* PUBLICATIONS - 2013 [#n782a49e]
#contents
** Journal [#da90e548]
+%%%Keiichi Tokuda%%%, “Flexible speech synthesis based on hidden Markov models," Asia-Pacific
Signal and Information Processing Association Annual Summit and Conference 2013 (AP-
SIPA ASC 2013), Kaohsiung, Taiwan, 2013 (invited talk). (without proceedings paper)
+%%%徳田恵一%%%，“ユーザ参加型双方向音声案内デジタルサイネージシステム：「メイちゃん」," 平
成25 年度電気関係学会東海支部連合大会案内, 2013 (招待講演).
+%%%徳田恵一%%%，“統計的機械学習問題としての音声合成," 情報処理学会音楽情報科学研究会（音学シンポジウム）, 2013 (招待講演).
+ Keiichi Tokuda, Yoshihiko Nankaku, Tomoki Toda, Heiga Zen, Junichi Yamagishi, and Keiichiro Oura, ``Speech synthesis based on hidden Markov models,'' Proceedings of the IEEE, vol. 101, no. 5, pp. 1234-1252, 2013. (Full paper peer reviewed, Invited paper)
+ Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``A Bayesian framework using multiple model structures for speech recognition,'' IEICE Transactions on Information and Systems, vol. E96-D, No. 4, pp. 939-948, 2013. (Full paper peer reviewed)
+%%%徳田恵一%%%，大浦圭一郎，李晃伸，山本大介，打矢隆弘，内匠逸，“ユーザ参加型双方向音声
案内デジタルサイネージシステムの開発・設置・運用事例," 日本音響学会春季研究発表会,
pp.119-122, 2013 (招待講演).
+ John Dines, Hui Liang, Lakshmi Saheer, Matthew Gibson, William Byrne, Keiichiro Oura, Keiichi Tokuda, Junichi Yamagishi, Simon King, Mirjam Wester, Teemu Hirsimaki, Reima Karhila, and Mikko Kurimo, ``Personalising speech-to-speech translation: unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis,'' Computer Speech and Language, vol. 27, pp. 420-437, 2013. (Full paper peer reviewed)
+ 大浦圭一郎，山本大介，内匠逸，李晃伸，徳田恵一，``キャンパスの公共空間におけるユーザ参加型双方向音声案内デジタルサイネージシステム,'' 人工知能学会誌, vol. 28, no. 1, pp. 60-67, 2013. (フルペーパー査読，招待論文)
** International Conference [#vb6f4953]
+%%%Keiichi Tokuda%%%, ``Flexible speech synthesis based on hidden Markov models,'' Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2013 (APSIPA ASC 2013), Kaohsiung, Taiwan, 2013. (Invited talk, Special session)
+%%%Kei Sawada%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Image recognition based on hidden Markov eigen-image models using variational Bayesian method,'' Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2013 (APSIPA ASC 2013), pp. 1-8, Kaohsiung, Taiwan, 2013. (Full paper peer reviewed)
+%%%Shinji Takaki%%%, Kei Sawada, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda, ``Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2013,'' Blizzard Challenge 2013 Workshop, Barcelona, Spain, 2013.
+%%%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,'' 8th International Symposium on Computer Architecture (ISCA) Speech Synthesis Workshop, pp. 317-322, Lyon, France, 2013. (Full paper peer reviewed)
+%%%Shinji Takaki%%%, Yoshihiko Nankaku, and Keiichi Tokuda, ``Contextual partial additive structure for HMM-based speech synthesis,'' 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 7878-7882, Vancouver, Canada, 2013. (Full paper peer reviewed)
+%%%Kazuhiro Nakamura%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Integration of acoustic modeling and mel-cepstral analysis for HMM-based speech synthesis,'' 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 7883-7887, Vancouver, Canada, 2013. (Full paper peer reviewed)
+%%%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,'' 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 3203-3207, Vancouver, Canada, 2013. (Full paper peer reviewed)
+%%%Akira Tamamori%%%, Yoshihiko Nankaku, and Keiichi Tokuda, ``Image recognition based on separable lattice trajectory HMMs,'' 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 3467-3271, Vancouver, Canada, 2013. (Full paper peer reviewed)
+%%%Akinobu Lee%%%, Keiichiro Oura, Keiichi Tokuda, “MMDAgent –A FULLY OPEN-SOURCE
TOOLKIT FOR VOICE INTERACTION SYSTEMS–,” 2013 IEEE International Conference
on Acoustics, Speech, and Signal Processing (ICASSP 2013), pp.8382–8385, Vancouver,
Canada, 2013. (Full paper peer reviewed)
** Workshop [#m11f486e]
+%%%徳田恵一%%%, ``ユーザ参加型双方向音声案内デジタルサイネージシステム：「メイちゃん」,'' 平成25年度電気関係学会東海支部連合大会案内, 愛知, 日本, 2013. (招待講演)
+%%%大浦圭一郎%%%, 南角吉彦, 徳田恵一, ``Sinsy〜隠れマルコフモデルに基づく歌声合成の現状と今後〜,'' 情報処理学会音楽情報科学研究会 (SIGMUS), vol. 2013-MUS-99, no. 52, pp. 1-3, 東京, 日本, 2013.
