- 追加された行はこの色です。
- 削除された行はこの色です。
* PUBLICATIONS - 2012 [#n782a49e]
#contents
** Journal [#da90e548]
+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, no.7, pp.857-866, 2012. (Full paper peer reviewed)
+Akira Tamamori, Yoshihiko Nankuaku, and Keiichi Tokuda, “An extension of separable lattice 2-D HMMs for rotational data variations," IEICE Transactions on Information and
Systems, vol.E95-D, no.8, pp.2074-2083, 2012. (Full paper peer reviewed)
+Keiichiro Oura, Junichi Yamagishi, MirjamWester, Simon King, and Keiichi Tokuda, “Analysis
of unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using
KLD-based transform mapping," Speech Communication, vol.54, no.6, pp.703-714, 2012. (Full paper peer reviewed)
+徳田恵一，大浦圭一郎， “自動学習により人間のように歌う音声合成システム－Sinsy－," 2012
Information Processing Society of Japan, vol.2012-MUS-94, no.1, pp.1-6,
2012 (招待講演). (Full paper peer reviewed)
+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, no. 7, pp. 857-866, September, 2012. (Full paper peer reviewed)
&publication(2012/20120801_Journal_SCommunication_Kei_Hashimoto_paper.pdf, paper);
[[link>http://www.sciencedirect.com/science/article/pii/S0167639312000283]]
[[link>https://nitech.repo.nii.ac.jp/?action=pages_view_main&active_action=repository_view_main_item_detail&item_id=5693&item_no=1&page_id=13&block_id=21]]
+Akira Tamamori, Yoshihiko Nankuaku, and Keiichi Tokuda, ``An extension of separable lattice 2-D HMMs for rotational data variations,'' IEICE Transactions on Information and Systems, vol. E95-D, no. 8, pp. 2074-2083, August, 2012. (Full paper peer reviewed)
&publication(2012/20120801_Journal_IEICE_Akira_Tamamori_paper.pdf, paper);
[[link>http://search.ieice.org/bin/summary.php?id=e95-d_8_2074&category=D&year=2012&lang=E]]
[[link>https://nitech.repo.nii.ac.jp/?action=pages_view_main&active_action=repository_view_main_item_detail&item_id=5682&item_no=1&page_id=13&block_id=21]]
+Keiichiro Oura, Junichi Yamagishi, MirjamWester, Simon King, and Keiichi Tokuda, ``Analysis of unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using KLD-based transform mapping,'' Speech Communication, vol. 54, no. 6, pp. 703-714, July, 2012. (Full paper peer reviewed)
&publication(2012/20120801_Journal_SCommunication_Keiichiro_Oura_paper.pdf, paper);
[[link>http://www.sciencedirect.com/science/article/pii/S0167639311001774]]
[[link>https://nitech.repo.nii.ac.jp/?action=pages_view_main&active_action=repository_view_main_item_detail&item_id=5665&item_no=1&page_id=13&block_id=21]]
** International Conference [#vb6f4953]
+%%%Shinji Takaki%%%, Kei Sawada, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda, ``Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2012'' Blizzard Challenge 2012 Workshop, Portland, USA, September, 2012 (web proceedings).
