#author("2024-03-25T16:37:46+01:00","default:web","web")
* 発表論文 - 2022 [#h900a096]
#contents
//** 論文誌 [#f00f28ab]
** 国際会議 [#r32cf446]
+ %%%Kentaro Mitsui%%%, Tianyu Zhao, Kei Sawada, Yukiya Hono, Yoshihiko Nankaku, and Keiichi Tokuda, ``End-to-End Text-to-Speech Based on Latent Representation of Speaking Styles Using Spontaneous Dialogue,'' Interspeech 2022, pp. 2328–2332, Incheon, Korea, September, 2022. (Full paper peer reviewed, On-Site Special Session)
&publication(2022/20220920_IConference_Interspeech_Kentaro_Mitsui_paper.pdf, paper);
&publication(2022/20220920_IConference_Interspeech_Kentaro_Mitsui_poster.pdf, poster);
[[link (arXiv)>https://arxiv.org/abs/2206.12040]]
+ %%%Takato Fujimoto%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Autoregressive variational autoencoder with a hidden semi-Markov model-based structured attention for speech synthesis,'' 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 7462-7466, Singapore, Singapore, May, 2022. (Full paper peer reviewed)
&publication(2022/20220511_IConference_ICASSP_Takato_Fujimoto_paper.pdf, paper);
&publication(2022/20220511_IConference_ICASSP_Takato_Fujimoto_poster.pdf, poster);
&publication(2022/20220511_IConference_ICASSP_Takato_Fujimoto_slide.pptx, slide);
//** 研究会
** 全国大会 [#na57a424]
+ %%%西原美玖%%%, 法野行哉, 橋本佳, 南角吉彦, 徳田恵一,
``Sequence-to-sequence歌声合成のための発声タイミングのモデル化に関する検討,'' 日本音響学会2022年秋季研究発表会, pp. 1359-1362, 北海道, 日本, 2022年9月.
//%%%Miku Nishihara%%%, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``A study on vocal timing modeling for sequence-to-sequence singing voice synthesis,'' Acoustical Society of Japan 2022 Autumn Meeting, pp. 1359-1362, Hokkaido, Japan, September, 2022.
&publication(2022/20220916_DConference_ASJA_Miku_Nishihara_paper.pdf, paper);
&publication(2022/20220916_DConference_ASJA_Miku_Nishihara_abst.pdf, abst);
&publication(2022/20220916_DConference_ASJA_Miku_Nishihara_poster.pdf, poster);
&publication(2022/20220916_DConference_ASJA_Miku_Nishihara_slide.pptx, slide);
+ %%%石田龍成%%%, 藤本崇人, 橋本佳, 南角吉彦, 徳田恵一,
``隠れセミマルコフモデルに基づく構造化アテンションを用いた音声合成におけるパラメータ共有構造の検討,'' 日本音響学会2022年秋季研究発表会, pp. 1199-1202, 北海道, 日本, 2022年9月.
//%%%Ryusei Ishida%%%, Takato Fujimoto, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Parameter sharing structures in speech synthesis using structured attention based on a hidden semi-Markov model,'' Acoustical Society of Japan 2022 Autumn Meeting, pp. 1199-1202, Hokkaido, Japan, September, 2022.
&publication(2022/20220916_DConference_ASJA_Ryusei_Ishida_paper.pdf, paper);
&publication(2022/20220916_DConference_ASJA_Ryusei_Ishida_abst.pdf, abst);
&publication(2022/20220916_DConference_ASJA_Ryusei_Ishida_slide.pptx, slide);
+ %%%白木佑弥%%%, 橋本佳, 南角吉彦, 徳田恵一,
``デコーディング時の探索を考慮した系列識別学習によるEnd-to-End音声認識,'' 日本音響学会2022年秋季研究発表会, pp. 1141-1144, 北海道, 日本, 2022年9月.
//%%%Yuya Shiraki%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``End-to-end speech recognition with sequence discriminative training under constraints of decoding algorithms,'' Acoustical Society of Japan 2022 Autumn Meeting, pp. 1141-1144, Hokkaido, Japan, September, 2022.
