* PUBLICATIONS - 2015 [#s2ef45ce] #contents ** Books [#kc139840] +山岸順一, 徳田恵一, 戸田智基, みわよしこ, ``おしゃべりなコンピュータ ~音声合成技術の現在と未来~,'' 情報研シリーズ19, 丸善ライブラリ, 2015. //2015/03/30 ** Journal [#m4bb004c] +大浦圭一郎, ``統計モデルに基づいた歌声合成技術の最先端,'' 電子情報通信学会誌, vol. 98, no. 6, pp. 460-466, 2015. (Full paper peer reviewed) [[link>http://www.journal.ieice.org/summary.php?id=k98_6_460&year=2015&lang=J]] //2015/06/01 ** Lectures and Panel Discussions (without theses)[#f07d7615] + %%%徳田恵一%%%, ``統計的音声合成技術の現在・過去・未来,'' 第17回音声言語シンポジウム, 電子情報通信学会技術研究報告, 愛知, 日本, 2015. (招待講演) //2015/12/02 +%%%徳田恵一%%%, ``これからの歌声合成,'' 第109回音楽情報科学研究会(SIG-MUS), 石川, 日本, 2015(パネル討論) //2015/11/7 +%%%Keiichi Tokuda%%%, ``Text-to-speech Synthesis as a Machine Learning Problem,'' Recent Advances in Machine Learning and Applications, Aichi, Japan, 2015.(招待講演) //2015/11/5 +%%%Keiichi Tokuda%%%, ``Human-like singing and talking machines: exible speech synthesis in karaoke, anime, smart phones, video games, digital signage, TV and radio programs, etc.,'' CUED Speech Group Seminars, The University of Cambridge, 2015.(招待講演) //2015/2/6 +%%%Keiichi Tokuda%%%, ``Human-like singing and talking machines,'' Speech and Hearing Seminars, The University of Sheffield, 2015.(招待講演) //2015/1/13 ** International Conference [#sf4b9b45] + %%%Kei Sawada%%%, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda, ``The NITECH HMM-based text-to-speech system for the Blizzard Challenge 2015,'' Blizzard Challenge 2015 Workshop, Berlin, Germany, 2015. (Full paper peer reviewed) &publication(2015/20150911_IConference_Blizzard_Kei_Sawada_paper.pdf, paper); &publication(2015/20150911_IConference_Blizzard_Kei_Sawada_slide.pptx, slide); + %%%Takenori Yoshimura%%%, Kei Hashimoto, Keiichiro Oura,Yoshihiko Nankaku, and Keiichi Tokuda, ``Simultaneous optimization of multiple tree structures for factor analyzed HMM-based speech synthesis,'' Interspeech 2015, pp. 1196-1200, Dresden, Germany, 2015. (Full paper peer reviewed) &publication(2015/20150908_IConference_Interspeech_Takenori_Yoshimura_paper.pdf, paper); &publication(2015/20150908_IConference_Interspeech_Takenori_Yoshimura_slide.pptx, slide); + %%%Kei Hashimoto%%%, Keiichiro Oura,Yoshihiko Nankaku, and Keiichi Tokuda, ``The effect of neural networks in statistical parametric speech synthesis,'' 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 4455-4459, Brisbane, Australia, 2015. (Full paper peer reviewed) &publication(2015/20150424_IConference_ICASSP_Kei_Hashimoto_paper.pdf, paper); &publication(2015/20150424_IConference_ICASSP_Kei_Hashimoto_slide.pptx, slide); + %%%Keiichi Tokuda%%% and Heiga Zen, ``Directly modeling speech waveforms by neural networks for statistical parametric speech synthesis,'' 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 4215-4219, Brisbane, Australia, 2015. (Full paper peer reviewed) &publication(2015/20150422_IConference_ICASSP_Keiichi_Tokuda_paper.pdf, paper); &publication(2015/20150422_IConference_ICASSP_Keiichi_Tokuda_slide.pdf, slide); ** Workshop [#ya42055a] + %%%沢田慶%%%, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一, ``発音情報が未知の言語におけるテキスト音声合成システム構築法の評価,'' 第17回音声言語シンポジウム, 電子情報通信学会技術研究報告, vol. 115, no. 346, SP2015-80, pp. 93-98, 愛知, 日本, 2015. &publication(2015/20151203_TReport_SP_Kei_Sawada_paper.pdf, paper); &publication(2015/20151203_TReport_SP_Kei_Sawada_slide.pptx, slide); //Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, //"Evaluation of text-to-speech system construction for unknown-pronunciation languages," //Technical Report of IEICE, vol.115, no.346, SP2015-80, pp.93-98, Aichi, Japan, 2015. //+ %%%徳田恵一%%%, ``統計的音声合成技術の現在・過去・未来,'' 第17回音声言語シンポジウム, 電子情報通信学会技術研究報告, 愛知, 日本, 2015. (招待講演) + %%%橋本佳%%%, 山岸順一, 越前功, ``自動話者照合システムの性能を低下させるプライバシープリザービングサウンドの検討,'' 電子情報通信学会技術研究報告, vol. 115, no. 146, SP2015-49, pp. 79-84, 長野, 日本, 2015. &publication(2015/20150717_TReport_SP_Kei_Hashimoto_paper.pdf, paper); &publication(2015/20150717_TReport_SP_Kei_Hashimoto_slide.pptx, slide); //Kei Hashimoto, Junichi Yamagishi, Isao Echizen, //"Investigation of privacy-preserving sounds to degrade automatic spaker verificationperformance," //Technical Report of IEICE, vol.115, no.146, SP2015-49, pp.79-84, Nagano, July 16-17, 2015. + 岡本拓磨, 小川哲司, 落合翼, 柏木陽佑, 亀岡弘和, 木下慶介, 郡山知樹, 齋藤大輔, 篠崎隆宏, 高木信二, 滝口哲也, 太刀岡勇気, 俵直弘, 橋本佳, 藤本雅清, 松田繁樹, 三村正人, 吉岡拓也, 渡部晋治, ``国際会議ICASSP2015参加報告,'' 音声言語情報処理研究会, vol. 2015-SLP-107, no. 3, pp. 1-7, 長野, 日本, 2015. &publication(2015/20150716_TReport_SLP_Kei_Hashimoto_paper.pdf, paper); //英語タイトル無し + %%%虫鹿弘二%%%, 中村和寛, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一, ``HMM歌声合成における音声データの誤りに頑健なモデル化手法の検討,'' 音楽情報科学研究会, vol. 2015-MUS-106, no. 13, pp. 1-6, 山梨, 日本, 2015. //%%%Koji Mushika%%%, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura,Yoshihiko Nankaku, and Keiichi Tokuda, ``A robust modeling technique against training data errors for HMM-based singing voice synthesis,'' IPSJ Special Interest Group on Music and Computer, vol. 2015-MUS-106, no. 13, pp. 1-6, Yamanashi, Japan, 2015. //&publication(2014/20140123_TReport_SP_Akifumi_Tsuge_paper.pdf, paper); //&publication(2014/20140123_TReport_SP_Akifumi_Tsuge_slide.pptx, slide); //[[link>http://www.ieice.org/ken/paper/201401230BjN/]] //[[link>http://www.ieice.org/ken/paper/201401230BjN/eng/]] ** National Convention [#yf65ad36] + %%%橋本佳%%%, 大浦圭一郎, 南角吉彦, 徳田恵一,  ``ニューラルネットワークに基づく音声合成における系列内変動を考慮したトラジェクトリモデル学習,''  日本音響学会2015年秋季研究発表会, pp. 237-238, 福島, 日本, 2015. //%%%Kei Hashimoto%%%, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Trajectory model training considering global variance for speech synthesis based on neural network,'' Acoustical Society of Japan 2015 Autumn Meeting , pp. 237-238, Fukushima, Japan, 2015. &publication(2015/20150918_DConference_ASJA_Kei_Hashimoto_paper.pdf, paper); &publication(2015/20150918_DConference_ASJA_Kei_Hashimoto_slide.pptx, slide); &publication(2015/20150918_DConference_ASJA_Kei_Hashimoto_abst.pdf, abst); + %%%中村和寛%%%, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田 