Lists of Publications

English | Japanese


TOP





Journal Paper
  1. Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Constructing text-to-speech systems for languages with unknown pronunciations," Acoustical Science and Technology. (Accepted)
  2. Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Simultaneous optimization of multiple tree-based factor analyzed HMM for speech synthesis," IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 25, Issue 9, pp. 1532-1541, September, 2017. (DOI: 10.1109/TASLP.2017.2721219) [paper(link)]
  3. Kei Hashimoto and Shinji Takaki, "Statistical parametric speech synthesis based on deep learning," The journal of the acoustical society of Japan, vol. 73, no. 1, pp. 55-62, January, 2017. (in Japanese) (Review paper)
  4. Kei Sawada, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "A Bayesian approach to image recognition based on separable lattice hidden Markov models," IEICE TRANSACTIONS on Information & Systems, vol. E99-D, no. 12, pp. 3119-3131, December, 2016. (DOI: 10.1587/transinf.2016EDP7112) [paper(link)]
  5. Kazuhiro Nakamura, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Integration of spectral feature extraction and modeling for HMM-based speech synthesis," IEICE TRANSACTIONS on Information & Systems, vol. E97-D, no. 6, pp. 1438-1448, June, 2014. (DOI: 10.1587/transinf.E97.D.1438) [paper(link)]
  6. Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "A Bayesian framework using multiple model structures for speech recognition," IEICE TRANSACTIONS on Information & Systems, vol. E96-D, no. 4, pp. 939-948, April, 2013. (DOI: 10.1587/transinf.E96.D.939) [paper(link)]
  7. Kei Hashimoto, Junichi Yamagishi, William Byrne, Simon King, and Keiichi Tokuda, "Impacts of machine translation and speech synthesis on speech-to-speech translation," Speech Communication, vol. 54, Issue 7, pp. 854-866, September, 2012. (DOI: 10.1016/j.specom.2012.02.004) [paper(link)]
  8. Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Speech recognition based on statistical models including multiple phonetic decision trees," Acoustical Science and Technology, vol. 32, no. 6, pp. 236-243, November, 2011. (DOI: 10.1250/ast.32.236) [paper(link)]
  9. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Bayesian context clustering using cross validation for speech recognition," IEICE TRANSACTIONS on Information & Systems, vol. E94-D, no. 3, pp. 668-678, March, 2011. (DOI: 10.1587/transinf.E94.D.668) [paper(link)]
  10. Kei Hashimoto, Hirohumi Yamamoto, Hideo Okuma, Eiichiro Sumita, and Keiichi Tokuda, "A reordering model using a source-side parse-tree for statistical machine translation," IEICE TRANSACTIONS on Information & Systems, vol. E92-D, no. 12, pp. 2386-2393, December, 2009. (DOI: 10.1587/transinf.E92.D.2386) [paper(link)]


International Conference
  1. Kei Sawada, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda, "The NITech text-to-speech system for the Blizzard Challenge 2017," Proceedings of Blizzard Challenge 2017 Workshop, Stockholm, Sweden, August 25, 2017. (web proceedings)
  2. Amelia Gully, Takenori Yoshimura, Damian Murphy, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Articulatory text-to-speech synthesis using the digital waveguide mesh driven by a deep neural network," Proceedings of Interspeech 2017, pp. 234-238, Stockholm, Sweden, August 20--24, 2017.
  3. Yoshinari Tsuzuki, Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Image recognition based on discriminative models using features generated from separable lattice HMMs," Proceedings of 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2017), pp. 2607-2611, New Orleans, USA, March 5-9, 2017.
  4. Kei Sawada, Chiaki Asai, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda, "The NITech text-to-speech system for the Blizzard Challenge 2016," Proceedings of Blizzard Challenge 2016 Workshop, California, USA, September 16, 2016. (web proceedings)
  5. Keiichi Tokuda, Kei Hashimoto, Keiichiro Oura, and Yoshihiko Nankaku, "Temporal modeling in neural network based statistical parametric speech synthesis," Proceedings of 9th ISCA Speech Synthesis Workshop (SSW9), pp. 113-118, California, USA, September 13--15, 2016.
