Lists of Publications

English | Japanese


TOP





Journal Paper
  1. Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, " A Bayesian approach 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)]
  2. 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. [paper(link)]
  3. 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. [paper(link)]
  4. 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. [paper(link)]
  5. Kei Hashimotou, 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. [paper(link)]


International Conference
  1. 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," in Proc. ICASSP 2013, pp.3203--3207, September 2012.
  2. Kazuhiro Nakamura, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Integration of acoustic modeling and mel-cepstral analysis for HMM-based speech synthesis," in Proc. ICASSP 2013, pp.7883--7887, September 2012.
  3. Shinji Takaki, Kei Sawada, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda, "Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2012," in Proc. Blizzard Challenge 2012, September 2012.
  4. Takafumi Hattori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "A Bayesian approach to speaker recognition based on GMMs using multiple model structures," in Proc. Interspeech 2012, September 2012.
  5. Kei Sawada, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Face recognition based on separable lattice 2-D HMMs using variational Bayesian method," in Proc. ICASSP 2012, pp.2205--2208, March 2012.
  6. Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "A model structure integration based on Bayesian framework for speech recognition," in Proc. ICASSP 2012, pp.4813--4816, March 2012.
  7. Kei Hashimoto, Shinji Takaki, Keiichiro Oura, and Keiichi Tokuda, "Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2011," in Proc. Blizzard Challenge 2011, September 2011. [paper.pdf] [slide.ppt]
  8. Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Multi-speaker modeling with shared prior distributions and model structures for Bayesian speech synthesis," in Proc. Interspeech 2011, pp.113--116, August 2011. [paper.pdf] [slide.ppt]
  9. 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," in Proc. ICASSP 2011, pp.5108--5111, May 2011. [paper.pdf] [poster.pdf]
  10. Keiichiro Oura, Kei Hashimoto, Sayaka Shiota, and Keiichi Tokuda, "Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2010," in Proc. Blizzard Challenge 2010, September 2010. [paper.pdf]
  11. Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Bayesian speech synthesis framework integrating training and synthesis processes," in Proc. SSW7, pp.106--111, September 2010. [paper.pdf] [slide.ppt]
  12. Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "A Bayesian approach to hidden semi Markov model based speech synthesis," in Proc. Interspeech 2009, pp.1751--1754, September 2009. (Student Paper Award Finalist) [paper.pdf] [poster.pdf]
  13. Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Deterministic annealing based training algorithm for Bayesian speech recognition," in Proc. Interspeech 2009, pp.680--683, September 2009.
  14. Kei Hashimoto, Hirohumi Yamamoto, Hideo Okuma, Eiichiro Sumita, and Keiichi Tokuda, "Reordering model using syntactic information of a source tree for statistical machine translation," in Proc. NAACL-HLT 2009 Workshop SSST-3, pp.69--77, June 2009. [paper.pdf] [slide.ppt]
  15. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Takashi Masuko, and Keiichi Tokuda, "A Bayesian approach to HMM-based speech synthesis," in Proc. ICASSP 2009, pp.4029--4032, April 2009. [paper.pdf] [slide.ppt]
  16. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Bayesian context clustering using cross valid prior distribution for HMM-based speech recognition," in Proc. Interspeech, pp.936--939, September 2008. [paper.pdf] [poster.pdf]
  17. Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Acoustic modeling based on model structure annealing for speech recognition," in Proc. Interspeech, pp.932--935, September 2008.
  18. Tatsuya Ito, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Speaker recognition based on variational Bayesian method," in Proc. Interspeech, pp.1417--1420, September 2008.
  19. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Hyperparameter estimation for speech recognition based on variational Bayesian approach," in Proc. ASA & ASJ Joint Meeting, 1pSC32, p.3042, USA, Honolulu, December 2006. [poster.ppt]