&publication(2022/20220915_DConference_ASJA_Yuya_Shiraki_paper.pdf, paper);
&publication(2022/20220915_DConference_ASJA_Yuya_Shiraki_abst.pdf, abst);
&publication(2022/20220915_DConference_ASJA_Yuya_Shiraki_slide.pptx, slide);
+ %%%三井健太郎%%%, 趙天雨, 沢田慶, 法野行哉, 南角吉彦, 徳田恵一,
``自発的対話を用いた潜在スタイル表現の抽出・予測に基づく音声合成,'' 日本音響学会2022年秋季研究発表会, pp. 1593-1596, 北海道, 日本, 2022年9月. (スペシャルセッション)
//%%%Kentaro Mitsui%%%, Tianyu Zhao, Kei Sawada, Yukiya Hono, Yoshihiko Nankaku, and Keiichi Tokuda, ``Text-to-speech synthesis based on the extraction and prediction of latent speaking style representation using spontaneous dialogue,'' Acoustical Society of Japan 2022 Autumn Meeting, pp. 1589-1592, Hokkaido, Japan, September, 2022. (Special session)
&publication(2022/20220914_DConference_ASJA_Kentaro_Mitsui_paper.pdf, paper);
+ %%%法野行哉%%%, 橋本佳, 南角吉彦, 徳田恵一,
``Sequence-to-sequence歌声合成のための音符位置に基づくアテンション機構の検討,'' 日本音響学会2022年秋季研究発表会, pp. 1589-1592, 北海道, 日本, 2022年9月. (スペシャルセッション)
//%%%Yukiya Hono%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``A study on musical note position-aware attention mechanism for sequence-to-sequence singing voice synthesis,'' Acoustical Society of Japan 2022 Autumn Meeting, pp. 1589-1592, Hokkaido, Japan, September, 2022. (Special session)
&publication(2022/20220914_DConference_ASJA_Yukiya_Hono_paper.pdf, paper);
&publication(2022/20220914_DConference_ASJA_Yukiya_Hono_abst.pdf, abst);
&publication(2022/20220914_DConference_ASJA_Yukiya_Hono_slide.pptx, slide);
+ %%%吉村建慶%%%, 高木信二, 中村和寛, 大浦圭一郎, 法野行哉, 橋本佳, 南角吉彦, 徳田恵一,
``微分可能なメルケプストラム合成フィルタを組み込んだend-to-end 音声合成システムの検討,'' 日本音響学会2022年秋季研究発表会, pp. 1585-1588, 北海道, 日本, 2022年9月.
//%%%Takenori Yoshimura%%%, Shinji Takaki, Kazuhiro Nakamura, Keiichiro Oura, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Embedding a differentiable mel-cepstral synthesis filter to an end-to-end speech synthesis system,'' Acoustical Society of Japan 2022 Autumn Meeting, pp. 1585-1588, Hokkaido, Japan, September, 2022.
