* PUBLICATIONS - 2016 [#n782a49e] #contents ** Books [#b4a30c8b] + 大浦圭一郎(分担執筆), ``HMM音声合成,'' 音響キーワードブック, コロナ社, II-26, 2016. //2016/03/22 ** Journal [#da90e548] ** International Conference [#vb6f4953] + %%%Keiichi Tokuda%%%, and Heiga Zen, ``Directly modeling voiced and unvoiced components in speech waveforms by neural networks,'' 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 5640-5644, Shanghai, China, 2016. (Full paper peer reviewed) &publication(2016/20160324_IConference_ICASSP_Keiichi_Tokuda_paper.pdf, paper); &publication(2016/20160324_IConference_ICASSP_Keiichi_Tokuda_poster.pdf, poster); + %%%Kei Hashimoto%%%, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Trajectory training considering global variance for speech synthesis based on neural networks,'' 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 5600-5604, Shanghai, China, 2016. (Full paper peer reviewed) &publication(2016/20160323_IConference_ICASSP_Kei_Hashimoto_paper-2.pdf, paper); &publication(2016/20160323_IConference_ICASSP_Kei_Hashimoto_poster-2.pptx, poster); + %%%Kei Hashimoto%%%, Junichi Yamagishi, and Isao Echizen, ``Privacy-preserving sound to degrade automatic speaker verification performance,'' 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 5500-5504, Shanghai, China, 2016. (Full paper peer reviewed) &publication(2016/20160323_IConference_ICASSP_Kei_Hashimoto_paper-1.pdf, paper); &publication(2016/20160323_IConference_ICASSP_Kei_Hashimoto_poster-1.pptx, poster); ** Workshop [#m11f486e] + %%%助川正人%%%, 沢田慶, 橋本佳, 南角吉彦, 徳田恵一, ``画像認識のための混合出力分布を用いた分離型格子HMM におけるパラメータ共有構造の検討,'' パターン認識・メディア理解研究会(PRMU), vol. 115, no. 456, PRMU2015-138, pp. 37-42, 福岡, 日本, 2016. //%%%Masato Sukegawa%%%, Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Parameter sharing structures of separable lattice HMMs using mixture output distributions for image recognition,'' PRMU, vol. 115, no. 456, PRMU2015-138, pp. 37-42, Fukuoka, Japan, 2016. &publication(2016/20160221_TReport_PRMU_Masato_Sukegawa_paper.pdf, paper); &publication(2016/20160221_TReport_PRMU_Masato_Sukegawa_slide.pptx, slide); ** National Convention [#lc2ab40e] + %%%鈴木達也%%%, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一, ``条件付確率場に基づく音声の基本周波数推定の検討,'' 日本音響学会2016年春季研究発表会, pp. 279-280, 神奈川, 日本, 2016. //%%%Tatsuya Suzuki%%%, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Investigation of voice fundamental frequency estimation based on conditional random fields,'' Acoustical Society of Japan 2016 Spring Meeting , pp. 279-280, Kanagawa, Japan, 2016. &publication(2016/20160311_DConference_ASJS_Tatsuya_Suzuki_paper.pdf, paper); &publication(2016/20160311_DConference_ASJS_Tatsuya_Suzuki_slide.pptx, slide); &publication(2016/20160311_DConference_ASJS_Tatsuya_Suzuki_abst.pdf, abst); + %%%保坂尚紀%%%, 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声質変換における系列内変動を考慮したトラジェクトリ学習,'' 日本音響学会2016年春季研究発表会, pp. 239-240, 神奈川, 日本, 2016. //%%%Naoki Hosaka%%%, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Trajectory training considering global variance for voice conversion based on neural network, pp. 239-240, Kanagawa, Japan, 2016. &publication(2016/20160310_DConference_ASJS_Naoki_Hosaka_paper.pdf, paper); &publication(2016/20160310_DConference_ASJS_Naoki_Hosaka_slide.pptx, slide); &publication(2016/20160310_DConference_ASJS_Naoki_Hosaka_abst.pdf, abst); + %%%吉村建慶%%%, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一, ``クラウドソーシングによる音声収集のための収録ソフトウェアの設計,'' 