- 追加された行はこの色です。
- 削除された行はこの色です。
* 発表論文 - 2004 [#n782a49e]
#contents
** 論文誌 [#da90e548]
+Amaro Lima, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, and Tadashi
Kitamura, “On the use of kernel PCA for feature extraction in speech recognition," IEICE
Transactions on Information and Systems, vol.E87-D, no.12, pp.2802-2811, 2004. (Full paper peer reviewed)
+徳田恵一, “特集号：音声情報処理技術の最先端(1) HMM による音声認識と音声合成," 情報
処理学会誌「情報処理」, vol.45, no.10, pp.1005-1011, 2004.（解説論文）
//英語タイトル不詳
+小林隆夫，徳田恵一，“講座コーパスベース音声合成技術の動向[IV] |HMM 音声合成方
式|," 電子情報通信学会誌，vol.87, no.4, pp.322-327, 2004.（解説論文）
//Takao Kobayashi, Keiichi Tokuda, 〝Technology Trends in Corpus-based Speech Synthesis [IV] : HMM-Based Speech Synthesis"
+Takahiro Hoshiya, Heiga Zen, Shinji Sako, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi,
and Tadashi Kitamura, “An HMM-based approach to speaker-dependent 100 bit/s speech coding,"
Special Workshop in MAUI (SWIM), Lectures by Masters in Speech Processing,
Maui, Hawaii, 2004. (Invited Session Paper)
+Shinji Sako, Hiroaki Kuwabara, Keiichiro Oura, Yusuke Morioka, Keiichi Tokuda, and Shigeki
Sagayama, “HMM-based singing-voice synthesizer," The 4th Contest for Performance Rendering
Systems (Rencon 2004), (予稿なし).
+ 全炳河, 徳田恵一, 北村正, ``決定木に基づく音素コンテキスト・次元・状態位置の同時クラスタリングによる音響モデリング,'' 電子情報通信学会論文誌, vol. 87-D-II, no. 8, pp. 1593-1602, 2004.
//Heiga Zen, Keiichi Tokuda, and Tadashi Kitamura, ``Decision tree based simultaneous clustering of phonetic contexts, dimensions, and state positions for acoustic modeling,'' IEICE transactions, vol. 87-D-II, no. 8, pp. 1593-1602, 2004.
+ 吉村貴克, 徳田恵一, 益子貴史, 小林隆夫, 北村正, ``HMMに基づくテキスト音声合成への混合励振源モデルとポストフィルタの導入,'' 電子情報通信学会論文誌, vol. 87-D-II, no. 8, pp. 1565-1571, 2004.
//Takayoshi Yoshimura, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, and Tadashi Kitamura, ``Incorporation of mixed excitation model and postfilter into HMM-based text-to-speech synthesis,'' IEICE transactions, vol. 87-D-II, no. 8, pp. 1565-1571, 2004.
+ 酒向慎司, 宮島千代美, 徳田恵一, 北村正, ``隠れマルコフモデルに基づいた歌声合成システム,'' 情報処理学会論文誌, vol. 45, no. 3, pp. 719-727, 2004.
//Shinji Sako, Chiyomi Miyajima, Keiichi Tokuda, and Tadashi Kitamura, ``A singing voice synthesis system based on hidden Markov model,'' IPSJ Transactions, vol. 45, no. 3, pp. 719-727, 2004.
** 国際会議 [#vb6f4953]
+%%%Keiichi Tokuda%%%, Heiga Zen, and Tadashi Kitamura, “Reformulating the HMM as a trajectory model," Workshop on Statictical modeling Approach for Speech Recognition (Beyond
HMM), Kyoto, Japan, 2004.(Full paper peer reviewed)
+%%%Shunsuke Kataoka%%%, Nobuaki Mizutani, Keiichi Tokuda, and Tadashi Kitamura, “Decision-tree
backing-off in HMM-based speech synthesis," International Conference on Spoken Lan-
guage Processing (INTERSPEECH2004-ICSLP2004), vol.2, pp.II-1205－II-1208, Jeju, Ko-
rea, 2004. (Full paper peer reviewed)
+%%%Ryosuke Tsuzuki%%%, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Murtaza Bulut, and Shrikanth
S. Narayanan, “Constructing emotional speech synthesizers with limited speech database,"International Conference on Spoken Language Processing (INTERSPEECH2004-ICSLP2004),
vol.2, pp.II-1185－II-1188, Jeju, Korea, 2004. (Full paper peer reviewed)
+%%%Tomoki Toda%%%, Alan W. Black, and Keiichi Tokud “Acoustic-to-articulatory inversion mapping
with Gaussian mixture model," International Conference on Spoken Language Processing
(INTERSPEECH2004-ICSLP2004), vol.2, pp.II-1129－II-1132, Jeju, Korea, 2004. (Full paper peer reviewed)
+%%%Heiga Zen%%%, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, and Tadashi Kitamura, “Hidden
semi-Markov model based speech synthesis," International Conference on Spoken Language
Processing (INTERSPEECH2004-ICSLP2004), vol.2 pp.II-1393－II-1396, Jeju, Korea, 2004. (Full paper peer reviewed)
+%%%Yohei Itaya%%%, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, and Tadashi
Kitamura, “Deterministic annealing EM algorithm in parameter estimation for acoustic
model," International Conference on Spoken Language Processing (INTERSPEECH2004-
ICSLP2004), vol.1, pp.I-437－I-440, Jeju, Korea, 2004. (Full paper peer reviewed)
+%%%T. Nitta%%%, S. Sagayama, Y. Yamashita, T. Kawahara, S. Morishima, S. Nakamura, A. Ya-
mada, K. Ito, M. Kai, A. Li, M. Mimura, K. Hirose, T. Kobayashi, K. Tokuda, N. Mine-
matsu, Y. Den, T. Utsuro, T. Yotsukura, H. Shimodaira, M. Araki, T. Nishimoto, N.