恵一, ``音声の高帯域成分復元を考慮したメルケプストラム分析に基づくHMM音声合成の検討,'' 日本音響学会2015年秋季研究発表会, pp. 233-234, 福島, 日本, 2015. //%%%Kazuhiro Nakamura%%%, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``A mel-cepstral analysis technique restoring missing high-frequency components of speech for HMM-based speech synthesis,'' Acoustical Society of Japan 2015 Autumn Meeting , pp. 231-232, Fukushima, Japan, 2015. &publication(2015/20150918_DConference_ASJA_Kazuhiro_Nakamura_paper.pdf, paper); &publication(2015/20150918_DConference_ASJA_Kazuhiro_Nakamura_slide.pptx, slide); &publication(2015/20150918_DConference_ASJA_Kazuhiro_Nakamura_abst.pdf, abst); + %%%沢田慶%%%, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田 恵一, ``発音情報が未知の言語におけるテキスト音声合成システム構築法の検討,'' 日本音響学会2015年秋季研究発表会, pp. 231-232, 福島, 日本, 2015. //%%%Kei Sawada%%%, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Investigation of text-to-speech system construction in unknown-pronunciation language,'' Acoustical Society of Japan 2015 Autumn Meeting , pp. 231-232, Fukushima, Japan, 2015. &publication(2015/20150918_DConference_ASJA_Kei_Sawada_paper.pdf, paper); &publication(2015/20150918_DConference_ASJA_Kei_Sawada_slide.pptx, slide); &publication(2015/20150918_DConference_ASJA_Kei_Sawada_abst.pdf, abst); + %%%橋本佳%%%, 山岸順一, 越前功,  ``自動話者照合システムの性能を低下させるプライバシー保護音の検討,''  日本音響学会2015年秋季研究発表会, pp. 27-28, 福島, 日本, 2015. //%%%Kei Hashimoto%%%, Junichi Yamagishi, and Isao Echizen, ``Investigation of privacy-preserving sounds to degrade performance of automatic speaker verification systems,'' Acoustical Society of Japan 2015 Autumn Meeting , pp. 27-28, Fukushima, Japan, 2015. &publication(2015/20150916_DConference_ASJA_Kei_Hashimoto_paper.pdf, paper); &publication(2015/20150916_DConference_ASJA_Kei_Hashimoto_slide.pptx, slide); &publication(2015/20150916_DConference_ASJA_Kei_Hashimoto_abst.pdf, abst); + %%%橋本聖矢%%%, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一,  ``複数の音響特徴量を用いた対数線形モデルに基づく話者認識の検討,''  日本音響学会2015年秋季研究発表会, pp. 25-26, 福島, 日本, 2015. //%%%Masaya Hashimoto%%%, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Speaker recognition based on log linear models using multiple acoustic features,'' Acoustical Society of Japan 2015 Autumn Meeting , pp. 25-26, Fukushima, Japan, 2015. &publication(2015/20150916_DConference_ASJA_Masaya_Hashimoto_paper.pdf, paper); &publication(2015/20150916_DConference_ASJA_Masaya_Hashimoto_slide.pptx, slide); &publication(2015/20150916_DConference_ASJA_Masaya_Hashimoto_abst.pdf, abst); ** Master's and Bachelor's Theses [#i7f1bb4b] + %%%三浦直也%%%, ``音声対話システムにおけるコンテンツ作成者の音声入力を利用した応答音声生成法,'' 卒業論文, 名古屋工業大学, 2015. //%%%Naoya Miura%%%, ``A synthesis technique for spoken dialogue systems using speech inputs uttered by content creators,'' Bachelor thesis, Nagoya institute