OF SPEECH SEGMENT FEATURES BASED ON FINITE STATE MACHINES," Proc. IEEE ICASSP'12, pp. 4201-4204, Kyoto, Japan (2012.3)
  82. Marc Delcroix, Atsunori Ogawa, Shinji Watanabe, Tomohiro Nakatani and Atsushi Nakamura, "DISCRIMINATIVE FEATURE TRANSFORMS USING DIFFERENCED MAXIMUM MUTUAL INFORMATION," Proc. IEEE ICASSP'12, pp. 4753-4756, Kyoto, Japan (2012.3)
  83. Atsunori Ogawa, Takaaki Hori and Atsushi Nakamura, "ERROR TYPE CLASSIFICATION ANDWORD ACCURACY ESTIMATION USING ALIGNMENT FEATURES FROMWORD CONFUSION NETWORK," Proc. IEEE ICASSP'12, pp. 4925-4928, Kyoto, Japan (2012.3)
  84. Takanobu Oba, Takaaki Hori, Atsushi Nakamura and Akinori Ito, "SPOKEN DOCUMENT RETRIEVAL BY DISCRIMINATIVE MODELING IN A HIGH DIMENSIONAL FEATURE SPACE," Proc. IEEE ICASSP'12, pp. 5153-5156, Kyoto, Japan (2012.3)
  85. Seong-Jun Hahm, Shinji Watanabe, Masakiyo Fujimoto, Takaaki Hori and Atsushi Nakamura, "NORMALIZATION AND ADAPTATION BY CONSISTENTLY EMPLOYING MAP ESTIMATION," Proc. IWSML'12, Poster 2, Kyoto, Japan (2012.3)
  86. Seong-Jun Hahm, Atsunori Ogawa, Masakiyo Fujimoto, Takaaki Hori and Atsushi Nakamura, "SPEAKER ADAPTATION USING VARIATIONAL BAYESIAN LINEAR REGRESSION IN NORMALIZED FEATURE SPACE," Proc. Interspeech'12, Tue.O4a.05, Portland, USA (2012.9)
  87. Yotaro Kubo, Takaaki Hori and Atsushi Nakamura, "INTEGRATING DEEP NEURAL NETWORKS INTO STRUCTURED CLASSIFICATION APPROACH BASED ON WEIGHTED FINITE-STATE TRANSDUCERS," Proc. Interspeech'12, Thu.P10b.07, Portland, USA (2012.9)
  88. Naohiro Tawara, Tetsuji Ogawa, Shinji Watanabe, Atsushi Nakamura and Tetsunori Kobayashi, "FULLY BAYESIAN SPEAKER CLUSTERING BASED ON HIERARCHICALLY STRUCTURED UTTERANCE-ORIENTED DIRICHLET PROCESS MIXTURE MODEL," Proc. Interspeech'12, Thu.O9b.04, Portland, USA (2012.9)
  89. Marc Delcroix, Atsunori Ogawa, Tomohiro Nakatani and Atsushi Nakamura, "DYNAMIC VARIANCE ADAPTATION USING DIFFERENCED MAXIMUM MUTUAL INFORMATION," Proc. MLSLP'12, Portland, USA (2012.9)
  90. Atsunori Ogawa, Takaaki Hori and Atsushi Nakamura, "RECOGNITION RATE ESTIMATION BASED ON WORD ALIGNMENT NETWORK AND DISCRIMINATIVE ERROR TYPE CLASSIFICATION," Proc. IEEE SLT'12, pp. 113-118, Miami, USA (2012.12)
  91. Takuro Maruyama, Shoko Araki, Tomohiro Nakatani, Shigeki Miyabe, Takeshi Yamada, Shoji Makino and Atsushi Nakamura, "NEW ANALYTICAL CALCULATION AND ESTIMATION FOR TDOA INFERENCE FOR UNDERDETERMINED BSS IN NOISY ENVIRONMENTS," Proc. APSIPA-ASC'12, 281, Hollywood, USA (2012.12)


[Tutorial papers, survey, etc.]

  1. Toshiyuki Takezawa, Osamu Furuse and Atsushi Nakamura, "CONSTRUCTION OF SPEECH AND LANGUAGE DATABASE -EXPLORATION INTO SPOKEN LANGUAGE FOR NATURAL PHONETIC AND LINGUISTIC PHENOMENA-," ATR Journal, ATRJ_17, pp. 4-5 (1994.Autumn) [in Japanese]
  2. Atsushi Nakamura, "SPEECH RECOGNITION USING HIDDEN MARKOV MODELS," Journal of Japan Society for Fuzzy Theory and Systems, 10, 6, pp. 1084-1090 (1998.12) [in Japanese]
  3. Atsushi Nakamura, "COMPUTERS CAN BE MORE LIBERAL FOR A DEFORMED SPEECH," ATR Journal, ATRJ_31, pp. 8-9 (1998.Spring) [in Japanese]
  4. Toshiyuki Takezawa, Atsushi Nakamura and Eiichiro Sumita, "DATABASES FOR CONVERSATIONAL SPEECH TRANSLATION RESEARCH AT ATR," Journal of the Phonetic Society of Japan, 4, 2, pp. 16-23 (2000.8) [in Japanese]
  5. Atsushi Nakamura, Yasuhiro Minami and Erik McDermott, "NEXT-GENERATION SPEECH RECOGNITION TECHNOLOGY," NTT Technical Journal, 15, 12, pp. 13-18 (2003.12) [in Japanese]
  6. Atsushi Nakamura, "BOOK REVIEW: THE MAN WHO TASTED SHAPES (RICHARD E. CYTOWIC; JAPANESE TRANSLATION BY ATSUKO YAMASHITA)," Journal of Acoustical Society of Japan, 62, 1, pp. 85-86 (2005.12) [in Japanese]
  7. Eisaku Maeda, Yasuhiro Minami, Masato Miyoshi, Minako Sawaki, Hiroshi Sawada, Atsushi Nakamura, Junji Yamato, Takeshi Yamada and Ryuichiro Higashinaka, "THE WORLD OF MUSHROOMS - A TRANSDISCIPLINARY APPROACH TO HUMAN-COMPUTER INTERACTION WITH AMBIENT INTELLIGENCE," NTT Technical Review, 4, 12, pp. 17-25 (2006.12)
  8. Takaaki Hori, Katsuhito Sudoh, Hajime Tsukada and Atsushi Nakamura, "-," Journal of the ITU Association of Japan, 38, 8, pp. 10-11 (2008.8) [in Japanese]
  9. Takaaki Hori, Katsuhito Sudoh, Hajime Tsukada and Atsushi Nakamura, "WORLD-WIDE MEDIA BROWSER-MULTILINGUAL AUDIO-VISUAL CONTENT RETRIEVAL AND BROWSING SYSTEM," NTT Technical Review, 7, 2, pp. 1-7 (2009.2)
  10. Takaaki Hori, Katsuhito Sudoh, Hajime Tsukada and Atsushi Nakamura, "WORLD-WIDE MEDIA BROWSER," NTT Technical Journal, 21, 5, pp. 13-16 (2009.5) [in Japanese]
  11. Shinji Watanabe and Atsushi Nakamura, "DISCRIMINATIVE TRAINING IN SPEECH RECOGNITION," Journal of IEICE, 94, 10, pp. 920-922 (2011.10) [in Japanese]


[Domestic symposiums/conferences]

Available from Japanese page.