  6. Rasmus Dall, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Redefining the linguistic context feature set for HMM and DNN TTS through position and parsing," Proceedings of Interspeech 2016, pp. 2851-2855, California, USA, September 8--12, 2016.
  7. Masanari Nishimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Singing voice synthesis based on deep neural networks," Proceedings of Interspeech 2016, pp. 2478-2482, California, USA, September 8--12, 2016.
  8. Naoki Hosaka, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Voice conversion based on trajectory model training of neural networks considering global variance," Proceedings of Interspeech 2016, pp. 307-311, California, USA, September 8--12, 2016.
  9. Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Trajectory training considering global variance for speech synthesis based on neural networks," Proceedings of 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2016), pp. 5600-5604, Shanghai, China, March 20-25, 2016.
  10. Kei Hashimoto, Junichi Yamagishi, and Isao Echizen, "Privacy-preserving sound to degrade automatic speaker verification performance," Proceedings of 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2016), pp. 5500-5504, Shanghai, China, March 20-25, 2016.
  11. Kei Sawada, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda, "The NITECH HMM-based text-to-speech system for the Blizzard Challenge 2015," Proceedings of Blizzard Challenge 2015 Workshop, Berlin, Germany, September 11, 2015. (web proceedings)
  12. Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Simultaneous optimization of multiple tree structures for factor analyzed HMM-based speech synthesis," Proceedings of Interspeech 2015, pp. 1196-1200, Dresden, Germany, September 6-10, 2015.
  13. Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "The effect of neural networks in statistical parametric speech synthesis," Proceedings of 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2015), pp. 4455-4459, Brisbane, Australia, April 19-24, 2015.
  14. Kei Sawada, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda, "Overview of NITECH HMM-based text-to-speech system for Blizzard Challenge 2014," Proceedings of Blizzard Challenge 2014 Workshop, Singapore, September 19, 2014. (web proceedings)
  15. Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "A mel-cepstral analysis technique restoring high frequency components from low-sampling-rate speech," Proceedings of Interspeech 2014, pp. 2494-2498, Singapore, September 14-18, 2014.
  16. Kanako Shirota, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Integration of speaker and pitch adaptive training for HMM-based singing voice synthesis," Proceedings of 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2014), pp. 2578-2582, Florence, Italy, May 4-9, 2014.
  17. Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Image recognition based on hidden Markov eigen-image models using variational Bayesian method," Proceedings of Asia-Pacific Signal ans Information Processing Association Annual Summit and Conference 2013 (APSIPA ASC 2013), Kaohsiung, Taiwan, October 29-November 1, 2013.
  18. Shinji Takaki, Kei Sawada, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda, "Overview of NITECH HMM-based speech synthesis system for Blizzard Challenge 2013," Proceedings of Blizzard Challenge 2013 Workshop, Barcelona, Spain, September 3, 2013. (web proceedings)
  19. Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Cross-lingual speaker adaptation based on factor analysis using bilingual speech data for HMM-based speech synthesis," Proceedings of 8th ISCA Speech Synthesis Workshop (SSW8), pp. 317-322, Barcelona, Spain, August 31-September 2, 2013.
  20. Takaya Makino, Shinji Takaki, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Separable lattice 2-D HMMs introducing state duration control for recognition of images with various variations," Proceedings of 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013), pp. 3203-3207, Vancouver, Canada, May 26-31, 2013.
  21. Kazuhiro Nakamura, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Integration of acoustic modeling and mel-cepstral analysis for HMM-based speech synthesis," Proceedings of 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013), pp. 7883-7887, Vancouver, Canada, May 26-31, 2013.
  22. Shinji Takaki, Kei Sawada, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda, "Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2012," Proceedings of Blizzard Challenge 2012, Portland, Oregon, U.S.A., September 14, 2012. (web proceedings)
  23. Takafumi Hattori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "A Bayesian approach to speaker recognition based on GMMs using multiple model structures," Proceedings of Interspeech 2012, Portland, Oregon, U.S.A., September 9-13, 2012.
  24. Kei Sawada, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Face recognition based on separable lattice 2-D HMMs using variational Bayesian method," Proceedings of 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp. 2205-2208, Kyoto, Japan, March 25-30, 2012.
  25. Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "A model structure integration based on Bayesian framework for speech recognition," Proceedings of 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp. 4813-4816, Kyoto, Japan, March 25-30, 2012.