Kawaguchi, H. Banno, and K. Katsurada, “Activities of interactive speech technology consortium (ISTC) targeting open software development for MMI systems," 13th IEEE In-
ternational Workshop on Robot and Human Interactive Communication (RO-MAN 2004),
Kurashiki, Okayama, Japan, 2004 (CD-ROM proceedings).
+%%%Heiga Zen%%%, Keiichi Tokuda, and Tadashi Kitamura, “An introduction of trajectory model into
HMM-based speech synthesis," Proc. of 5th ISCA Speech Synthesis Workshop, Pittsburgh,
U.S.A., 2004. (CD-ROM proceedings)
+%%%Tomoki Toda%%%, Alan W. Black, and Keiichi Tokuda, “Mapping from articulatory movements
to vocal tract spectrum with gaussian mixture model for articulatory speech synthesis,"
Proc. of 5th ISCA Speech Synthesis Workshop, Pittsburgh, U.S.A., 2004. (CD-ROM
proceedings)
+%%%Hisashi Kawai%%%, Tomoki Toda, Jinfu Ni, Minoru Tsuzaki, and Keiichi Tokuda, “Ximera: A
new TTS from ATR based on Corpus-based technologies," ISCA 5th Speech Synthesis
Workshop, pp.179-184, Pittsburgh, U.S.A., 2004. (CD-ROM
proceedings)
+%%%Heiga Zen%%%, Keiichi Tokuda, and Tadashi Kitamura, “A Viterbi algorithm for a trajectory model
derived from HMM with explicit relationship between static and dynamic features," Pro-
ceedings of 2004 IEEE International Conference on Acoustics, Speech, and Signal Process-
ing (ICASSP 2004), vol.1, pp.837-840, Montreal, Canada, 2004. (Full paper peer reviewed)
+%%%Hiroyoshi Yamamoto%%%, Yoshihoko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, and Tadashi
Kitamura, “Parameter sharing and minimum classi cation error training of mixtures of
factor analyzers for speaker identi cation," 2004 IEEE International Conference on Acous-
tics, Speech, and Signal Processing (ICASSP 2004), vol.1, pp.29-32, Montreal, Canada, 2004.(Full paper peer reviewed)
+%%%Takahiro Hoshiya%%%, Heiga Zen, Shinji Sako, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi,
and Tadashi Kitamura, “An HMM-based approach to speaker-dependent 100 bit/s speech coding," Special Workshop in MAUI (SWIM), Lectures by Masters in Speech Processing,
Maui, Hawaii, 2004 (invited session).
** 研究会 [#m11f486e]
** 全国大会 [#lc2ab40e]
+ %%%野村健%%%, 後藤富朗, 徳田恵一, 北村正, ``HMMジャスチャー認識の状態数の検討,'' 電子情報通信学会2004年ソサイエティ大会, pp. 97, 徳島, 日本, 2004.
//英語タイトル不明
+ %%%戸田智基%%%, Alan W. Black, 徳田恵一, ``発話内変動を考慮した最尤スペクトル変換法,'' 日本音響学会2004年秋季研究発表会, pp. 329-330, 沖縄, 日本, 2004.
//英語タイトル不明
+ %%%森岡裕介%%%, 片岡俊介, 全炳河, 南角吉彦, 徳田恵一, 北村正, ``HMM音声合成器の小型化に関する検討,'' 日本音響学会2004年秋季研究発表会,
pp. 325-326, 沖縄, 日本, 2004.