日本音響学会2016年春季研究発表会, pp. 307-308, 神奈川, 日本, 2016. //%%%Takenori Yoshimura%%%, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``A design of voice recording software tool to effectively collect speech data based on crowdsourcing,'' Acoustical Society of Japan 2016 Spring Meeting , pp. 307-308, Kanagawa, Japan, 2016. &publication(2016/20160309_DConference_ASJS_Takenori_Yoshimura_paper.pdf, paper); &publication(2016/20160309_DConference_ASJS_Takenori_Yoshimura_poster.pptx, poster); &publication(2016/20160309_DConference_ASJS_Takenori_Yoshimura_abst.pdf, abst); + %%%橋本佳%%%, 山岸順一, 越前功, ``話者照合性能を低下させるUBMに基づくプライバシー保護音の検討,'' 日本音響学会2016年春季研究発表会, pp. 131-132, 神奈川, 日本, 2016. //%%%Kei Hashimoto%%%, Junichi Yamagishi, and Isao Echizen, ``Privacy-preserving sounds based on universal background models to degrade performance of automatic speaker verification systems,'' Acoustical Society of Japan 2016 Spring Meeting , pp. 131-132, Kanagawa, Japan, 2016. &publication(2016/20160309_DConference_ASJS_Kei_Hashimoto_paper.pdf, paper); &publication(2016/20160309_DConference_ASJS_Kei_Hashimoto_poster.pptx, poster); &publication(2016/20160309_DConference_ASJS_Kei_Hashimoto_abst.pdf, abst); + %%%沢田慶%%%, 伊神和輝, 浅井千明, 佐藤雄介, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一, ``統計的パラメトリック音声合成のためのオーディオブックを用いた学習コーパス自動構築,'' 日本音響学会2016年春季研究発表会, pp. 219-220, 神奈川, 日本, 2016. (学生優秀発表賞) //%%%Kei Sawada%%%, Kazuki Igami, Chiaki Asai, Yusuke Sato, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Automatic construction of training corpus using audiobooks for statistical parametric speech synthesis,'' Acoustical Society of Japan 2016 Spring Meeting , pp. 219-220, Kanagawa, Japan, 2016. (The Student Presentation Award) &publication(2016/20160309_DConference_ASJS_Kei_Sawada_paper.pdf, paper); &publication(2016/20160309_DConference_ASJS_Kei_Sawada_slide.pptx, slide); &publication(2016/20160309_DConference_ASJS_Kei_Sawada_abst.pdf, abst); + %%%西村方成%%%, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一, ``Deep Neural Networkに基づく歌声合成の検討,'' 日本音響学会2016年春季研究発表会, pp. 213-214, 神奈川, 日本, 2016. //%%%Masanari Nishimura%%%, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Investigation of singing voice synthesis based on deep neural networks,'' Acoustical Society of Japan 2016 Spring Meeting , pp. 213-214, Kanagawa, Japan, 2016. &publication(2016/20160309_DConference_ASJS_Masanari_Nishimura_paper.pdf, paper); &publication(2016/20160309_DConference_ASJS_Masanari_Nishimura_slide.pptx, slide); &publication(2016/20160309_DConference_ASJS_Masanari_Nishimura_abst.pdf, abst); ** Master's and Bachelor's Theses [#o55d521e] + %%%森裕都%%%, ``重み付き有限状態トランスデューサに基づく音声対話システムのための音声認識部と応答選択部の統合,'' 卒業論文, 名古屋工業大学, 2016. //%%%Yuto Mori%%%, ``Integration of speech recognition and response selection for spoken dialogue systems based on weighted finite-state transducers,'' Bachelor thesis, Nagoya institute of technology, 2015. &publication(2016/20160223_Thesis_Bachelor_Yuto_Mori_paper.pdf, paper); &publication(2016/20160223_Thesis_Bachelor_Yuto_Mori_slide.pptx, slide); &publication(2016/20160223_Thesis_Bachelor_Yuto_Mori_abst.pdf, abst); + %%%村山賢汰%%%, ``音声入力を用いた応答生成に基づく音声対話システム構築法の検討,'' 卒業論文, 名古屋工業大学, 2016. //%%%Chiaki Asai%%%, ``HMM-based speech synthesis system generating various speaking styles using audiobooks,'' Bachelor thesis, Nagoya