* 発表論文 - 2011 [#n782a49e]
#contents
** 論文誌 [#da90e548]
+%%%徳田恵一%%%, “コンテンツ生成の循環系を軸とした音声技術基盤の構築を目指して," 電子情報通信
学会技術研究報告（第13回音声言語シンポジウム）, vol.111, no.365, SP2011-95, pp.153-157, 2011 (招待講演).
+%%%Keiichi Tokuda%%%, “Speech synthesis as a statistical machine learning problem," IEEE 2011 Automatic Speech Recognition and Understanding (ASRU 2011), Hawaii, 2011 (invited talk). (without proceedings paper)
+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, 2011.(Full paper peer reviewed)
+Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, “Bayesian
context clustering using cross validation for speech recognition" IEICE Transactions on
Information and Systems, vol.E94-D, no.3, pp.668-678, 2011. (Full paper peer reviewed)
+徳田恵一, “統計的パラメトリック音声合成技術の動向," 日本音響学会誌, vol.67, no.1, pp.17-22 2011. (解説論文)
//Keiichi Tokuda, 〝Recent advances in statistical parametric speech synthesis”Acoustical Science and Technology,
vol.67, no.1, pp.17-22, January 2011. (Tutorial paper)
** 国際会議 [#vb6f4953]
+ %%%Kei Hashimoto%%%, Shinji Takaki, Keiichiro Oura, and Keiichi Tokuda, “Overview of NIT HMM based speech synthesis system for Blizzard Challenge 2011,” Blizzard Challenge 2011 Workshop, Turin, Italy, 2011 (web proceedings).
+ %%%Lei Li%%%, Yoshihiko Nankaku, and Keiichi Tokuda, “A Bayesian approach to voice conversion based on GMMs using multiple model structures,”Interspeech 2011, pp.661–664, Florence, Italy, 2011.(Full paper peer reviewed)
+ %%%Ling-Hui Chen%%%, Yoshihiko Nankaku, Heiga Zen, Keiichi Tokuda, Zhen-Hua Ling, and Li-Rong Dai, “Estimation of window coefficients for dynamic feature extraction for HMM-based speech synthesis,” Interspeech 2011,pp.1801–1804, Florence, Italy, 2011.(Full paper peer reviewed)
+ %%%Tsuneo Kato%%%, Makoto Yamada, Nobuyuki Nishizawa, Keiichiro Oura, and Keiichi Tokuda,“Large-scale subjective evaluations of speech rate control methods for HMM-based speech synthesizers,” Interspeech 2011, pp.1845–1848, Florence, Italy, 2011.(Full paper peer reviewed)
+ %%%Naoaki Ito%%%, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda,“Evaluation of tree-trellis based decoding in over-million LVCSR,” Interspeech 2011, pp.1937–1940, Florence, Italy, 2011.(Full paper peer reviewed)
+ %%%Ulpu Remes%%%, Yoshihiko Nankaku, and Keiichi Tokuda, “GMM-based missing-feature reconstruction on multi-frame windows,” Interspeech 2011, pp.1665–1668, Florence, Italy, 2011.(Full paper peer reviewed)
+ %%%Minoru Tsuzaki%%%, Keiichi Tokuda, Hisashi Kawai, and Jinfu Ni, “Estimation of perceptual spaces for speaker identities based on the cross-lingual discrimination task,” Interspeech 2011, pp.157–160, Florence, Italy, 2011. (Full paper peer reviewed)
+ %%%Kei Hashimoto%%%, Yoshihiko Nankaku, and Keiichi Tokuda, “Multi-speaker modeling with shared prior distributions and model structures for Bayesian speech synthesis,” Interspeech 2011, pp.113–116, Florence, Italy, 2011.(Full paper peer reviewed)
+ %%%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,”2011 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2011), pp.5108–5111, Prague, Czech Republic, 2011.(Full paper peer reviewed)
+ %%%Shifeng Pan%%%, Yoshihiko Nankaku, Keiichi Tokuda, and Jianhua Tao, “Global variance modeling on frequency domain delta LSP for HMM-based speech synthesis,” 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2011), pp.4716–4719, Prague, Czech Republic, 2011.(Full paper peer reviewed)
+ %%%Shinji Takaki%%%, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda,“An optimization algorithm of independent mean and variance parameter tying structures for HMM-based speech synthesis,” 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2011), pp.5108–5111, Prague, Czech Republic, 2011.(Full paper peer reviewed)
+
** 研究会 [#m11f486e]
+%%%李晃伸%%%, 大浦圭一郎, 徳田恵一, ``魅力ある音声インタラクションシステムを構築するためのオープンソースツールキットMMDAgent,'' 第13回音声言語シンポジウム, vol. 111, no. 365, SP2011-96, pp. 159-164, 東京, 日本, 2011.
//%%%Akinobu Lee%%%, Keiichiro Oura, and Keiichi Tokuda, ``An Open-Source Toolkit Realizing Attractive Voice Interaction Systems : MMDAgent,'' SIG-SLP, vol. 111, no. 365, SP2011-96, pp. 159-164, Tokyo, Japan, 2011.