&publication(2022/20220914_DConference_ASJA_Takenori_Yoshimura_paper.pdf, paper);
&publication(2022/20220914_DConference_ASJA_Takenori_Yoshimura_abst.pdf, abst);
&publication(2022/20220914_DConference_ASJA_Takenori_Yoshimura_slide.pptx, slide);
+ %%%藤本崇人%%%, 橋本佳, 南角吉彦, 徳田恵一,
``半教師あり学習を用いた階層化生成モデルに基づく日本語 end-to-end 音声合成,'' 日本音響学会2022年秋季研究発表会, pp. 1579-1582, 北海道, 日本, 2022年9月. (スペシャルセッション)
``半教師あり学習を用いた階層化生成モデルに基づく日本語 end-to-end 音声合成,'' 日本音響学会2022年秋季研究発表会, pp. 1579-1582, 北海道, 日本, 2022年9月. (スペシャルセッション) (第7回 IEEE Signal Processing Society Tokyo Joint Chapter Student Award受賞 [[link>https://www.ieee-jp.org/section/tokyo/chapter/SP-01/sp.htm#HYOUSHOU]])
//%%%Takato Fujimoto%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Japanese end-to-end speech synthesis based on hierarchical generative models using semi-supervised learning,'' Acoustical Society of Japan 2022 Autumn Meeting, pp. 1579-1582, Hokkaido, Japan, September, 2022. (Special session)
&publication(2022/20220914_DConference_ASJA_Takato_Fujimoto_paper.pdf, paper);
&publication(2022/20220914_DConference_ASJA_Takato_Fujimoto_abst.pdf, abst);
&publication(2022/20220914_DConference_ASJA_Takato_Fujimoto_slide.pptx, slide);
+ %%%法野行哉%%%, 高木信二, 橋本佳, 中村和寛, 大浦圭一郎, 南角吉彦, 徳田恵一,
``非周期性指標を考慮したニューラルボコーダの学習,'' 日本音響学会2022年春季研究発表会, pp. 973-976, 日本, 2022年3月. (オンライン開催, 粟屋潔学術奨励賞)
//%%%Yukiya Hono%%%, Shinji Takaki, Kei Hashimoto, Kazuhiro Nakamura, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Neural vocoder training considering the aperiodic measure,'' Acoustical Society of Japan 2022 Spring Meeting, pp. 973-976, Japan, March, 2022. (Awaya Prize Young Researcher Award)
&publication(2022/20220311_DConference_ASJS_Yukiya_Hono_paper.pdf, paper);
&publication(2022/20220311_DConference_ASJS_Yukiya_Hono_abst.pdf, abst);
&publication(2022/20220311_DConference_ASJS_Yukiya_Hono_slide.pptx, slide);
+ %%%藤本崇人%%%, 橋本佳, 南角吉彦, 徳田恵一,
``HSMM構造化アテンションに基づく音声合成のためのメモリ削減手法,'' 日本音響学会2022年春季研究発表会, pp. 969-972, 日本, 2022年3月.
//%%%Takato Fujimoto%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Memory reduction methods for sequence-to-sequence speech synthesis using a hidden semi-Markov model based structured attention mechanism,'' Acoustical Society of Japan 2022 Spring Meeting, pp. 969-972, Japan, March, 2022.
&publication(2022/20220311_DConference_ASJS_Takato_Fujimoto_paper.pdf, paper);
&publication(2022/20220311_DConference_ASJS_Takato_Fujimoto_abst.pdf, abst);
&publication(2022/20220311_DConference_ASJS_Takato_Fujimoto_slide.pptx, slide);
(オンライン開催)
+ %%%佐々木一匡%%%, 吉村建慶, 高木信二, 橋本佳, 南角吉彦, 徳田恵一,
``声質・声の高さ・話速を変更可能なニューラルボコーダ構成法の検討,'' 日本音響学会2022年春季研究発表会, pp. 935-938, 日本, 2022年3月.
//%%%Kazumasa Sasaki%%%, Takenori Yoshimura, Shinji Takaki, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Neural vocoders which can control voice characteristics, average pitch and speaking rate,'' Acoustical Society of Japan 2022 Spring Meeting, pp. xx-xx, Japan, March, 2022.
&publication(2022/20220309_DConference_ASJS_Kazumasa_Sasaki_paper.pdf, paper);
&publication(2022/20220309_DConference_ASJS_Kazumasa_Sasaki_abst.pdf, abst);
&publication(2022/20220309_DConference_ASJS_Kazumasa_Sasaki_slide.pptx, slide);
(オンライン開催)
+ %%%平光啓祐%%%, 橋本佳, 南角吉彦, 徳田恵一,
``深層学習に基づく音声合成における顔画像情報を用いたクロスモーダル話者適応,'' 日本音響学会2022年春季研究発表会, pp. 905-906, 日本, 2022年3月.
//%%%Keisuke Hiramitsu%%%, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Cross-Modal Speaker Adaptation Using Face Image Information in Speech Synthesis Based on Deep Learning,'' Acoustical Society of Japan 2022 Spring Meeting, pp. xx-xx, Japan, March, 2022.