institute of technology, 2015. &publication(2016/20160223_Thesis_Bachelor_Kenta_Murayama_paper.pdf, paper); &publication(2016/20160223_Thesis_Bachelor_Kenta_Murayama_slide.pptx, slide); &publication(2016/20160223_Thesis_Bachelor_Kenta_Murayama_abst.pdf, abst); + %%%水野隆%%%, ``話者識別におけるディープニューラルネットワークの適用法に関する検討,'' 卒業論文, 名古屋工業大学, 2016. //%%%Motoki Shikano%%%, ``A speech synthesis technique based on variable length frames using autoregressive HMMs,'' Bachelor thesis, Nagoya institute of technology, 2015. &publication(2016/20160223_Thesis_Bachelor_Takashi_Mizuno_paper.pdf, paper); &publication(2016/20160223_Thesis_Bachelor_Takashi_Mizuno_slide.pptx, slide); &publication(2016/20160223_Thesis_Bachelor_Takashi_Mizuno_abst.pdf, abst); + %%%保坂尚紀%%%, ``声質変換のための系列内変動を考慮したニューラルネットワークのトラジェクトリ学習,'' 卒業論文, 名古屋工業大学, 2016. //%%%Masahiro Hida%%%, ``Trajectory training of neural networks considering global variance for voice conversion,'' Bachelor thesis, Nagoya institute of technology, 2015. &publication(2016/20160223_Thesis_Bachelor_Naoki_hosaka_paper.pdf, paper); &publication(2016/20160223_Thesis_Bachelor_Naoki_hosaka_slide.pptx, slide); &publication(2016/20160223_Thesis_Bachelor_Naoki_hosaka_abst.pdf, abst); + %%%藤下太一%%%, ``周期成分の揺らぎを考慮した統計的励振源モデルに基づく音声合成手法,'' 卒業論文, 名古屋工業大学, 2016. //%%%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(2016/20160223_Thesis_Bachelor_Taichi_Fujishita_paper.pdf, paper); &publication(2016/20160223_Thesis_Bachelor_Taichi_Fujishita_slide.pptx, slide); &publication(2016/20160223_Thesis_Bachelor_Taichi_Fujishita_abst.pdf, abst); + %%%西村方成%%%, ``音高正規化を用いたディープニューラルネットワークに基づく歌声合成,'' 卒業論文, 名古屋工業大学, 2016. //%%%Masanari Nishimura%%%, ``Singing voice synthesis based on deep neural networks using pitch normalization,'' Bachelor thesis, Nagoya institute of technology, 2016. &publication(2016/20160223_Thesis_Bachelor_Masanari_Nishimura_paper.pdf, paper); &publication(2016/20160223_Thesis_Bachelor_Masanari_Nishimura_slide.pptx, slide); &publication(2016/20160223_Thesis_Bachelor_Masanari_Nishimura_abst.pdf, abst); + %%%鳥居靖広%%%, ``隠れマルコフモデルに基づく伴奏付き歌唱のモデル化と歌詞認識,'' 卒業論文, 名古屋工業大学, 2016. //%%%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(2016/20160223_Thesis_Bachelor_Yasuhiro_Torii_paper.pdf, paper); &publication(2016/20160223_Thesis_Bachelor_Yasuhiro_Torii_slide.pptx, slide); &publication(2016/20160223_Thesis_Bachelor_Yasuhiro_Torii_abst.pdf, abst); + %%%都築良成%%%, ``分離方格子HMMによる特徴量生成を用いた対数線形モデルに基づく画像認識,'' 卒業論文, 名古屋工業大学, 2016. //%%%Yoshinari Tsuzuki%%%, ``Image recognition based on log linear models using features generated from separable lattice HMMs,'' Bachelor thesis, Nagoya institute of technology, 2016. &publication(2016/20160223_Thesis_Bachelor_Yoshinari_Tsuzuki_paper.pdf, paper); &publication(2016/20160223_Thesis_Bachelor_Yoshinari_Tsuzuki_slide.pptx, slide); &publication(2016/20160223_Thesis_Bachelor_Yoshinari_Tsuzuki_abst.pdf, abst); + %%%伊神和輝%%%, ``HMM音声合成のためのオーディオブックを用いた学習コーパス自動構築,'' 卒業論文, 名古屋工業大学, 2016. //%%%Kazuki Igami%%%, ``Automatic construction of training corpus using audiobooks for HMM-based speech synthesis,'' Bachelor thesis, Nagoya institute of technology, 2016. &publication(2016/20160223_Thesis_Bachelor_Kazuki_Igami_paper.pdf, paper); &publication(2016/20160223_Thesis_Bachelor_Kazuki_Igami_slide.pptx, slide); &publication(2016/20160223_Thesis_Bachelor_Kazuki_Igami_abst.pdf, abst); + %%%鶴野高輝%%%, ``スペクトル・継続長・F0の同時モデル化に基づく声質変換,'' 