of technology, 2015. //&publication(2014/20140219_Thesis_Bachelor_Kouki_Tsuruno_paper.pdf, paper); //&publication(2014/20140219_Thesis_Bachelor_Kouki_Tsuruno_slide.pptx, slide); //&publication(2014/20140219_Thesis_Bachelor_Kouki_Tsuruno_abst.pdf, abst); + %%%梅村真由%%%, ``HMM歌声合成における楽譜と発声のずれを表現するタイミングモデルに関する検討,'' 卒業論文, 名古屋工業大学, 2015. //%%%Mayu Umemura%%%, ``Timing models representing differences between musical scores and vocalization for HMM-based singing voice synthesis,'' Bachelor thesis, Nagoya institute of technology, 2015. //&publication(2014/20140219_Thesis_Bachelor_Yusuke_Sato_paper.pdf, paper); //&publication(2014/20140219_Thesis_Bachelor_Yusuke_Sato_slide.pptx, slide); //&publication(2014/20140219_Thesis_Bachelor_Yusuke_Sato_abst.pdf, abst); + %%%市川裕詞%%%, ``歌唱者・言語性の同時変換に基づく多言語歌声合成のための多重特徴変換,'' 卒業論文, 名古屋工業大学, 2015. //%%%Yushi Ichikawa%%%, ``Multiple feature transformation for multi-lingual singing voice synthesis based on simultaneous conversion of singer and language,'' Bachelor thesis, Nagoya institute of technology, 2015. //&publication(2014/20140219_Thesis_Bachelor_Yusaku_Imai_paper.pdf, paper); //&publication(2014/20140219_Thesis_Bachelor_Yusaku_Imai_slide.pptx, slide); //&publication(2014/20140219_Thesis_Bachelor_Yusaku_Imai_abst.pdf, abst); + %%%水谷友哉%%%, ``因子分析に基づく構造化事前分布を用いた声質変換,'' 卒業論文, 名古屋工業大学, 2015. //%%%Tomoya Mizutani%%%, ``Voice conversion using structured prior distributions based on factor analysis,'' Bachelor thesis, Nagoya institute of technology, 2015. //&publication(2014/20140219_Thesis_Bachelor_Shota_Kamiya_paper.pdf, paper); //&publication(2014/20140219_Thesis_Bachelor_Shota_Kamiya_slide.pptx, slide); //&publication(2014/20140219_Thesis_Bachelor_Shota_Kamiya_abst.pdf, abst); + %%%浅井千明%%%, ``オーディオブックを用いた多様な発話スタイルを表現可能な音声合成システムの構築,'' 卒業論文, 名古屋工業大学, 2015. //%%%Chiaki Asai%%%, ``HMM-based speech synthesis system generating various speaking styles using audiobooks,'' Bachelor thesis, Nagoya institute of technology, 2015. //&publication(2014/20140219_Thesis_Bachelor_Tatsuya_Suzuki_paper.pdf, paper); //&publication(2014/20140219_Thesis_Bachelor_Tatsuya_Suzuki_slide.pptx, slide); //&publication(2014/20140219_Thesis_Bachelor_Tatsuya_Suzuki_abst.pdf, abst); + %%%鹿野本気%%%, ``自己回帰HMMを用いた可変長フレームに基づく音声合成手法の検討,'' 卒業論文, 名古屋工業大学, 2015. //%%%Motoki Shikano%%%, ``A speech synthesis technique based on variable length frames using autoregressive HMMs,'' Bachelor thesis, Nagoya institute of technology, 2015. //&publication(2014/20140219_Thesis_Bachelor_Hirotaka_Sato_paper.pdf, paper); //&publication(2014/20140219_Thesis_Bachelor_Hirotaka_Sato_slide.pptx, slide); //&publication(2014/20140219_Thesis_Bachelor_Hirotaka_Sato_abst.pdf, abst); + %%%肥田裕弘%%%, ``重み付き有限状態トランスデューサに基づいた階層型音声認識デコーダにおける動的仮説展開の高速化,'' 卒業論文, 名古屋工業大学, 2015. //%%%Masahiro Hida%%%, ``Fast hypothesis generation for a hierarchy speech recognition decoder based on weighted finite-state