&publication(2012/20120914_IConference_Blizzard_Shinji_Takagi_paper.pdf, paper);
&publication(2012/20120914_IConference_Blizzard_Shinji_Takagi_slide.ppt, slide);
[[link>http://www.festvox.org/blizzard/blizzard2012.html]]
[[link>https://nitech.repo.nii.ac.jp/?action=pages_view_main&active_action=repository_view_main_item_detail&item_id=4667&item_no=1&page_id=13&block_id=21]]
+%%%Takafumi Hattori%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``A Bayesian approach to speaker recognition based on GMMs using multiple model structures,'' Interspeech 2012, pp. 1107-1110, Portland, USA, September, 2012. (Full paper peer reviewed)
&publication(2012/20120909_IConference_Interspeech_Takafumi_Hattori_paper.pdf, paper);
&publication(2012/20120909_IConference_Interspeech_Takafumi_Hattori_slide.pptx, slide);
[[link>http://www.isca-speech.org/archive/interspeech_2012/i12_1107.html]]
+%%%Viviane de Franca Oliveira%%%, Sayaka Shiota, Yoshihiko Nankaku, and Keiichi Tokuda, ``Cross-lingual speaker adaptation for HMM-based speech synthesis based on perceptual characteristics and spaker interpolation,'' Interspeech 2012, pp. 983-986, Portland, USA, September, 2012. (Full paper peer reviewed)
&publication(2012/20120909_IConference_Interspeech_Viviane_de_Franca_Oliveira_paper.pdf, paper);
&publication(2012/20120909_IConference_Interspeech_Viviane_de_Franca_Oliveira_poster.pdf, poster);
[[link>http://www.isca-speech.org/archive/interspeech_2012/i12_0983.html]]
+%%%Keiichiro Oura%%%, Ayami Mase, Yoshihiko Nankaku, and Keiichi Tokuda, ``Pitch adaptive training for HMM-based singing voice synthesis,'' 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp. 5377-5380, Kyoto, Japan, March, 2012. (Full paper peer reviewed)
&publication(2012/20120325_IConference_ICASSP_Keiichiro_Oura_paper.pdf, paper);
+%%%Sayaka Shiota%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``A model structure integration based on a Byesian framework for speech recognition,'' 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp. 4813-4816, Kyoto, Japan, March, 2012. (Full paper peer reviewed)
&publication(2012/20120325_IConference_ICASSP_Sayaka_Shiota_paper.pdf, paper);
&publication(2012/20120325_IConference_ICASSP_Sayaka_Shiota_poster.pdf, poster);
+%%%Keisuke Kumaki%%%, Yoshihiko Nankaku, and Keiichi Tokuda, ``Face recognition based on separable lattice 2-D HMMs using variational Bayesian method,'' 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp. 2209-2212, Kyoto, Japan, March, 2012. (Full paper peer reviewed)
&publication(2012/20120325_IConference_ICASSP_Keisuke_Kumaki_paper.pdf, paper);
&publication(2012/20120325_IConference_ICASSP_Keisuke_Kumaki_poster.pdf, poster);
+%%%Kei Sawada%%%, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Face recognition based on separable lattice 2-D HMMs using variational Bayesian method,'' 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp. 2205-2208, Kyoto, Japan, March, 2012. (Full paper peer reviewed)
&publication(2012/20120325_IConference_ICASSP_Kei_Sawada_paper.pdf, paper);
&publication(2012/20120325_IConference_ICASSP_Kei_Sawada_poster.pdf, poster);
+%%%Shinji Takaki%%%, Kei Sawada, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda, ``Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2012'' Blizzard Challenge 2012 Workshop, Portland, USA, 2012 (web proceedings).
+%%%Takafumi Hattori%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``A Bayesian approach to speaker recognition based on GMMs using multiple model structures,'' Interspeech 2012, pp. 1107-1110, Portland, USA, 2012. (Full paper peer reviewed)
+%%%Viviane de Franca Oliveira%%%, Sayaka Shiota, Yoshihiko Nankaku, and Keiichi Tokuda, ``Cross-lingual speaker adaptation for HMM-based speech synthesis based on perceptual characteristics and spaker interpolation,'' Interspeech 2012, pp. 983-986, Portland, USA, 2012. (Full paper peer reviewed)
+%%%Keiichiro Oura%%%, Ayami Mase, Yoshihiko Nankaku, and Keiichi Tokuda, ``Pitch adaptive training for HMM-based singing voice synthesis,'' 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp. 5377-5380, Kyoto, Japan, 2012. (Full paper peer reviewed)
+%%%Sayaka Shiota%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``A model structure integration based on a Byesian framework for speech recognition,'' 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp. 4813-4816, Kyoto, Japan, 2012. (Full paper peer reviewed)
+%%%Keisuke Kumaki%%%, Yoshihiko Nankaku, and Keiichi Tokuda, ``Face recognition based on separable lattice 2-D HMMs using variational Bayesian method,'' 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp. 2209-2212, Kyoto, Japan, 2012. (Full paper peer reviewed)
+%%%Kei Sawada%%%, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Face recognition based on separable lattice 2-D HMMs using variational Bayesian method,'' 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp. 2205-2208, Kyoto, Japan, 2012. (Full paper peer reviewed)
** Workshop [#m11f486e]
+%%%平野隆司%%%, 加藤杏樹, 南角吉彦, 李晃伸, 徳田恵一, ``登録キーワードと汎用言語モデルを用いた音声認識部・応答選択部の密結合に基づく統計的音声対話システム,'' 音声言語情報処理研究会(SIG-SLP), vol. 2012-SLP-92, no. 3, pp. 1-6, 山形, 日本, 2012.