&publication(2022/20220309_DConference_ASJS_Keisuke_Hiramitsu_paper.pdf, paper);
&publication(2022/20220309_DConference_ASJS_Keisuke_Hiramitsu_abst.pdf, abst);
&publication(2022/20220309_DConference_ASJS_Keisuke_Hiramitsu_slide.pptx, slide);
(オンライン開催)
** 学位論文 [#na57a425]
+ %%%Yukiya Hono%%%,
``Acoustic and waveform modeling for singing voice synthesis based on deep neural networks,''
Doctor thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220228_Thesis_Doctor_Yukiya_Hono_paper.pdf, paper);
&publication(2022/20220228_Thesis_Doctor_Yukiya_Hono_slide.pptx, slide);
+ %%%谷口晃平%%%,
``デコーディング時を想定したEnd-to-End音声認識における系列識別学習のための損失関数の改良''
卒業論文, 名古屋工業大学, 2022年2月.
//%%% %%%, ``END-TO-END SPEECH RECOGNITION WITH IMPROVED LOSS FUNCTION ON SEQUENCE DISCRIMINATIVE TRAINING IN DECODING,'' February, 2022.
&publication(2022/20220215_Thesis_Bachelor_Kohei_Taniguchi_paper.pdf, paper);
&publication(2022/20220215_Thesis_Bachelor_Kohei_Taniguchi_slide.pptx, slide);
&publication(2022/20220215_Thesis_Bachelor_Kohei_Taniguchi_abst.pdf, abst);
+ %%%田中琉聖%%%,
``自己教師あり学習による特徴抽出を用いたノンパラレル歌声声質変換の検討''
卒業論文, 名古屋工業大学, 2022年2月.
//%%% %%%, ``NON-PARALLEL SINGING VOICE CONVERSION USING FEATURE EXTRACTION WITH SELF-SUPERVISED LEARNING,'' February, 2022.
&publication(2022/20220215_Thesis_Bachelor_Ryusei_Tanaka_paper.pdf, paper);
&publication(2022/20220215_Thesis_Bachelor_Ryusei_Tanaka_slide.pptx, slide);
&publication(2022/20220215_Thesis_Bachelor_Ryusei_Tanaka_abst.pdf, abst);
+ %%%鈴木涼%%%,
``Variational AutoEncoderに基づく声質変換における潜在変数表現の検討''
卒業論文, 名古屋工業大学, 2022年2月.
//%%% %%%, ``OPTIMAL lATENT VARIABLES OF VARIATIONAL AUTOENCODER IN VOICE CONVERSION ,'' February, 2022.
&publication(2022/20220215_Thesis_Bachelor_Ryo_Suzuki_paper.pdf, paper);
&publication(2022/20220215_Thesis_Bachelor_Ryo_Suzuki_slide.pptx, slide);
&publication(2022/20220215_Thesis_Bachelor_Ryo_Suzuki_abst.pdf, abst);
+ %%%石田龍成%%%,
``隠れセミマルコフモデルを用いた構造化アテンションに基づく音声合成におけるパラメータ共有構造の検討,''
卒業論文, 名古屋工業大学, 2022年2月.
//%%% %%%, ``A PARAMETER SHARING STRUCTURE IN SPEECH SYNTHESIS BASED ON STRUCTURED ATTENTION USING A HIDDEN SEMI-MARKOV MODEL,'' February, 2022.
&publication(2022/20220215_Thesis_Bachelor_Ryusei_Ishida_paper.pdf, paper);
&publication(2022/20220215_Thesis_Bachelor_Ryusei_Ishida_slide.pptx, slide);
&publication(2022/20220215_Thesis_Bachelor_Ryusei_Ishida_abst.pdf, abst);
+ %%%伊藤天良%%%,
``リアルタイム歌声変換のためのピッチ・音圧変換聴覚フィードバックの検討,''
卒業論文, 名古屋工業大学, 2022年2月.
//%%% %%%, ``A STUDY ON PITCH AND SOUND PRESSURE TRANSFORMED AUDITORY FEEDBACK FOR REAL-TIME SINGING VOICE CONVERSION,'' February, 2022.