修士論文, 名古屋工業大学, 2016. //%%%Kouki Tsuruno%%%, ``Voice conversion using a modified posterior probability function based on Gaussian mixture models,'' Bachelor thesis, Nagoya institute of technology, 2014. &publication(2016/20160215_Thesis_Master_Koki_Tsuruno_paper.pdf, paper); &publication(2016/20160215_Thesis_Master_Koki_Tsuruno_slide.pptx, slide); &publication(2016/20160215_Thesis_Master_Koki_Tsuruno_abst.pdf, abst); + %%%高松佳広%%%, ``特徴抽出とクラス識別を統合した単一統計モデルに基づく話者認識,'' 修士論文, 名古屋工業大学, 2016. //%%%Yoshihiro Takamatsu%%%, ``Efficient feature extraction based on generative models for speaker recognition,'' Bachelor thesis, Nagoya institute of technology, 2016. &publication(2016/20160215_Thesis_Master_Yoshihiro_Takamatsu_paper.pdf, paper); &publication(2016/20160215_Thesis_Master_Yoshihiro_Takamatsu_slide.pptx, slide); &publication(2016/20160215_Thesis_Master_Yoshihiro_Takamatsu_abst.pdf, abst); + %%%鈴木達也%%%, ``条件付確率場を用いた統計的学習に基づく音声の基本周波数推定,'' 修士論文, 名古屋工業大学, 2016. //%%%Tatsuya Suzuki%%%, ``A statistical approach to fundamental frequency estimation based on conditional random fields,'' Bachelor thesis, Nagoya institute of technology, 2016. &publication(2016/20160215_Thesis_Master_Tatsuya_Suzuki_paper.pdf, paper); &publication(2016/20160215_Thesis_Master_Tatsuya_Suzuki_slide.pptx, slide); &publication(2016/20160215_Thesis_Master_Tatsuya_Suzuki_abst.pdf, abst); + %%%助川正人%%%, ``パラメータ共有構造を有する混合分布を用いた分離型格子HMMによる画像認識,'' 修士論文, 名古屋工業大学, 2016. //%%%Masato Sukegawa%%%, ``Image recognition based on separable lattice HMMs using multiple model structures,'' Bachelor thesis, Nagoya institute of technology, 2014. &publication(2016/20160215_Thesis_Master_Masato_Sukegawa_paper.pdf, paper); &publication(2016/20160215_Thesis_Master_Masato_Sukegawa_slide.pptx, slide); &publication(2016/20160215_Thesis_Master_Masato_Sukegawa_abst.pdf, abst); + %%%佐藤雄介%%%, ``HMM音声合成のための最尤線形回帰と因子分析を統合した話者適応学習,'' 修士論文, 名古屋工業大学, 2016. //%%%Yusuke Sato%%%, `` A speaker adaptive training technique integrating maximum likelihood linear regression and factor analysis for HMM-based speech synthesis systems,'' Bachelor thesis, Nagoya institute of technology, 2016. &publication(2016/20160215_Thesis_Master_Yusuke_Sato_paper.pdf, paper); &publication(2016/20160215_Thesis_Master_Yusuke_Sato_slide.pptx, slide); &publication(2016/20160215_Thesis_Master_Yusuke_Sato_abst.pdf, abst); + %%%佐藤寛恭%%%, ``生成モデルの構造を考慮した階層識別モデルによる音声認識,'' 修士論文, 名古屋工業大学, 2016. //%%%Hirotaka Sato%%%, ``Speech recognition based on hierarchical discriminative models using statistics of generative models,'' Bachelor thesis, Nagoya institute of technology, 2014. &publication(2016/20160215_Thesis_Master_Hirotaka_Sato_paper.pdf, paper); &publication(2016/20160215_Thesis_Master_Hirotaka_Sato_slide.pptx, slide); &publication(2016/20160215_Thesis_Master_Hirotaka_Sato_abst.pdf, abst); + %%%神谷翔大%%%, ``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, 2016. //%%%Shota Kamiya%%%, ``Integration of high/low accent estimation, and acoustic modeling in HMM-based speech synthesis,'' Bachelor thesis, Nagoya institute of technology, 2014. &publication(2016/20160215_Thesis_Master_Shota_Kamiya_paper.pdf, paper); &publication(2016/20160215_Thesis_Master_Shota_Kamiya_slide.pptx, slide); &publication(2016/20160215_Thesis_Master_Shota_Kamiya_abst.pdf, abst); **Past Publications [#d97906db] #ls2(HOME/PUBLICATIONS,reverse);