Technical Report
  1. 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," PRMU2013, Technical Report of IEICE, vol.112, no.441, pp.149--154, February 2013.
  2. Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Image recognition based on hidden Markov eigen-image models with the variational Bayesian method," PRMU2013, Technical Report of IEICE, vol.112, no.441, pp.155--160, February 2013.
  3. Kei Sawada, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Face recognition based on separable lattice 2-D HMMs with variational Bayesian method," PRMU2011, Technical Report of IEICE, vol.111, no.317, pp.125--130, November 2011.
  4. Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Bayesian speech recognition based on model structure integration," SP2011, Technical Report of IEICE, vol.111, no.97, pp.11--16, June 2011. (IEICE ISS Young Researcher's Award in Speech Field)
  5. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, and Keiichi Tokuda, "Bayesian context clustering using cross validation for HMM-based speech synthesis," SLP2008, Technical Report of IEICE, vol.108, no.338, pp.73--78, December 2008. [paper.pdf] [slide.ppt]
  6. Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Speech recognition based on statistical models including multiple decision trees," SLP2008, Technical Report of IEICE, vol.108, no.338, pp.221--226, December 2008.
  7. Tatsuya Ito, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Speaker recognition based on Gaussian mixture models using variational Bayesian method," SLP2008, Technical Report of IEICE, vol.108, no.338, pp.185--190, December 2008.
  8. 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, July 2007.


Domestic Conference
  1. Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, "Cross-lingual speaker adaptation based on factor analysis using bilingual speech data," in Proc. ASJ2013 spring meeting, pp.267--268, March 2013.
  2. 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," in Proc. ASJ2013 spring meeting, pp.269--270, March 2013.
  3. Kazuhiro Nakamura, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Integration of acoustic modeling and mel-cepstral analysis for HMM-based speech synthesis," in Proc. ASJ2013 spring meeting, pp.289--290, March 2013.
  4. Shuichi Kuwako, Shinji Takaki, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Utterance adaptive training in factor analyzed acoustic models for HMM-based speech synthesis," in Proc. ASJ2013 spring meeting, pp.291--292, March 2013.
  5. 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," in Proc. ASJ2013 spring meeting, pp.337--338, March 2013.
  6. Takafumi Hattori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "A Bayesian approach to speaker recognition based on GMMs using multiple model structures," in Proc. ASJ2012 autumn meeting, pp.39--40, September 2012.
  7. 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," in Proc. ASJ2012 spring meeting, pp.403--404, March 2012. [paper.pdf] [slide.ppt]
  8. 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, March 2012.
  9. Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Bayesian speech synthesis sharing prior distributions and model structures among multiple speakers," in Proc. ASJ2011 autumn meeting, pp.345--348, September 2011. [paper.pdf] [slide.ppt]
  10. 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," in Proc. ASJ2011 spring meeting, pp.315--316, March 2011. [paper.pdf] [slide.ppt]
  11. Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Acoustic modeling based model structure annealing for Bayesian speech recognition," in Proc. ASJ2011 spring meeting, pp.21--24, March 2011. (Student Paper Award)
  12. Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Bayesian speech synthesis integrating training and synthesis processes," in Proc. ASJ2010 autumn meeting, pp.243--244, September 2010. [paper.pdf] [slide.ppt]
  13. Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Evaluation of HSMM-based speech synthesis based on Bayesian framework," in Proc. ASJ2009 autumn meeting, pp.257--258, September 2009. [paper.pdf] [slide.ppt]
  14. Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Training algorithm based on deterministic annealing for Bayesian speech recognition," in Proc. ASJ2009 autumn meeting, pp.3--6, September 2009.
  15. Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "Hidden semi-Markov model based Bayesian speech synthesis," in Proc. ASJ2009 spring meeting, pp.303--304, March 2009. [paper.pdf] [slide.ppt]
  16. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "HMM based speech synthesis using cross validation for Bayesian criterion," in Proc. ASJ2008 autumn meeting, pp.251--252, September 2008. [paper.pdf] [slide.ppt]
  17. Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Speech recognition based on multiple phonetic decision tree structures," in Proc. ASJ2008 autumn meeting, pp.125--126, September 2008.
  18. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Context clustering using cross validation based on Bayesian criterion," in Proc. ASJ2008 spring meeting, pp.69--70, March 2008. [paper.pdf] [slide.ppt]
  19. Tatsuya Ito, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Speaker recognition based on variational Bayesian method," in Proc. ASJ2008 spring meeting, pp.143--144, March 2008.
  20. Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Hyper-parameter tying structure for speech recognition based on variational Bayesian method," in Proc. ASJ2007 autumn, pp.139--142, September 2007. [paper.pdf] [slide.ppt]
  21. Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, "Acoustic modeling based on model structure annealing for speech recognition," in Proc. ASJ2007 autumn meeting, pp.143--146, September 2007.


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


Talk
  1. Kei Hashimotoกค "Bayesian speech synthesis" , Kyoto University, Media Archiving Laboratory (Prof. Kawahara Lab.), 11 June 2012. (in Japanese)