  26. Kei Hashimoto, Shinji Takaki, Keiichiro Oura, and Keiichi Tokuda, "Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2011," Proceedings of Blizzard Challenge 2011, Turin, Italy, September 2, 2011. (web proceedings)
  27. Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Multi-speaker modeling with shared prior distributions and model structures for Bayesian speech synthesis," Proceedings of Interspeech 2011, pp. 113-116, Florence, Italy, August 28-31, 2011.
  28. Kei Hashimoto, Junichi Yamagishi, William Byrne, Simon King, and Keiichi Tokuda, "An analysis of machine translation and speech synthesis in speech-to-speech translation system," Proceedings of 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2011), pp. 5108-5111, Prague, Czech Republic, May 22-27, 2011.
  29. Keiichiro Oura, Kei Hashimoto, Sayaka Shiota, and Keiichi Tokuda, "Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2010," Proceedings of Blizzard Challenge 2010, Kyoto, Japan, September 25, 2010.
  30. Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Bayesian speech synthesis framework integrating training and synthesis processes," Proceedings of 7th ISCA Speech Synthesis Workshop (SSW7), pp. 106-111, Kyoto, Japan, September 22-24, 2010.
  31. Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "A Bayesian approach to hidden semi Markov model based speech synthesis," Proceedings of Interspeech 2009, pp. 1751-1754, Brighton, United Kingdom, September 6-10, 2009. (Student Paper Award Finalist)
  32. Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Deterministic annealing based training algorithm for Bayesian speech recognition," Proceedings of Interspeech 2009, pp. 680-683, Brighton, United Kingdom, September 6-10, 2009.
  33. Kei Hashimoto, Hirohumi Yamamoto, Hideo Okuma, Eiichiro Sumita, and Keiichi Tokuda, "Reordering model using syntactic information of a source tree for statistical machine translation," Proceedings of the Third Workshop on Syntax and Structure in Statistical Translation (SSST-3) at North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT) 2009, pp. 69-77, Boulder, Colorado, U.S.A., June 5, 2009.
  34. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Takashi Masuko, and Keiichi Tokuda, "A Bayesian approach to HMM-based speech synthesis," Proceedings of 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009), pp. 4029-4032, Taipei, Taiwan, April 19-24, 2009.
  35. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Bayesian context clustering using cross valid prior distribution for HMM-based speech recognition," Proceedings of Interspeech 2008, pp. 936-939, Brisbane, Australia, September 22-26, 2008.
  36. Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Acoustic modeling based on model structure annealing for speech recognition," Proceedings of Interspeech 2008, pp. 932-935, Brisbane, Australia, September 22-26, 2008.
  37. Tatsuya Ito, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Speaker recognition based on variational Bayesian method," Proceedings of Interspeech 2008, pp. 1417-1420, Brisbane, Australia, September 22-26, 2008.
  38. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Hyperparameter estimation for speech recognition based on variational Bayesian approach," Proceedings of ASA & ASJ Joint Meeting, p. 3042, Honolulu, Hawaii, U.S.A., November 28-December 2, 2006.


Technical Report
  1. 浅見太一, 大谷大和, 岡本拓磨, 小川哲司, 落合翼, 亀岡弘和, 駒谷和範, 高木信二, 高道慎之介, 俵直弘, 南條浩輝, 橋本佳, 福田 隆, 増村亮, 松田繁樹, 李晃伸, 渡部晋治 "国際会議ICASSP2017報告," IPSJ SIG Technical Report, vol. 2017-SLP-117, no. 3, pp. 1-8, 宮城, July 27-28, 2017.
  2. 浅見太一, 小川厚徳, 小川哲司, 大谷大和, 倉田岳人, 齋藤大輔, 塩田さやか, 篠原雄介, 鈴木雅之, 高道慎之介, 南條浩輝, 橋本佳, 樋口卓哉, 増村亮, 吉野幸一郎, 渡部晋治, "国際会議INTERSPEECH2016報告," IPSJ SIG Technical Report, vol. 2017-SLP-115, no. 7, pp. 1-7, Kagawa, February 17-18, 2017.