+%%%徳田恵一%%%, ``コンテンツ生成の循環系を軸とした音声技術基盤の構築を目指して,'' 第13回音声言語シンポジウム, vol. 111, no. 365, SP2011-95, pp. 153-157, 東京, 日本, 2011. (招待講演)
//%%%Keiichi Tokuda%%%, ``Development of a framework for constructing spoken dialogue systems based on user-generated content,'' SIG-SLP, vol. 111, no. 365, SP2011-95, pp. 153-157, Tokyo, Japan, 2011.
+%%%熊木慶介%%%, 南角吉彦, 徳田恵一, ``分離型格子HMMの構造を用いた隠れ条件付確率場に基づく顔画像認識,'' パターン認識・メディア理解研究会(PRMU), vol. 111, no. 317, PRMU2011-121, pp. 131-136, 長崎, 日本, 2011.
//%%%Keisuke Kumaki%%%, Yoshihiko Nankaku, and Keiichi Tokuda, ``Face recognition based on hidden conditional random fields using structure of separable lattice HMMs,'' PRMU, vol. 111, no. 317, PRMU2011-121, pp. 131-136, Nagasaki, Japan, 2011.
+%%%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に基づく顔画像認識,'' パターン認識・メディア理解研究会(PRMU), vol. 111, no. 317, PRMU2011-120, pp. 125-130, 長崎, 日本, 2011.
//+%%%Kei Sawada%%%, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Face recognition based on separable lattice 2-D HMMs with variational Bayesian method,'' PRMU, vol. 111, no. 317, PRMU2011-120, pp. 125-130, Nagasaki, Japan, 2011.
+%%%Sayaka Shiota%%%, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda, ``Bayesian speech recognition based on model structure integration,'' 音声研究会，vol. 111, no. 97, pp. 11-16, 愛知, 日本, 2011.
//%%%Sayaka Shiota%%%, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda, ``Bayesian speech recognition based on model structure integration,''IEICE Technical Report, vol. 111, no. 97, pp. 11-16, Aichi, Japan, 2011.
** 全国大会 [#lc2ab40e]
+ %%%山本大介%%%, 大浦圭一郎, 李晃伸, 打矢隆弘, 内匠逸, 徳田恵一, 松尾啓志, ``双方向音声案内デジタルサイネージのための学内イベント登録システム,'' 大学ICT 推進協議会, 福岡, 日本, 2011.
///英語タイトルなし
+ %%%橋本佳%%%, 南角吉彦, 徳田恵一, ``ベイズ音声合成における事前分布とモデル構造の話者間共有,'' 日本音響学会2011年秋季研究発表会, pp. 345-348, 島根, 日本, 2011.
//%%%Kei Hashimoto%%%, Yoshihiko Nankaku, and Keiichi Tokuda, ``Bayesian speech synthesis prior distributions and model structures among multiple speakers,'' Acoustical Society of Japan 2011 Autumn Meeting, pp. 345-348, Shimane, Japan, 2011
+ %%%大野博之%%%, 南角吉彦, 李晃伸, 徳田恵一, ``連続音声認識における仮説の低遅延逐次確定アルゴリズムの評価,'' 日本音響学会2011年秋季研究発表会, pp. 45-46, 島根, 日本, 2011.
//%%%Hiroyuki Ono%%%, Yoshihiko Nanakaku, Akinobu Lee, and Keiichi Tokuda, ``Evaluation of successive low-latency hypothesis determination algorithm for continuous speech recognition,'' Acoustical Society of Japan 2011 Autumn Meeting, pp. 45-46, Shimane, Japan, 2011
+ %%%間瀬絢美%%%, 大浦圭一郎, 南角吉彦, 徳田恵一, ``音高正規化学習を用いたHMM歌声合成の検討,'' 日本音響学会2011年秋季研究発表会, pp. 283-284, 島根, 日本, 2011.
//%%%Ayami Mase%%%, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``HMM-based singing voice synthesis using pitch adaptive training,'' Acoustical Society of Japan 2011 Autumn Meeting, pp. 283-284, Shimane, Japan, 2011
+ %%%橋本佳%%%, 山岸順一, William Byrne, Simon King, 徳田恵一, ``音声翻訳における機械翻訳・音声合成の性能評価および分析,'' 日本音響学会2011年春季研究発表会, pp. 315-316, 東京, 日本, 2011.
//%%%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,'' Acoustical Society of Japan 2011 Spring Meeting , pp. 315-316, Tokyo, Japan, 2011.
+ %%%安達璃沙%%%, 間瀬絢美, 南角吉彦, 徳田恵一, ``HMMに基づく早口音声合成における話速と了解度に関する評価,'' 日本音響学会2011年春季研究発表会, pp. 307-308, 東京, 日本, 2011.
//%%%Risa Adachi%%%, Ayami Mase, Yoshihiko Nankaku, and Keiichi Tokuda, ``An evaluation of speech speed and understanding level on rapid speech synthesis based on HMM,'' Acoustical Society of Japan 2011 Spring Meeting , pp. 307-308, Tokyo, Japan, 2011.