//%%%Ryuji HIrano%%%, Anjyu Kato, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, ``A statistical spoken dialogue system based on tight integration of speech recognition and response selection using registered keywords and general language models,'' SIG-SLP, vol. 2012-SLP-92, no. 3, pp. 1-6, Yamagata, Japan, 2012.
+%%%津崎実%%%, 徳田恵一, 河井恒, 志賀芳則, 倪晋富, 大浦圭一郎, 塩田さやか, ``個人性を考慮した異言語音声合成に対する知覚評価,'' 日本音響学会聴覚研究会資料, vol. 112, no. 81, SP2012-39, pp. 33-38, 神奈川, 日本, 2012.
//%%%Minoru Tsuzaki%%%, Keiichi Tokuda, Hisashi Kawai, Yoshinori Shiga, Jinfu Ni, Keiichiro Oura, and Sayaka Shiota, ``Perceptual evaluation of synthesized speech reflecting "personalities",'' IEICE Technical Report, vol. 112, no. 81, SP2012-39, pp. 33-38, Kanagawa, Japan, 2012.
+%%%徳田恵一%%%, 大浦圭一郎, ``自動学習により人間のように歌う音声合成システム-Sinsy-,'' 第94回情報処理学会音楽情報科学研究会(SIGMUS), vol. 2012-MUS-94, no. 1, pp. 1-6, 静岡, 日本, 2012 (招待講演).
//%%%Keiichi Tokuda%%%, Keiichiro Oura, ``-Sinsy- human-like singing system based on automatic learning,'' SIGMUS, vol. 2012-MUS-94, no. 1, pp. 1-6, Shizuoka, Japan, 2012.
+%%%大浦圭一郎%%%, 間瀬絢美, 南角吉彦, 徳田恵一, ``HMM歌声合成における音高正規化学習の検討,'' 第94回情報処理学会音楽情報科学研究会(SIGMUS), vol. 2012-MUS-94, no. 1, pp. 1-6, 静岡, 日本, 2012.
//%%%Keiichiro Oura%%%, Mase Ayami, Yoshihiko Nankaku, and Keiichi Tokuda, ``HMM-based synthesis of singing voices using pitch adaptive training,'' SIGMUS, vol. 2012-MUS-94, no. 1, pp. 1-6, Shizuoka, Japan, 2012.
+%%%才野慶二郎%%%, 大浦圭一郎, 橘誠, 剣持秀紀, 徳田恵一, ``ラップスタイル歌声合成の検討,'' 第94回情報処理学会音楽情報科学研究会(SIGMUS), vol. 2012-MUS-94, no. 7, pp. 1-6, 静岡, 日本, 2012.
//%%%Keijiro Saino%%%, keiichiro Oura, Tachibana Makoto, Hideki Kenmochi, and Keiichi Tokuda, ``Rap-style Singing Voice Synthesis,'' SIGMUS, vol. 2012-MUS-94, no. 7, pp. 1-6, Shizuoka, Japan, 2012.
** National Convention [#lc2ab40e]
+ %%%高木信二%%%, 南角吉彦, 徳田恵一, ``HMM音声合成のための加算モデル構造に基づく複数話者同時モデリングの検討,'' 日本音響学会2012年秋季研究発表会, pp. 281-282, 長野, 日本, 2012.
//%%%Shinji Takaki%%%, Yoshihiko Nankaku, and Keiichi Tokuda, ``Multiple speaker modeling based on the additive structure for HMM-based speech synthesis,'' Acoustical Society of Japan 2012 Autumn Meeting , pp. 281-282, Nagano, Japan, 2012.