+ %%%徳田恵一%%%, ``統計的機械学習問題としての音声合成,'' 情報処理学会音楽情報科学研究会 (SIGMUS), 東京, 日本, 2013. (招待講演)
+ %%%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可変固有画像モデルに基づく画像認識,'' パターン認識・メディア理解研究会(PRMU), vol. 112, no. 441, PRMU2012-130, pp. 155-160, 大阪, 日本, 2013.
//%%%Kei Sawada%%%,Akira Tamamori, Yoshihiko Nankaku, and Keiichi Tokuda, ``Image recognition based on hidden Markov eigen-image models with the variational Bayesian method,'' PRMU, vol. 112, no. 441, PRMU2012-130, pp. 155-160, Osaka, Japan, 2013.
+ %%%牧野貴也%%%, 高木信二, 橋本佳, 南角吉彦, 徳田恵一, ``状態継続長制御に基づいた格調分離型格子HMM による変動に頑健な画像認識,'' パターン認識・メディア理解研究会(PRMU), vol. 112, no. 441, PRMU2012-130, pp. 149-154, 大阪, 日本, 2013.
//%%%Takaya Makino%%%, Shinji Takaki, Kei Sawada, and Keiichi Tokuda, ``Extended separable lattice HMMs based on state duration control for recognition of images with variations,'' PRMU, vol. 112, no. 441, PRMU2012-130, pp. 149-154, Osaka, Japan, 2013.
** National Convention [#lc2ab40e]
+%%%柘植彬史%%%, 橋本佳, 南角吉彦, 徳田恵一, ``ベイズ統計量を用いた対数線形モデルに基づく話者認識,'' 日本音響学会2013年秋季研究発表会, pp. 73-74, 愛知, 日本, 2013.
//+%%%Akifumi Tsuge%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Speaker recognition based on log-linear models using Bayesian statistic,'' Acoustical Society of Japan 2013 Autumn Meeting, pp. 73-74, Aichi, Japan, 2013.
+%%%中村和寛%%%, 大浦圭一郎, 南角吉彦, 徳田恵一, ``HMMに基づく英語歌声合成の検討,'' 日本音響学会2013年秋季研究発表会, pp. 299-230, 愛知, 日本, 2013.
//+%%%Kazuhiro Nakamura%%%, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``An HMM-based approach for English singing voice synthesis,'' Acoustical Society of Japan 2013 Autumn Meeting, pp. 299-230, Aichi, Japan, 2013.
+%%%船谷内泰斗%%%, 大浦圭一郎, 南角吉彦, 李晃伸, 徳田恵一, ``ユーザ生成型音声対話コンテンツに向けた有限状態トランスデューサに基づく簡潔な対話記述法の検討,'' 日本音響学会2013年秋季研究発表会, pp. 223-224, 愛知, 日本, 2013.
//+%%%Taito Funayachi%%%, Keiichiro Oura, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, ``A simple dialogue description based on finite state transducers for user-generated spoken dialog content,'' Acoustical Society of Japan 2013 Autumn Meeting, pp. 223-224, Aichi, Japan, 2013.
+%%%城田佳菜子%%%, 中村和寛, 大浦圭一郎, 南角吉彦, 徳田恵一, ``HMM歌声合成における歌唱者適応学習の検討,'' 日本音響学会2013年春季研究発表会, pp. 339-340, 東京, 日本, 2013.
//+%%%Kanako Shirota%%%, Kazuhiro Nakamura, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Integration of speaker and pitch adaptive training techniques for HMM-based singing voice synthesis,'' Acoustical Society of Japan 2013 Spring Meeting, pp. 339-340, Tokyo, Japan, 2013.
+%%%喜多村翔斗%%%, 中村和寛, 橋本佳, 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歌声合成における調子外れの補正,'' 日本音響学会2013年春季研究発表会, pp. 337-338, 東京, 日本, 2013.