+ %%%鹿住恭介%%%, 南角吉彦, 徳田恵一, ``因子分析に基づくHMM音声合成における話者類似性の評価,'' 日本音響学会2011年春季研究発表会, pp. 299-302, 東京, 日本, 2011.
//%%%Kyosuke Kazumi%%%, Yoshihiko Nankaku, and Keiichi Tokuda, ``Evaluating similarity similarity of voice characteristics in factor analyzed acoustic models for HMM-based speech synthesis,'' Acoustical Society of Japan 2011 Spring Meeting , pp. 299-302, Tokyo, Japan, 2011.
+ %%%平野隆司%%%, 南角吉彦, 李晃伸, 徳田恵一, ``双方向探索に基づくN-gramを用いたキーワードからの文生成,'' 日本音響学会2011年春季研究発表会, pp. 211-212, 東京, 日本, 2011.
//%%%Takashi Hirano%%%, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, ``Sentence generation from keywords using N-gram based on bidirectional serch,'' Acoustical Society of Japan 2011 Spring Meeting , pp. 211-212, Tokyo, Japan, 2011.
+ %%%服部貴文%%%, 李蕾, 南角吉彦, 李晃伸, 徳田恵一, ``複数のモデル構造を用いたGMMに基づく話者認識,'' 日本音響学会2011年春季研究発表会, pp. 49-50, 東京, 日本, 2011.
//%%%Takafumi Hattori%%%, Lei Li, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, ``Speaker recognition based on GMM using multiple model structures,'' Acoustical Society of Japan 2011 Spring Meeting , pp. 49-50, Tokyo, Japan, 2011.
+ %%%笠松幹郎%%%, 南角吉彦, 李晃伸, 徳田恵一, ``オンライン処理を考慮した条件付確率場に基づく音声区間検出の検討,'' 日本音響学会2011年春季研究発表会, pp. 35-36, 東京, 日本, 2011.
//%%%Mikio Kasamatsu%%%, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, ``Online processing for voice activity detection using conditional random fields,'' Acoustical Society of Japan 2011 Spring Meeting , pp. 35-36, Tokyo, Japan, 2011.
+ %%%澤田俊彦%%%, 高木信二, 南角吉彦, 李晃伸, 徳田恵一, ``HMM音声認識における平均・分散パラメータの共有構造に関する検討,'' 日本音響学会2011年春季研究発表会, pp. 25-26, 東京, 日本, 2011.
//%%%Toshihiko Sawada%%%, Shinji Takaki, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, ``An optimization algorithm of independent mean and variance parameter tying structures for HMM-based speech recognition,'' Acoustical Society of Japan 2011 Spring Meeting , pp. 25-26, Tokyo, Japan, 2011.
+ %%%塩田さやか%%%, 橋本佳, 南角吉彦, 徳田恵一, ``複数のパラメータ共有構造を考慮したベイズ基準による音響モデリングの検討,'' 日本音響学会2011年春季研究発表会, pp. 21-24, 東京, 日本, 2011.
//%%%Sayaka Shiota%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Acoustic modeling based model structure annealing for Bayesian speech recognition,'' Acoustical Society of Japan 2011 Spring Meeting , pp. 21-24, Tokyo, Japan, 2011.
** 学位論文 [#o55d521e]
+ %%%安達璃沙%%%, ``HMMに基づく早口音声合成における話速と了解度に関する評価,'' 卒業論文, 名古屋工業大学, 2011.
//%%%Risa Adachi%%%, ``An evaluation of speaking rate and intelligibility of HMM-based rapid speech synthesis,'' Bachelor thesis, Nagoya institute of technology, 2011.
+ %%%足立貴昭%%%, ``HMM音声合成におけるFO抽出誤りに頑健な音響モデルの検討,'' 卒業論文, 名古屋工業大学, 2011.
//%%%Takaaki Adachi%%%, ``An investigation of robust pitch models in HMM-based speech synthesis,'' Bachelor thesis, Nagoya institute of technology, 2011.
+ %%%沢田慶%%%, ``変分ベイズ法を用いた分離型2次元格子HMMに基づく顔画像認識,'' 卒業論文, 名古屋工業大学, 2011.
//%%%Kei Sawada%%%, ``Face recognition based on separable lattice 2-D HMMs with variational bayesian method,'' Bachelor thesis, Nagoya institute of technology, 2011.
+ %%%天野貴裕%%%, ``分離型2次元格子HMMによる3次元物体のモデル化,'' 卒業論文, 名古屋工業大学, 2011.
//%%%Takahiro Amano%%%, ``Modeling of 3-D objects with separable lattice 2-D HMMs,'' Bachelor thesis, Nagoya institute of technology, 2011.
+ %%%土屋貴裕%%%, ``文脈自由文法に基づく一般化LR法を用いた大語重連続音声認識アルゴリズム,'' 卒業論文, 名古屋工業大学, 2011.
//%%%Takahiro Tsuchiya%%%, ``A large vocabulary continuous speech recognition algorithm based on generalized LR parsing with context-free grammar,'' Bachelor thesis, Nagoya institute of technology, 2011.
**過去の発表論文 [#d97906db]
#ls2(ホーム/発表論文,reverse);