+ %%%大浦圭一郎%%%, 南角吉彦, 徳田恵一, ``HMM歌声合成における状態数可変のモデル構造の検討,'' 日本音響学会2012年秋季研究発表会, pp. 275-276, 長野, 日本, 2012.
//%%%Keiichiro Oura%%%, Yoshihiko Nankaku, and Keiichi Tokuda, ``Model structure of variable number of states for HMM-based siniging voice synthesis,'' Acoustical Society of Japan 2012 Autumn Meeting , pp. 275-276, Nagano, Japan, 2012
+ %%%真野翔平%%%, 南角吉彦, 徳田恵一, ``隠れ条件付確率場を用いた音声認識のためのアニーリングに基づく学習アルゴリズムの検討,'' 日本音響学会2012年秋季研究発表会, pp. 79-80, 長野, 日本, 2012.
//%%%Shohei Mano%%%, Yoshihiko Nankaku, and Keiichi Tokuda, ``A training algorithm of hidden conditional random fields based on deterministic annealing process forspeech recognition'', Acoustical Society of Japan 2012 Autumn Meeting , pp. 79-80, Nagano, Japan, 2012
+ %%%服部貴文%%%, 橋本佳, 南角吉彦, 徳田恵一, ``複数のモデル構造を用いた変分ベイズ法に基づく話者認識,'' 日本音響学会2012年秋季研究発表会, pp. 39-40, 長野, 日本, 2012.
//%%%Takafumi Hattori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``A bayesian approach to speaker recognition based on GMMs using multiple model structures'', Acoustical Society of Japan 2012 Autumn Meeting , pp. 39-40, Nagano, Japan, 2012
+ %%%Viviane de Franca Oliveira%%%, 塩田さやか, 南角吉彦, 徳田恵一, ``Cross-lingual speaker adaptation for HMM-based speech synthesis using speaker interpolation based on perceptual chracteristics,'' 日本音響学会2012年春季研究発表会, pp. 405-406, 神奈川, 日本, 2012.
//%%%Viviane de Franca Oliveira%%%, Sayaka Shiota, Yoshihiko Nankaku, and Keiichi Tokuda, ``Cross-lingual speaker adaptation for HMM-based speech synthesis using speaker interpolation based on perceptual chracteristics,'' Acoustical Society of Japan 2012 Spring Meeting , pp. 405-406, Kanagawa, Japan, 2012.
+ %%%橋本佳%%%, 山岸順一, Peter Bell, Simon King, Steve Renals, 南角吉彦, 徳田恵一, ``HMM音声合成における変分ベイズ法に基づく線形回帰,'' 日本音響学会2012年春季研究発表会, pp. 403-404, 神奈川, 日本, 2012.
//%%%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,'' Acoustical Society of Japan 2012 Spring Meeting , pp. 403-404, Kanagawa, Japan, 2012.
+ %%%高木信二%%%, 南角吉彦, 徳田恵一, ``コンテキストの部分的な加算構造に基づくHMM音声合成,'' 日本音響学会2012年春季研究発表会, pp. 303-304, 神奈川, 日本, 2012.
//%%%Shinji Takaki%%%, Yoshihiko Nankaku, and Keiichi Tokuda, ``HMM-based speech synthesis with contextual partial additive structure,'' Acoustical Society of Japan 2012 Spring Meeting , pp. 303-304, Kanagawa, Japan, 2012.
+ %%%沢田慶%%%, 玉森聡, 橋本佳, 南角吉彦, 徳田恵一, ``変分ベイズ法を用いた分離型2次元格子HMMの学習におけるアニーリング制御の適用,'' 情報処理学会第74回全国大会, pp. 409-410, 愛知, 日本, 2012.
//%%%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,'' 2012 Infomation Processing Society of Japan (IPSJ), pp. 409-410, Aichi, Japan, 2012.
** Master's and Bachelor's Theses [#o55d521e]
** Past Publications [#d97906db]
#ls2(HOME/PUBLICATIONS/,reverse);