transducers,'' Bachelor thesis, Nagoya institute of technology, 2015. //&publication(2014/20140219_Thesis_Bachelor_Yoshihiro_Takamatsu_paper.pdf, paper); //&publication(2014/20140219_Thesis_Bachelor_Yoshihiro_Takamatsu_slide.pptx, slide); //&publication(2014/20140219_Thesis_Bachelor_Yoshihiro_Takamatsu_abst.pdf, abst); + %%%安藤雄輝%%%, ``大語彙連続音声認識における識別学習に基づいた統計モデルによる仮説の枝刈り,'' 卒業論文, 名古屋工業大学, 2015. //%%%Yuki Ando%%%, ``Hypothesis pruning with statistical models based on discriminative training in large vocabulary continuous speech recognition,'' Bachelor thesis, Nagoya institute of technology, 2015. //&publication(2014/20140219_Thesis_Bachelor_Masato_Sukegawa_paper.pdf, paper); //&publication(2014/20140219_Thesis_Bachelor_Masato_Sukegawa_slide.pptx, slide); //&publication(2014/20140219_Thesis_Bachelor_Masato_Sukegawa_abst.pdf, abst); + %%%橋本聖矢%%%, ``複数の音響特徴量を用いた識別モデルに基づく話者認識,'' 卒業論文, 名古屋工業大学, 2015. //%%%Seiya Hashimoto%%%, ``Speaker recognition based on discriminative models using multiple acoustic features,'' Bachelor thesis, Nagoya institute of technology, 2015. //&publication(2014/20140219_Thesis_Bachelor_Masato_Sukegawa_paper.pdf, paper); //&publication(2014/20140219_Thesis_Bachelor_Masato_Sukegawa_slide.pptx, slide); //&publication(2014/20140219_Thesis_Bachelor_Masato_Sukegawa_abst.pdf, abst); + %%%山森滉二%%%, ``分離型格子構造に基づく隠れ条件付き確率場を用いた画像認識における有効な特徴量の検討,'' 卒業論文, 名古屋工業大学, 2015. //%%%Koji Yamamori%%%, ``Effective features in image recognition using hidden conditional random fields based on separable lattice structure,'' Bachelor thesis, Nagoya institute of technology, 2015. //&publication(2014/20140219_Thesis_Bachelor_Masato_Sukegawa_paper.pdf, paper); //&publication(2014/20140219_Thesis_Bachelor_Masato_Sukegawa_slide.pptx, slide); //&publication(2014/20140219_Thesis_Bachelor_Masato_Sukegawa_abst.pdf, abst); + %%%軸屋竜太%%%, ``識別モデルに基づく画像認識に有効な局所特徴の自動選択に関する検討,'' 卒業論文, 名古屋工業大学, 2015. //%%%Jikuya Ryuta%%%, ``Automatic selection of effective local features for image recognition based on discriminative models,'' Bachelor thesis, Nagoya institute of technology, 2015. //&publication(2014/20140219_Thesis_Bachelor_Masato_Sukegawa_paper.pdf, paper); //&publication(2014/20140219_Thesis_Bachelor_Masato_Sukegawa_slide.pptx, slide); //&publication(2014/20140219_Thesis_Bachelor_Masato_Sukegawa_abst.pdf, abst); + %%%喜多村翔斗%%%, ``音声対話システムにおける重み付き有限状態トランスデューサに基づいた音声認識部と応答選択部の統合,'' 修士論文, 名古屋工業大学, 2015. //%%%Syoto Kitamura%%%, ``Integration of speech recognition and response selection in spoken dialogue systems based on weighted finite-state transducers,'' Master thesis, Nagoya institute of technology, 2015. //&publication(2014/20140214_Thesis_Master_Manami_Toyoda_paper.pdf, paper); //&publication(2014/20140214_Thesis_Master_Manami_Toyoda_slide.pptx, slide); //&publication(2014/20140214_Thesis_Master_Manami_Toyoda_abst.pdf, abst); + %%%岡田麻未%%%, ``入力信号の信頼度を考慮した音響・画像特徴量のモデル化に基づくバイモーダル音声認識,'' 