  3. Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Simultaneous modeling of acoustic feature sequences and its temporal structures for DNN-based speech synthesis," Technical Report of IEICE, vol. 116, no. 414, SP2016-76, pp. 71-76, Tokyo, January 21, 2017. (IEICE ISS Young Researcher's Award in Speech Field)
  4. Chiaki Asai, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Designing linguistic features for expressive speech synthesis using audiobooks," Technical Report of IEICE, vol. 116, no. 414, SP2016-70, pp. 35-40, Tokyo, January 21, 2017.
  5. Yoshinari Tsuzuki, Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Image recognition based on discriminative models using features extracted from separable lattice HMMs," Technical Report of IEICE, vol. 116, no. 89, PRMU2016-36, pp. 7-12, Tokyo, June 13-14, 2016.
  6. Masato Sukegawa, Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Parameter sharing structures of separable lattice HMMs using mixture output distributions for image recognition," Technical Report of IEICE, vol. 115, no. 456, PRMU2015-138, pp. 37-42, Fukuoka, February 21-22, 2016.
  7. Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Evaluation of text-to-speech system construction for unknown-pronunciation languages," Technical Report of IEICE, vol. 115, no. 346, SP2015-80, pp. 93-98, Aichi, December 2-3, 2015.
  8. Kei Hashimoto, Junichi Yamagishi, and Isao Echizen, "Investigation of privacy-preserving sounds to degrade automatic spaker verificationperformance," Technical Report of IEICE, vol. 115, no. 146, SP2015-49, pp. 79-84, Suwa, July 16-17, 2015.
  9. Takuma Okamoto, Tetsuji Ogawa, Tsubasa Ochiai, Yosuke Kashiwagi, Hirokazu Kameoka, Keisuke Kinoshita, Tomoki Koriyama, Daisuke Saito, Takahiro Shinozaki, Shinji Takaki, Tetsuya Takiguchi, Yuki Tachioka, Naohiro Tawara, Kei Hashimoto, Masakiyo Fujimoto, Shigeki Matsuda, Masato Mimura, Takuya Yoshioka, and Shinji Watanabe, "国際会議ICASSP2015参加報告", IPSJ SIG Technical Report, vol. 2015-SLP-107, no. 3, pp. 1-7, Suwa, July 16-17, 2015.
  10. Koji Mushika, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "A robust modeling technique against training data errors for HMM-based singing voice synthesis," IPSJ SIG Technical Report, vol. 2015-MUS-106, no. 13, pp. 1-6, Kofu, March 2-3, 2015.
  11. Akifumi Tsuge, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Speaker recognition based on log-linear models using feature generation by variational Bayesian method," Technical Report of IEICE, vol. 113, no. 404, pp. 13-18, Nagoya, January 23-24, 2014.
  12. Takaya Makino, Shinji Takaki, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Extended separable lattice HMMs with state duration control for recognition of images with variations," Technical Report of IEICE, vol. 112, no. 441, pp. 149-154, Osaka, February 21-22, 2013.
  13. Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Image recognition based on hidden Markov eigen-image models with the variational Bayesian method," Technical Report of IEICE, vol. 112, no. 441, pp. 155-160, Osaka, February 21-22, 2013.
  14. Kei Sawada, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Face recognition based on separable lattice 2-D HMMs with variational Bayesian method," Technical Report of IEICE, vol. 111, no. 317, pp. 125-130, Nagasaki, November 24-25, 2011.
  15. Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Bayesian speech recognition based on model structure integration," Technical Report of IEICE, vol. 111, no. 97, pp. 11-16, Nagoya, June 23-24, 2011. (IEICE ISS Young Researcher's Award in Speech Field)
  16. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, and Keiichi Tokuda, "Bayesian context clustering using cross validation for HMM-based speech synthesis," Technical Report of IEICE, vol. 107, no. 165, pp. 67-72, Tokyo, December 9-10, 2008.
  17. Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Speech recognition based on statistical models including multiple decision trees," Technical Report of IEICE, vol. 108, no. 338, pp. 221-226, Tokyo, December 9-10, 2008.
  18. Tatsuya Ito, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Speaker recognition based on Gaussian mixture models using variational Bayesian method," Technical Report of IEICE, vol. 108, no. 338, pp. 185-190, Tokyo, December 9-10, 2008.