//+%%%Shota 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,'' Acoustical Society of Japan 2013 Spring Meeting, pp. 337-338, Tokyo, Japan, 2013.
+%%%岡田知大%%%, 高木信二, 南角吉彦, 徳田恵一, ``HMM音声合成におけるF0/有声・無声重みの個別クラスタリングによる合成音声の評価,'' 日本音響学会2013年春季研究発表会, pp. 293-294, 東京, 日本, 2013.
//+%%%Tomohiro Okada%%%, Shinji Takaki, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Evaluation of individual clustering of F0 and voice/unvoiced weights for HMM-based speech synthesis,'' Acoustical Society of Japan 2013 Spring Meeting, pp. 293-294, Tokyo, Japan, 2013.
+%%%桑子修一%%%, 高木信二, 橋本佳, 南角吉彦, 徳田恵一, ``HMM音声合成における因子分析を用いた発話適応学習の検討,'' 日本音響学会2013年春季研究発表会, pp. 291-292, 東京, 日本, 2013.
//+%%%Shuichi Kuwako%%%, Shinji Takaki, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Utterance adaptive training in factor analyzed acoustic models for HMM-based speech synthesis'' Acoustical Society of Japan 2013 Spring Meeting, pp. 291-292, Tokyo, Japan, 2013.
+%%%中村和寛%%%, 橋本佳, 南角吉彦, 徳田恵一, ``HMM音声合成におけるメルケプストラム分析を統合した音響モデリングの検討,'' 日本音響学会2013年春季研究発表会, pp. 289-290, 東京, 日本, 2013.
//+%%%Kazuhiro Nakamura%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Integration of acoustic modeling and mel-cepstral analysis for HMM-based speech synthesis,'' Acoustical Society of Japan 2013 Spring Meeting, pp. 289-290, Tokyo, Japan, 2013.
+%%%徳田恵一%%%, 大浦圭一郎, 李晃伸, 山本大介, 打矢隆弘, 内匠逸, ``ユーザ参加型双方向音声案内デジタルサイネージシステムの開発・設置・運用事例,'' 日本音響学会2013年春季研究発表会, pp. 119-122, 東京, 日本, 2013.(招待講演)
//+%%%Keiichi Tokuda%%%, Keiichiro Oura, Akinobu Lee, Daisuke Yamamoto, Takahiro Uchiya, and Ichi Takumi, ``Developing a user-participated voice-interactive digital signage system and running it in the campus,'' Acoustical Society of Japan 2013 Spring Meeting, pp. 119-122, Tokyo, Japan, 2013.
+%%%Viviane Oliveira%%%, 塩田さやか, 橋本佳, 南角吉彦, 徳田恵一, ``Cross-lingual speaker adaptation for HMM-based speech synthesis using joint-eigenvoices with a space of perceptual characteristics,'' 日本音響学会2013年春季研究発表会, pp. 269-270, 東京, 日本, 2013.
//+%%%Viviane 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,'' Acoustical Society of Japan 2013 Spring Meeting, pp. 269-270, Tokyo, Japan, 2013.
+%%%吉村建慶%%%, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一, ``HMM音声合成のためのバイリンガルデータを用いた因子分析に基づくクロスリンガル話者適応,'' 日本音響学会2013年春季研究発表会, pp. 267-268, 東京, 日本, 2013.
//+%%%Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Cross-lingual speaker adaptation based on factor analysis using bilingual speech data,'' Acoustical Society of Japan 2013 Spring Meeting, pp. 267-268, Tokyo, Japan, 2013.
** Master's and Bachelor's Theses [#o55d521e]
+ %%%柘植彬史%%%, ``ベイズ基準による特徴量生成を用いた対数線形モデルに基づく話者認識,'' 卒業論文, 名古屋工業大学, 2013.
//%%%Akifumi Tsuge%%%, ``Speaker recognition based on log-linear models using feature generation by bayesian method,'' Bachelor thesis, Nagoya institute of technology, 2013.
+ %%%喜多村翔斗%%%, ``HMM歌声合成における音高正規化学習を用いた調子外れ補正,'' 卒業論文, 名古屋工業大学, 2013.
//%%%Shota Kitamura%%%, ``Automatic correction of tuneless singing for HMM-based singing voice synthesis using pitch adaptive training,'' Bachelor thesis, Nagoya institute of technology, 2013.
+ %%%桑子修一%%%, ``HMM音声合成における因子分析を用いた発話適応学習,'' 卒業論文, 名古屋工業大学, 2013.
//%%%Syuichi Kuwako%%%, ``Utterance adaptive training based on factor analyzed acoustic models in HMM-based speech synthesis,'' Bachelor thesis, Nagoya institute of technology, 2013.