修士論文, 名古屋工業大学, 2015. //%%%Mami Okada%%%, ``Audio-visual speech recognition based on acoustic and image feature modeling considering reliability of input streams,'' Master thesis, Nagoya institute of technology, 2015. //&publication(2014/20140214_Thesis_Master_Kanako_Shirota_paper.pdf, paper); //&publication(2014/20140214_Thesis_Master_Kanako_Shirota_slide.pptx, slide); //&publication(2014/20140214_Thesis_Master_Kanako_Shirota_abst.pdf, abst); + %%%柘植彬史%%%, ``生成モデルに基づく特徴量生成を用いた識別モデルによる話者認識,'' 修士論文, 名古屋工業大学, 2015. //%%%Akifumi Tuge%%%, ``Speaker recognition based on discriminative models using features generated from statistical generative models,'' Master thesis, Nagoya institute of technology, 2015. //&publication(2014/20140214_Thesis_Master_Tomohiro_Okada_paper.pdf, paper); //&publication(2014/20140214_Thesis_Master_Tomohiro_Okada_slide.pptx, slide); //&publication(2014/20140214_Thesis_Master_Tomohiro_Okada_abst.pdf, abst); + %%%虫鹿弘二%%%, ``HMM歌声合成における音声データの誤りに頑健なモデル化手法,'' 修士論文, 名古屋工業大学, 2015. //%%%Koji Mushika%%%, ``HMM-based singing voice synthesis using a robust modeling technique against training data errors,'' Master thesis, Nagoya institute of technology, 2015. //&publication(2014/20140214_Thesis_Master_Motoharu_Noda_paper.pdf, paper); //&publication(2014/20140214_Thesis_Master_Motoharu_Noda_slide.pptx, slide); //&publication(2014/20140214_Thesis_Master_Motoharu_Noda_abst.pdf, abst); + %%%吉村建慶%%%, ``因子分析に基づくHMM音声合成における基底クラスタリング,'' 修士論文, 名古屋工業大学, 2015. //%%%Takenori Yoshimura%%%, ``Context clustering with multiple tree structures for factor analyzed HMM-based speech synthesis,'' Master thesis, Nagoya institute of technology, 2015. //&publication(2014/20140214_Thesis_Master_Tatsunai_Kato_paper.pdf, paper); //&publication(2014/20140214_Thesis_Master_Tatsunai_Kato_slide.pptx, slide); //&publication(2014/20140214_Thesis_Master_Tatsunai_Kato_abst.pdf, abst); + %%%桑子修一%%%, ``因子分析を用いたHMM音声合成における発話適応学習 ,'' 修士論文, 名古屋工業大学, 2015. //%%%Syuichi Kuwako%%%, ``Utterance adaptive training for HMM-based speech synthesis using factor analysis,'' Master thesis, Nagoya institute of technology, 2015. //&publication(2014/20140214_Thesis_Master_Takaya_Makino_paper.pdf, paper); //&publication(2014/20140214_Thesis_Master_Takaya_Makino_slide.pptx, slide); //&publication(2014/20140214_Thesis_Master_Takaya_Makino_abst.pdf, abst); + %%%有竹貴士%%%, ``周期成分の揺らぎを考慮した複素ケプストラムに基づく統計的音声生成システム,'' 修士論文, 名古屋工業大学, 2015. //%%%Takashi Aritake%%%, ``A statistical speech synthesis system using complex cepstrum considering variation of periodic components,'' Master thesis, Nagoya institute of technology, 2015. //&publication(2014/20140214_Thesis_Master_Takaya_Makino_paper.pdf, paper); //&publication(2014/20140214_Thesis_Master_Takaya_Makino_slide.pptx, slide); //&publication(2014/20140214_Thesis_Master_Takaya_Makino_abst.pdf, abst); ** Past Publications [#d97906db] #ls2(HOME/PUBLICATIONS/,reverse);