  19. Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Acoustic modeling based on model structure annealing for speech recognition," Technical Report of IEICE, vol. 107, no. 165, pp. 67-72, Toyama, July 26-27, 2007.


Domestic Conference
  1. Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Overview of the NITech text-to-speech system for the Blizzard Challenge 2017," Proceedings of ASJ2017 autumn meeting, pp. 287-290, Ehime, September 25-27, 2017.
  2. Yukiya Hono, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda, Daisuke Kondo, and Daisuke Ichikawa "Singing voice conversion using post data in music SNS," Proceedings of ASJ2017 autumn meeting, pp. 209-210, Ehime, September 25-27, 2017.
  3. Jumpei Niwa, Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "WaveNet-based voice conversion," Proceedings of ASJ2017 autumn meeting, pp. 207-208, Ehime, September 25-27, 2017.
  4. Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Mel-cepstrum based quantization noise shaping applied for WaveNet," Proceedings of ASJ2017 autumn meeting, pp. 193-194, Ehime, September 25-27, 2017.
  5. Shiori Murase, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Investigation of conditions for acoustic feature extraction for speech synthesis based on deep neural networks," Proceedings of ASJ2017 spring meeting, pp. 263-264, Kanagawa, March 15-17, 2017.
  6. Yushi Ichikawa, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Voice conversion based on hybrid deep neural network - Gaussian mixture model," Proceedings of ASJ2017 spring meeting, pp. 233-234, Kanagawa, March 15-17, 2017. (Student Presentation Award)
  7. Kei Hashimoto, Junichi Yamagishi, and Isao Echizen, "Privacy-preserving sounds based on universal background models to degrade performance of automatic speaker verification systems," Proceedings of ASJ2016 spring meeting, pp. 131-132, Kanagawa, March 9-11, 2016.
  8. Keiichiro Oura, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Prior probability distribution based on musical score for HMM-based singing voice synthesis," Proceedings of ASJ2016 spring meeting, pp. 245-246, Kanagawa, March 9-11, 2016.
  9. Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "A design of voice recording software tool to effectively collect speech data based on crowdsourcing," Proceedings of ASJ2016 spring meeting, pp. 307-308, Kanagawa, March 9-11, 2016.
  10. Tatsuya Suzuki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Investigation of voice fundamental frequency estimation based on conditional random fields," Proceedings of ASJ2016 spring meeting, pp. 279-280, Kanagawa, March 9-11, 2016.
  11. Masanari Nishimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Investigation of singing voice synthesis based on deep neural networks," Proceedings of ASJ2016 spring meeting, pp. 213-214, Kanagawa, March 9-11, 2016.
  12. Naoki Hosaka, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Trajectory training considering global variance for voice conversion based on neural network," Proceedings of ASJ2016 spring meeting, pp. 239-240, Kanagawa, March 9-11, 2016.
  13. Kei Sawada, Kazuki Igami, Chiaki Asai, Yusuke Sato, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Automatic construction of training corpus using audiobooks for statistical parametric speech synthesis," Proceedings of ASJ2016 spring meeting, pp. 219-220, Kanagawa, March 9-11, 2016. (Student Presentation Award)
  14. Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Trajectory model training considering global variance for speech synthesis based on neural network," Proceedings of ASJ2015 autumn meeting, pp. 237-238, Fukushima, September 16-18, 2015.
  15. Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "A mel-cepstral analysis technique restoring missing high-frequency components of speech for HMM-based speech synthesis," Proceedings of ASJ2015 autumn meeting, pp. 233-234, Fukushima, September 16-18, 2015.
  16. Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Investigation of text-to-speech system construction in unknown-pronunciation language," Proceedings of ASJ2015 autumn meeting, pp. 231-232, Fukushima, September 16-18, 2015.
  17. Kei Hashimoto, Junichi Yamagishi, and Isao Echizen, "Investigation of privacy-preserving sounds to degrade performance of automatic speaker verification systems," Proceedings of ASJ2015 autumn meeting, pp. 27-28, Fukushima, September 16-18, 2015.
  18. Masaya Hashimoto, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Speaker recognition based on log linear models using multiple acoustic features," Proceedings of ASJ2015 autumn meeting, pp. 25-26, Fukushima, September 16-18, 2015.