//%%%Yusuke Morioka%%%, Shunsuke Kataoka, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, and Tadashi Kitamura, ``Miniaturization of HMM-based speech synthesis system,'' Acoustical Society of Japan 2004 Autumn Meeting , pp.325-326, Okinawa, Japan, 2004.
+ %%%戸田智基%%%, Alan W. Black, 徳田恵一, ``混合正規分布モデルを用いた調音運動に基づく音声合成,'' 日本音響学会2004年秋季研究発表会, pp. 319-329, 沖縄, 日本, 2004.
//英語タイトル不明
+ %%%桑原宏明%%%, 都筑亮介, 全炳河, 酒向慎司, 徳田恵一, 北村正, ``HMM歌声合成における楽譜情報を用いたラベル設計,'' 日本音響学会2004年秋季研究発表会, pp. 323-324, 沖縄, 日本, 2004.
//%%%Hiroaki Kuwabara%%%, Ryosuke Tsuzuki, Heiga Zen, Shinji Sako, Keiichi Tokuda, Tadashi Kitamura, ``A study on designing context-dependent labels based on musical score for HMM-based singing voice synthesis,'' Acoustical Society of Japan 2004 Autumn Meeting , pp.323-324, Okinawa, Japan, 2004.
+ %%%山本啓善%%%, 南角吉彦, 宮島千代美, 徳田恵一, 北村正, ``混合因子分析に基づく話者モデルの構造に関する検討,'' 日本音響学会2004年秋季研究発表会, pp. 95-96, 沖縄, 日本, 2004.
//%%%Hiroyoshi Yamamoto%%%, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, and Tadashi Kitamura, ``Speaker modeling based on mixtures of factor analyzers,'' Acoustical Society of Japan 2004 Autumn Meeting , pp.95-96, Okinawa, Japan, 2004.
+ %%%布目哲也%%%, 南角吉彦, 徳田恵一, 北村正, ``分離型2次元格子HMMに基づく音声認識の検討,'' 日本音響学会2004年秋季研究発表会, pp. 71-72, 沖縄, 日本, 2004.
//%%%Tetsuya Nunome%%%, Yoshihiko Nankaku, Keiichi Tokuda, and Tadashi Kitamura, ``Speech recognition based on separable 2-D lattice hidden Markov models,'' Acoustical Society of Japan 2004 Autumn Meeting , pp.71-72, Okinawa, Japan, 2004.
+ %%%Amaro Lima%%%, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, and Fernando Gil Resende, ``Feature extraction for speech recognition using sparse KPCA,'' 日本音響学会2004年秋季研究発表会, pp. 69-70, 沖縄, 日本, 2004.
+ %%%西本卓也%%%, 荒木雅弘, 伊藤克亘, 宇津呂武仁, 甲斐充彦, 河口信夫, 河原達也, 桂田浩一, 小林隆夫, 嵯峨山茂樹, 下平博, 伝康晴, 徳田恵一, 中村哲, 新田恒雄, 坂野秀樹, 広瀬啓吉, 峯松信明, 三村正人, 森島繁生, 山下洋一, 山田篤, 四倉達夫, 李晃伸, ``Galatea: 音声対話擬人化エージェント開発キット,'' インタラクション2004, pp. 27-28, 東京, 日本, 2004.
//%%%Takuya Nishimoto%%%, Masahiro araki, Katsunobu Itou, Takehito Utsuro, Atsuhiko Kai, Nobuo Kawaguchi, Tatsuya Kawahara, Kouichi Katsurada, Takao Kobayashi, Shigeki Sagayama, Hiroshi Shimodaira, Yasuharu Den, Keiichi Tokuda, Satoshi Nakamura, Tsuneo Nitta, Hideki Banno, Keikichi Hirose, Nobuaki Minematsu, Masato Mimura, Shigeo Morishima, Yoichi Yamashita, Atsushi Yamada, Tatsuo Yotsukura, and Akinobu Lee, ``Galatea: An Anthropomorphic Spoken Dialogue Agent Toolkit,'' Interaction2004 , pp. 27-28, Tokyo, Japan, 2004.
+ %%%柳哲%%%, 柳生雄午, 徳田恵一, 北村正, ``手の動作と形状を用いたHMM手話認識,'' 電子情報通信学会2004年総合大会, p. 285, 東京, 日本, 2004.
//%%%Satoru Yanagi%%%, Yugo Yagyu, Keiichi Tokuda, and Tadashi Kitamura, ``HMM-based sign kanghuage recognition using hand gesture and hand posture,'' Information and Communication Engineers General Conference 2004, p. 285, Tokyo, Japan, 2004.
+ %%%野村健%%%, 柳哲, 後藤富朗, 徳田恵一, 北村正, ``情報量基準に基づいたHMMジェスチャー認識の状態数の検討,'' 電子情報通信学会2004年総合大会, p.283, 東京, 日本, 2004.
