Publications

Journal Papers and Letters

  1. Masakiyo Fujimoto, Shinji Watanabe, and Tomohiro Nakatani, "Frame-wise model re-estimation method based on Gaussian pruning with weight normalization for noise robust voice activity detection," Speech Communication, vol. 54, pp. 229--244 (2012).
  2. 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 & Language Processing, vol.xxx, pp.xx--xx, (2011).
  3. 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," (in Japanese)  IEICE Transactions on Information and Systems, vol.J94-D, No.10, pp.1664--1675, (2011).
  4. Hideyuki Watanabe, Shin'ichi TANIGUCHI, Shigeru Katagiri, Kouta Yamada, Atsushi Nakamura, Erik McDermott, Shinji Watanabe, and Miho Ohsaki, "Incremental Minimum Classification Error Training for Pattern Recognition," (in Japanese)  IEICE Transactions on Information and Systems vol. J94-D, no. 4, pp. 702--711,  (2011).
  5. Shinji Watanabe, Tomoharu Iwata, Takaaki Hori, Atsushi Sako, and Yasuo Ariki, "Topic Tracking Language Model for Speech Recognition," Computer Speech & Language, vol. 25, issue 2, pp. 440--461, (2011).
  6. 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, vol 4, issue 6, pp. 974--984 (2010) IEEE Signal Processing Society Japan Chapter Student Paper Award.
  7. 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, vol 4, issue 6, pp. 1071--1083 (2010).
  8. Tomoharu Iwata, Shinji Watanabe, Takeshi Yamada and Naonori Ueda, "Topic Tracking Model for Purchase Behavior Analysis," (in Japanese) IEICE Transactions on Information and Systems, vol. J93-D, No. 6, pp. 978--987 (2010).
  9. Kenta Nishiki, Yousuke Izumi, Shinji Watanabe, Takuya Nishimoto, Nobutaka Ono, And Shigeki Sagayama, "Stereo-input speech recognition using sparseness-based blind source separation," (in Japanese) IEICE Transactions on Information and Systems vol. J93-D, no. 3, pp. 303--311,  (2010).
  10. Shinji Watanabe and Atsushi Nakamura, "Predictor-Corrector Adaptation by using Time Evolution System with Macroscopic Time Scale," IEEE Transactions on Audio, Speech & Language Processing, vol. 18, issue 2, pp. 395--406 (2010)
  11. Marc Delcroix, Tomohiro Nakatani, and Shinji Watanabe, "Static and Dynamic Variance Compensation for Recognition of Reverberant Speech With Dereverberation Preprocessing, " IEEE Transactions on Audio, Speech & Language Processing, vol. 17, issue 2, pp. 324--334, (2009).
  12. Shinji Watanabe and Atsushi Nakamura, "Speech recognition based on Student's t-distribution derived from total Bayesian framework," IEICE Transactions on Information and Systems, vol.E89-D, no. 3, pp. 970--980, (2006).
  13. 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 Speech and Audio Processing,, vol. 14, issue 3, pp. 855--872, (2006). (received the TELECOM System Technology Award from the Telecommunications Advancement Foundation in 2006)
  14. Shinji Watanabe and Atsushi Nakamura, "Acoustic Model Adaptation based on Coarse/Fine Training of Transfer Vectors," (in Japanese), Information Technology Letters (2004).
  15. Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura, and Naonori Ueda, "Variational Bayesian Estimation and Clustering for Speech Recognition," IEEE Transactions on Speech and Audio Processing, vol. 12, pp. 365--381, (2004).
  16. Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura, and Naonori Ueda, "Selection of Shared-State Hidden Markov Model Structure Using Bayesian Criterion,"IEICE D-II, vol. J86-D-II, no. 6, pp. 776--786, (2003), (received the Best Paper Award from IEICE. The English translation version is in IEICE Transactions on Information and Systems, vol.E88-D, no. 1, pp. 1--9, (2005)).
  17. Hisakazu Minakata and Shinji Watanabe, "Solar Neutrinos and Leptonic CP Violation," Phys. Lett. B, 468, p. 256, (1999).