  19. Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Investigation of neural network based speech synthesis using generative models," Proceedings of ASJ2014 autumn meeting, pp. 245-246, Hokkaido, September 3-5, 2014. (Awaya Prize Young Researcher Award)
  20. Takenori Yoshimura, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "A clustering technique for factor analyzed HMM-based speech synthesis," Proceedings of ASJ2014 autumn meeting, pp. 239-240, Hokkaido, September 3-5, 2014.
  21. Shota Kamiya, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Simultaneous high/low accent and acoustic model training for HMM-based speech synthesis," Proceedings of ASJ2014 autumn meeting, pp. 237-238, Hokkaido, September 3-5, 2014. (Student Presentation Award)
  22. Yusuke Sato, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Evaluation of a cross-lingual speaker adaptation technique using joint-eigenvoices with a perceptual characteristic space," Proceedings of ASJ2014 spring meeting, pp. 325-326, Tokyo, March 10-12, 2014.
  23. Koki Tsuruno, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "GMM-based voice conversion using a modified posterior probability function," Proceedings of ASJ2014 spring meeting, pp. 325-326, Tokyo, March 10-12, 2014.
  24. Koji Mushika, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "A robust acoustic modeling technique against training data errors in HMM-based singing voice synthesis," Proceedings of ASJ2014 spring meeting, pp. 335-336, Tokyo, March 10-12, 2014.
  25. Takashi Aritaka, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Comparing spectrum representation methods related to LSPs for HMM-based speech synthesis," Proceedings of ASJ2014 spring meeting, pp. 337-338, Tokyo, March 10-12, 2014.
  26. Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "A mel-cepstral analysis technique restoring missing high-frequency components from low-sampling-rate speech," Proceedings of ASJ2014 spring meeting, pp. 339-340, Tokyo, March 10-12, 2014. (Student Presentation Award)
  27. Keiichiro Oura, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "The use of state-level contexts in HMM-based speech synthesis," Proceedings of ASJ2014 spring meeting, pp. 341-342, Tokyo, March 10-12, 2014.
  28. Akifumi Tsuge, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Speaker recognition based on log-linear models using Bayesian statistics," Proceedings of ASJ2013 autumn meeting, pp. 73-74, Aichi, September 25-27, 2013.
  29. Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Cross-lingual speaker adaptation based on factor analysis using bilingual speech data," Proceedings of ASJ2013 spring meeting, pp. 267-268, Tokyo, March 13-15, 2013.
  30. Viviane de Franca Oliveira, Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Cross-lingual speaker adaptation for HMM-based speech synthesis using joint-eigenvoices with a space of perceptual characteristics," Proceedings of ASJ2013 spring meeting, pp. 269-270, Tokyo, March 13-15, 2013.
  31. Kazuhiro Nakamura, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Integration of acoustic modeling and mel-cepstral analysis for HMM-based speech synthesis," Proceedings of ASJ2013 spring meeting, pp. 289-290, Tokyo, March 13-15, 2013.
  32. Shuichi Kuwako, Shinji Takaki, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Utterance adaptive training in factor analyzed acoustic models for HMM-based speech synthesis," Proceedings of ASJ2013 spring meeting, pp. 291-292, Tokyo, March 13-15, 2013.
  33. Shoto Kitamura, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Automatic correction of tuneless singing using pitch adaptive training for HMM-based singing voice synthesis," Proceedings of ASJ2013 spring meeting, pp. 337-338, Tokyo, March 13-15, 2013.
  34. Takafumi Hattori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "A Bayesian approach to speaker recognition based on GMMs using multiple model structures," Proceedings of ASJ2012 autumn meeting, pp. 39-40, Nagano, September 19-21, 2012.
  35. Kei Hashimoto, Junichi Yamagishi, Peter Bell, Simon King, Steve Renals, and Keiichi Tokuda, "Linear regression based on the variational Bayesian method for HMM-based speech synthesis," Proceedings of ASJ2012 spring meeting, pp. 403-404, Kanagawa, March 13-15, 2012.
  36. Kei Sawada, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "A training algorithm based on variational Bayesian method using deterministic annealing process for separable lattice 2-D HMMs," The 74th National Convention of IPSJ, pp. 409-410, Kanagawa, March 13-15, 2012.