+ %%%吉村建慶%%%, ``HMM音声合成のための因子分析に基づくクロスリンガル話者適応,''卒業論文, 名古屋工業大学, 2013.
//%%%Takenori Yoshimura%%%, ``Cross-lingual speaker adaptation based on factor analysis for HMM-based speech synthesis,'' Bachelor thesis, Nagoya institute of technology, 2013.
+ %%%有竹貴士%%%, ``HMM音声合成における周波数領域可変サンプリングに基づくスペクトル特徴量の検討,'' 卒業論文, 名古屋工業大学, 2013.
//%%%Takashi Aritake%%%, ``An investigation of spectrum features on variable sampling in frequency domain in HMM-based speech synthesis,'' Bachelor thesis, Nagoya institute of technology, 2013.
+ %%%岡田麻未%%%, ``拡張可変固有画像モデルに基づく画像認識,'' 卒業論文, 名古屋工業大学, 2013.
//%%%Mami Okada%%%, ``Image recognition based on extended hidden marcov eigen image models,'' Bachelor thesis, Nagoya institute of technology, 2013.
+ 芝地邦夫, ``音声対話システムにおける近接センサを用いたユーザ検出と検出情報のフィードバックに関する検討,'' 卒業論文, 名古屋工業大学, 2013.
//Kunio Shibachi, ``Examination of user detection and detection information feedback using proximity sensors in spoken dialogue systems,'' Bachelor thesis, Nagoya institute of technology, 2013.
+ %%%平野隆司%%%, ``キーワードと汎用言語モデルに基づく統計的音声対話システムにおける音声認識部と応答選択部の密結合,'' 修士論文, 名古屋工業大学, 2013.
//%%%Takashi Hirano%%%, ``Tight integration of speech recognition and response selection in a statistical spoken dialogue system based on keywords and general language models,'' Master thesis, Nagoya institute of technology, 2013.
+ %%%土屋貴裕%%%, ``仮説生成／選択による大語彙連続音声認識アルゴリズムの統一的表現とそれに基づく汎用デコーダの開発,'' 修士論文, 名古屋工業大学, 2013.
//%%%Takahiro Tsuchiya%%%, ``Development of a versatile decoder based on unified description of speech recognition algorithms using hypothesis generator/selector'' Master thesis, Nagoya institute of technology, 2013.
+ %%%真野翔平%%%, ``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,'' 修士論文, 名古屋工業大学, 2013.
//%%%Shohei Mano%%%, ``A training algorithm of hidden conditional random fields based on deterministic annealing process for speech recognition'' Master thesis, Nagoya institute of technology, 2013.
+ %%%天野貴裕%%%, ``条件付確率場に基づく基本周波数推定,'' 修士論文, 名古屋工業大学, 2013.
//%%%Takahiro Amano%%%, ``Fundamental frequency estimation based on conditional random fields,'' Master thesis, Nagoya institute of technology, 2013.
+ %%%足立貴昭%%%, ``HMM音声合成のためのH/L型アクセント推定を統合した音響モデリング,'' 修士論文, 名古屋工業大学, 2013.
//%%%Takaaki Adachi%%%, ``Acoustic modeling integrating high/low accent estimation for HMM-based speech synthesis'' Master thesis, Nagoya institute of technology, 2013.
+ %%%Viviane Oliveira%%%, ``表現語空間を用いた連結固有声法に基づくクロスリンガル話者適応,'' 修士論文, 名古屋工業大学, 2013.
//%%%Viviane Oliveira%%%, ``Cross-lingual speaker adaptation for HMM-based speech synthesis using joint-eigenvoices with a perceptual characteristic space,'' Master thesis, Nagoya institute of technology, 2013.
+ %%%服部貴文%%%, ``話者性の効率的特徴表現を自動抽出可能な生成モデルに基づく話者認識,'' 修士論文, 名古屋工業大学, 2013.
//%%%Takafumi Hattori%%%, ``Speaker recognition based on generative models incorporating automatic feature extraction for efficient speaker representation,'' Master thesis, Nagoya institute of technology, 2013.
+ %%%沢田慶%%%, ``ベイズ基準による可変固有画像モデルに基づく画像認識,'' 修士論文, 名古屋工業大学, 2013.
//%%%Kei Sawada%%%, ``A Bayesian approach to image recognition based on hidden Markov eigen-image models,'' Master thesis, Nagoya institute of technology, 2013.
** Past Publications [#d97906db]
#ls2(HOME/PUBLICATIONS/,reverse);