Review Papers and Book Chapters

  1. Shinji Watanabe, "Bayesian approaches in speech recognition," APSIPA ASC 2011, Plenary Overview Sessions, (2011).
  2. Shinji Watanabe and Atsushi Nakamura, "Tutorial: Discriminative Training in Speech Recognition," (in Japanese) The Journal of the Institute of Electronics, Information and Communication Engineers (IEICE), vol. 94(10), pp. 920--922, (2011)
  3. Marc Delcroix, Shinji Watanabe, and Tomohiro Nakatani, "Chapter 9 -Variance Compensation for Recognition of Reverberant Speech with Dereverberation Preprocessing-," in Robust Speech Recognition of Uncertain or Missing Data:Theory and Applications by Dorothea Kolossa, Reinhold Hab-Umbach, Springer Verlag, pp. 225--256, (2011).
  4. Shinji Watanabe, "Acoustic models in speech recognition," The Journal of the Acoustical Society of Japan, vol. 66, number 1, pp. 18--22, (2010). (in Japanese).
  5. 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, vol. 1, issue 2, pp. 5--9, (2006).
  6. Shinji Watanabe, "Speech recognition based on a Bayesian approach," The Journal of the Acoustical Society of Japan, vol. 62, number 8, pp. 599--604, (2006). (in Japanese) 