  37. Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Bayesian speech synthesis sharing prior distributions and model structures among multiple speakers," Proceedings of ASJ2011 autumn meeting, pp. 345-348, Shimane, September 20-22, 2011.
  38. Kei Hashimoto, Junichi Yamagishi, William Byrne, Simon King, and Keiichi Tokuda, "An evaluation and analysis of machine translation and speech synthesis in speech-to-speech translation," Proceedings of ASJ2011 spring meeting, pp. 315-316, Tokyo, March 9-11, 2011.
  39. Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Acoustic modeling based model structure annealing for Bayesian speech recognition," Proceedings of ASJ2011 spring meeting, pp. 21-24, Tokyo, March 9-11, 2011. (Student Presentation Award)
  40. Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Bayesian speech synthesis integrating training and synthesis processes," Proceedings of ASJ2010 autumn meeting, pp. 243-244, Osaka, September 14-16, 2010.
  41. Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Evaluation of HSMM-based speech synthesis based on Bayesian framework," Proceedings of ASJ2009 autumn meeting, pp. 257-258, Fukushima, September 15-17, 2009.
  42. Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Training algorithm based on deterministic annealing for Bayesian speech recognition," Proceedings of ASJ2009 autumn meeting, pp. 3-6, Fukushima, September 15-17, 2009.
  43. Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Hidden semi-Markov model based Bayesian speech synthesis," Proceedings of ASJ2009 spring meeting, pp. 303-304, Tokyo, March 17-19, 2009.
  44. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "HMM based speech synthesis using cross validation for Bayesian criterion," Proceedings of ASJ2008 autumn meeting, pp. 251-252, Nagano, September 10-12, 2008.
  45. Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Speech recognition based on multiple phonetic decision tree structures," Proceedings of ASJ2008 autumn meeting, pp. 125-126, Nagano, September 10-12, 2008.
  46. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Context clustering using cross validation based on Bayesian criterion," Proceedings of ASJ2008 spring meeting, pp. 69-70, Chiba, March 17-19, 2008.
  47. Tatsuya Ito, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Speaker recognition based on variational Bayesian method," Proceedings of ASJ2008 spring meeting, pp. 143-144, Chiba, March 17-19, 2008.
  48. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Hyper-parameter tying structure for speech recognition based on variational Bayesian method," Proceedings of ASJ2007 autumn, pp. 139-142, Yamanashi, September 19-21, 2007.
  49. Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Acoustic modeling based on model structure annealing for speech recognition," Proceedings of ASJ2007 autumn meeting, pp. 143-146, Yamanashi, September 19-21, 2007.


Book
  1. 橋本佳(分担執筆), "人工知能学大辞典(音声合成(HMM 合成方式))," 人工知能学会編, 共立出版, pp. 785-787, 2017年7月7日. (ISBN:978-4-320-12420-2)
  2. Keiichi Tokuda, Akinobu Lee, Yoshihiko Nankaku, Keiichiro Oura, Kei Hashimoto, Daisuke Yamamoto, Ichi Takumi, Takahiro Uchiya, Shuhei Tsutsumi, Steve Renals, and Junichi Yamagishi(分担執筆), "User generated dialogue systems: uDialogue," Human Harmonized Information Technology, Volume 2, Springer, pp. 77-114, May, 2017. (ISBN:978-4-431-56533-8) (DOI: 10.1007/978-4-431-56535-2)
  3. 橋本佳(分担執筆), "音響学入門ペディア(Q34 統計的音声合成の仕組みを教えてください)," 日本音響学会編, コロナ社, pp. 136-139, 2017年3月15日. (ISBN:978-4-339-00895-1)


Thesis
  1. Kei Hashimoto, "Statistical models of machine translation, speech recognition, and speech synthesis for speech-to-speech translation," Doctoral Dissertation, February 2011.
  2. Kei Hashimoto, "Estimation of Prior Distribution for Speech Recognition Based on Bayesian criterion," Master Thesis, February 2008.
  3. Kei Hashimoto, "Investigation of Prior Distribution for Speech Recognition Based on Bayesian Criterion," Graduation Thesis, February 2006.


Talk
  1. 橋本佳, "音声合成における深層学習," 日本音響学会2017年秋季研究発表会ビギナーズセミナー, 愛媛, 2017年9月25日.