//%%%Ken Nomura%%%, Satoru Yanagi, Tomio Goto, Keiichi Tokuda, and Tadashi Kitamura, ``Study on the number of states of HMM gesture recognition based on information criterion,'' Information and Communication Engineers General Conference 2004, p. 283, Tokyo, Japan, 2004.
+ %%%木田祐介%%%, 山本啓善, 宮島千代美, 徳田恵一, 北村正, ``制約条件下におけるMCE学習の検討不正解時に正解を教えない学習,'' 日本音響学会2004年春季研究発表会, pp. 173-174, 神奈川, 日本, 2004.
//%%%Yusuke Kida%%%, Hiroyoshi Yamamoto, Chiyomi Miyajima, Keiichi Tokuda, and Tadashi Kitamura, ``Minimum classification error training for speaker identification without telling true speaker in case of incorrect recognition,'' Acoustical Society of Japan 2004 Spring Meeting , pp. 173-174, Kanagawa, Japan, 2004.
+ %%%Ranniery Maia%%%, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Fernando Gil Resende, ``In uence of part-of-speech tagging, syllabication, and stress on HMM-based Brazilian portuguese speech synthesis,'' 日本音響学会2004年春季研究発表会, pp. 369-370, 神奈川, 日本, 2004.
+ %%%都築亮介%%%, 全炳河, 徳田恵一, 北村正, Murtaza Bulut, and Shrikanth S. Narayanan, ``主観評価に基づくHMM感情音声合成,'' 日本音響学会2004年春季研究発表会, pp. 251-252, 神奈川, 日本, 2004.
//%%%Ryosuke Tsuzuki%%%, Heiga Zen, Keiichi Tokuda, and Tadashi Kitamura, ``Emotional speech synthesis based on HMM using subjective evaluation score,'' Acoustical Society of Japan 2004 Spring Meeting , pp. 251-252, Kanagawa, Japan, 2004.
+ %%%岡坂ひろみ%%%, 都築亮介, 徳田恵一, 北村正, ``HMM音声合成における感情ラベリングに関する検討,'' 日本音響学会2004年春季研究発表会, pp. 247-248, 神奈川, 日本, 2004.
//%%%Hiromi Okazaki%%%, Ryosuke Tsuzuki, Keiichi Tokuda, and Tadashi Kitamura, ``Effects of emotional level labeling in HMM-based speech synthesis,'' Acoustical Society of Japan 2004 Spring Meeting , pp. 247-248, Kanagawa, Japan, 2004.
+ %%%全炳河%%%, 徳田恵一, 益子貴史, 小林隆夫, 北村正, ``HMM音声合成のための継続長分布付き再推定,'' 日本音響学会2004年春季研究発表会, pp. 223-224, 神奈川, 日本, 2004.
//%%%Heiga Zen%%%, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, and Tadashi Kitamura, ``HMM parameter reestimation with explicit duration model for HMM-based speech synthesis,'' Acoustical Society of Japan 2004 Spring Meeting , pp. 223-224, Kanagawa, Japan, 2004.
** 学位論文 [#o55d521e]
+ %%%三好愛%%%, ``,'' 卒業論文, 名古屋工業大学, 2004.
//英語タイトル不詳
+ %%%古田翔矢%%%, ``HMM音声合成における学習条件に関する検討,'' 卒業論文, 名古屋工業大学, 2004.
//英語タイトル不詳
+ %%%藤井宗太郎%%%, ``HMM音声合成における音質向上に関する諸検討,'' 卒業論文, 名古屋工業大学, 2004.
//英語タイトル不詳
+ %%%布目哲也%%%, ``分離型2次元格子HMMを用いた顔画像認識,'' 卒業論文, 名古屋工業大学, 2004.
//英語タイトル不詳
+ %%%中井亜由子%%%, ``,'' 卒業論文, 名古屋工業大学, 2004.
//英語タイトル不詳
+ %%%近藤大輔%%%, ``話速を考慮した音響モデルによる話し言葉音声認識,'' 卒業論文, 名古屋工業大学, 2004.
//英語タイトル不詳
+ %%%桑原宏明%%%, ``HMM歌声合成システムにおける音質改善,'' 卒業論文, 名古屋工業大学, 2004.
//英語タイトル不詳
+ %%%木田祐介%%%, ``最小誤り分類基準に基づく話者識別ロボット犬学習,'' 卒業論文, 名古屋工業大学, 2004.
//英語タイトル不詳
+ %%%岡坂ひろみ%%%, ``HMM音声合成への感情強度の導入,'' 卒業論文, 名古屋工業大学, 2004.
//英語タイトル不詳
**Past Publications [#d97906db]
#ls2(HOME/PUBLICATIONS,reverse);