International Conferences and Workshops

  1. Shinji Watanabe, Atsushi Nakamura, and Biing-Hwang Juang, "Bayesian Linear Regression For Hidden Markov Model Based On Optimizing Variational Bounds," Proc. MLSP'11, pp.xx--xx,  (2011).
  2. 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 the presence of highly non-stationary noise based on spatial, spectral and temporal speech/noise modeling combined with dynamic variance adaptation," Proc. CHiME'11, pp.12--17 (2011).
  3. Shinji Watanabe, Atsushi Nakamura, and Biing-Hwang Juang, "Model Adaptation for Automatic Speech Recognition Based on Multiple Time Scale Evolution," Proc. Interspeech'11, (accepted).
  4. Masakiyo Fujimoto, Shinji Watanabe, and Tomohiro Nakatani, "A Robust Estimation Method of Noise Mixture Model for Noise Suppression," Proc. Interspeech'11, (accepted).
  5. Tomoharu Iwata and Shinji Watanabe, "Learning Influences from Word Use in Polylogue," Proc. Interspeech'11, (accepted).
  6. Naohiro Tawara, Shinji Watanabe, Tetsuji Ogawa, and Tetsunori Kobayashi, "Speaker Clustering Based on Utterance-oriented Dirichlet Process Mixture Model," Proc. Interspeech'11, (accepted).
  7. Tomoharu Iwata, Shinji Watanabe and Hiroshi Sawada, “Fashion Coordinates Recommender System using Photographs from Fashion Magazines,” Proc. IJCAI’11, pp. 2262--2267 (2011).
  8. Marc Delcroix, Shinji Watanabe, Tomohiro Nakatani, and Atsushi Nakamura, “Discriminative approach to dynamic variance adaptation for noisy speech recognition,” Proc. HSCMA’11, pp. 7--12 (2011).
  9. Shoko Araki, Takaaki Hori, Takuya Yoshioka, Masakiyo Fujimoto, Shinji Watanabe, Takanobu Oba, Atsunori Ogawa, Kazuhiro Otsuka, Dan Mikami, Keisuke Kinoshita, Tomohiro Nakatani, Atsushi Nakamura, Junji Yamato, “Low-latency meeting recognition and understanding using distant microphones,” Proc. HSCMA’11, pp. 151--152 (2011).
  10. Takuya Maekawa, Shinji Watanabe,” Unsupervised Activity Recognition with User's Physical Characteristics Data,” Proc. ISWC’11, pp. 89--96 (2011) Best In-Category Nominee.
  11. Shinji Watanabe, Daichi Mochihashi, Takaaki Hori, and Atsushi Nakamura,” Gibbs Sampling Based Multi-Scale Mixture Model for Speaker Clustering,” Proc. ICASSP’11, pp. 4524--4527 (2011).
  12. Masakiyo Fujimoto, Shinji Watanabe, and Tomohiro Nakatani, “Non-Stationary Noise Estimation Method Based on Bias-Residual Component Decomposition for Robust Speech Recognition,” Proc. ICASSP’11 , pp. 4816--4819 (2011).
  13. Daisuke Saito, Shinji Watanabe, Atsushi Nakamura, and Nobuaki Minematsu, “High Accurate Model-Integration-Based Voice Conversion Using Dynamic Features and Model Structure Optimization,” Proc. ICASSP’11, pp. 4576--4579 (2011).
  14. Yotaro Kubo, Simon Wiesler, Ralf Schlueter, Hermann Ney, Shinji Watanabe, Atsushi Nakamura, and Tetsunori Kobayashi, “Subspace Pursuit Method for Kernel-Log-Linear Models,” Proc. ICASSP’11, pp. 4500--4503 (2011).
  15. Shinji Watanabe, Tomoharu Iwata, Takaaki Hori, Atsushi Sako, and Yasuo Ariki, "Application of Topic Tracking Model to Language Model Adaptation and Meeting Analysis," Proc. IEEE Workshop on Spoken Language Technology (SLT'10), pp. 366--371 (2010).
  16. Takaaki Hori, Shoko Araki, Takuya Yoshioka, Masakiyo Fujimoto, Shinji Watanabe, Takanobu Oba, Atsunori Ogawa, Kazuhiro Otsuka, Dan Mikami, Keisuke Kinoshita, Tomohiro Nakatani, Atsushi Nakamura, Junji Yamato, "Real-time Meeting Recognition and Understanding Using Distant Microphones and Omni-directional Camera," Proc. IEEE Workshop on Spoken Language Technology (SLT'10), pp. 412--417 (2010)
  17. Shoko Araki, Takaaki Hori, Masakiyo Fujimoto, Shinji Watanabe, Takuya Yoshioka, Tomihiro Nakatani “Online Meeting Recognizer with Multichannel Speaker Diarization, “ Proc. Asilomar’10, pp. 1697--1701 (2010).
  18. 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, (2010).
  19. Masakiyo Fujimoto, Shinji Watanabe, and Tomohiro Nakatani, "Voice Activity Detection Using Frame-Wise Model Re-Estimation Method Based on Gaussian Pruning with Weight Normalization," Proc. Interspeech'10, pp. 3102--3105, (2010).
  20. 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, (2010).
  21. 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, (2010).
  22. 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, (2010).
  23. Shinji Watanabe, Takaaki Hori, Erik McDermott, and Atsushi Nakamura, "A discriminative model for continuous speech recognition based on weighted finite state transducers," Proc. ICASSP'10, pp. 4922--4925, (2010).
  24. David Cournapeau, Shinji Watanabe, and Atsushi Nakamura, Tatsuya Kawahara, "Using online model comparison in the variational Bayes framework for online unsupervised voice activity detection," Proc. ICASSP'10, pp. 4462--4465, (2010).
  25. Takaaki Hori, Shinji Watanabe, and Atsushi Nakamura, "Search error risk minimization in Viterbi beam search for speech recognition," Proc. ICASSP'10, pp. 4934--4937, (2010).
  26. Kazuo Aoyama, Shinji Watanabe, Hiroshi Sawada, Yasuhiro Minami, Naonori Ueda, and Kazumi Saito, "Fast similarity search on a large speech data set with neighborhood graph indexing," Proc. ICASSP'10, pp. 5358--5361, (2010).
  27. Erik McDermott, Shinji Watanabe, and Atsushi Nakamura, "Discriminative training based on an integrated view of MPE and MMI in margin and error space," Proc. ICASSP'10, pp. 4894--4897, (2010).
  28. Hideyuki Watanabe, Shigeru Katagiri, Kouta Yamada, Erik McDermott, Atsushi Nakamura, Shinji Watanabe, and Miho Ohsaki, "Minimum error classification with geometric margin control," Proc. ICASSP'10, pp. 4922―4925, (2010).
  29. 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, (2009).
  30. Yosuke Izumi, Kenta Nishiki, Shinji Watanabe, Takuya Nishimoto, Nobutaka Ono, and Shigeki Sagayama, "Stereo-input Speech Recognition using Sparseness-based Time-frequency Masking in a Reverberant Environment," Proc. Interspeech'09, pp. 1955--1958, (2009).
  31. Tomoharu. Iwata, Shinji Watanabe, Takeshi Yamada and Naonori Ueda, "Topic tracking model for analyzing consumer purchase behavior," Proc. IJCAI'09, pp. 1427--1432, (2009).
  32. Atushi 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. ICASSP'09, pp. 1633-1636, (2009).
  33. Shinji Watanabe and Atsushi Nakamura, "Speech recognition with incremental tracking and detection of changing environments based on a macroscopic time evolution system, " Proc. ICASSP'09, pp. 4373-4376, (2009).
  34. Marc Delcroix, Tomohiro Nakatani, and Shinji Watanabe, "Combined static and dynamic variance adaptation for efficient interconnection of speech enhancement pre-processor with speech recognizer," Proc. ICASSP'08, pp. 4073--4076, (2008).
  35. Shinji Watanabe and Atsushi Nakamura, "A unified interpretation of adaptation approaches based on a macroscopic time evolution system and indirect/direct adaptation approaches," Proc. ICASSP'08, pp. 4285--4288, (2008)
  36. Shinji Watanabe and Atsushi Nakamura, "Incremental adaptation based on a macroscopic time evolution system," Proc. ICASSP'07,  vol. 4, pp. 769--772, (2007)
  37. Shinji Watanabe and Atsushi Nakamura, "Acoustic model adaptation based on coarse/fine training of transfer vectors using directional statistics," Proc. ICASSP'06, vol. 1, pp. 1005--1008, (2006)
  38. Shinji Watanabe and Atsushi Nakamura, "Effects of Bayesian predictive classification using variational Bayesian posteriors for sparse training data in speech recognition," Proc. Interspeech'05, pp. 1105--1109, (2005).
  39. Shinji Watanabe and Atsushi Nakamura, "Robustness of acoustic model topology determined by VBEC (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. 55--60, (2004).
  40. Shinji Watanabe and Atsushi Nakamura, "Acoustic model adaptation based on coarse-fine training of transfer vectors and its application to speaker adaptation task," Proc. ICSLP'04, vol. 4, pp. 2933--2936, (2004).
  41. Parham Zolfaghari, Shinji Watanabe, Atsushi Nakamura and Shigeru Katagiri, "Bayesian Modelling of the Speech Spectrum Using Mixture of Gaussians," Proc. ICASSP'04, vol. 1, pp. 553--556, (2004).
  42. Shinji Watanabe, Atsushi Sako and Atsushi Nakamura, "Automatic Determination of Acoustic Model Topology using Variational Bayesian Estimation and Clustering," Proc. ICASSP'04, vol. 1, pp. 813--816, (2004).
  43. Parham Zolfaghari, Hiroko Kato, Shinji Watanabe and Shigeru Katagiri, "Speech Spectral Modelling using Mixture of Gaussians, " Proc. SWIM , (2004)
  44. Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura, and Naonori Ueda, "Bayesian Acoustic Modeling for Spontaneous Speech Recognition," Proc. SSPR'03, pp. 47--50, (2003).
  45. Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura, and Naonori Ueda, "Application of Variational Bayesian Estimation and Clustering to Acoustic Model Adaptation," Proc. ICASSP'03, vol. 1, pp. 568--571, (2003).
  46. Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura, and Naonori Ueda, "Application of Variational Bayesian Approach to Speech Recognition," NIPS15 MIT Press, (2002).
  47. Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura, and Naonori Ueda, "Constructing Shared-State Hidden Markov Models Based on a Bayesian Approach," Proc. ICSLP'02, vol. 4, pp. 2669--2672, (2002).

 

BACK