&publication(2022/20220215_Thesis_Bachelor_Takara_Ito_paper.pdf, paper);
&publication(2022/20220215_Thesis_Bachelor_Takara_Ito_slide.pptx, slide);
&publication(2022/20220215_Thesis_Bachelor_Takara_Ito_abst.pdf, abst);
+ %%%西原美玖%%%,
``Sequence-to-sequence歌声合成における発声タイミングのモデル化手法,''
卒業論文, 名古屋工業大学, 2022年2月.
//%%%Miku Nishihara%%%, `` VOCAL TIMING MODELING METHOD IN SEQUENCE-TO-SEQUENCE SINGING VOICE SYNTHESIS,'' Bachelor thesis, Nagoya institute of technology, February, 2022.
&publication(2022/20220215_Thesis_Bachelor_Miku_Nishihara_paper.pdf, paper);
&publication(2022/20220215_Thesis_Bachelor_Miku_Nishihara_slide.pptx, slide);
&publication(2022/20220215_Thesis_Bachelor_Miku_Nishihara_abst.pdf, abst);
+ %%%倉田颯人%%%,
``隠れセミマルコフモデルの構造を導入したDNNに基づく音声合成におけるクロスリンガル話者適応,''
卒業論文, 名古屋工業大学, 2022年2月.
//%%% %%%, ``CROSS-LINGUAL SPEAKER ADAPTATION IN SPEECH SYNTHESIS BASED ON DEEP NEURAL NETWORKS INTRODUCING HIDDEN SEMI-MARKOV MODEL STRUCTURES,'' Bachelor thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220215_Thesis_Bachelor_Hayato_Kurata_paper.pdf, paper);
&publication(2022/20220215_Thesis_Bachelor_Hayato_Kurata_slide.pptx, slide);
&publication(2022/20220215_Thesis_Bachelor_Hayato_Kurata_abst.pdf, abst);
+ %%%須内翔%%%,
``隠れセミマルコフモデルに基づく構造化アテンションを用いた音声合成におけるモデル化単位の検討,''
卒業論文, 名古屋工業大学, 2022年2月.
//%%% %%%, ``A MODELING UNIT IN SPEECH SYNTHESIS BASED ON STRUCTURED ATTENTION USING A HIDDEN SEMI-MARKOV MODEL,'' Bachelor thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220215_Thesis_Bachelor_Sho_Sunouchi_paper.pdf, paper);
&publication(2022/20220215_Thesis_Bachelor_Sho_Sunouchi_slide.pptx, slide);
&publication(2022/20220215_Thesis_Bachelor_Sho_Sunouchi_abst.pdf, abst);
+ %%%中塚恭平%%%,
``敵対的生成モデルに基づく音声合成におけるテキストデータを利用した半教師あり学習法,''
卒業論文, 名古屋工業大学, 2022年2月.
//%%% %%%, ``A Semi-Supervised Learning Method Using Text Data for Speech Synthesis Based on Generative Adversarial Networks ,'' Bachelor thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220215_Thesis_Bachelor_Kyohei_Nakatsuka_paper.pdf, paper);
&publication(2022/20220215_Thesis_Bachelor_Kyohei_Nakatsuka_slide.pptx, slide);
&publication(2022/20220215_Thesis_Bachelor_Kyohei_Nakatsuka_abst.pdf, abst);
+ %%%中村朋生%%%,
``触覚情報を入力としたクロスモーダル感情音声合成,''
卒業論文, 名古屋工業大学, 2022年2月.
//%%%Tomoki Nakamura%%%, ``CROSS-MODAL EMOTIONAL SPEECHSYNTHESIS USING TACTILE INFORMATIONAS INPUT,'' Bachelor thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220215_Thesis_Bachelor_Tomoki_Nakamura_paper.pdf, paper);
&publication(2022/20220215_Thesis_Bachelor_Tomoki_Nakamura_slide.pptx, slide);
&publication(2022/20220215_Thesis_Bachelor_Tomoki_Nakamura_abst.pdf, abst);
+ %%%片山優太%%%,
``深層距離学習を導入したSequential Variational Autoencoderに基づく話者照合,''
卒業論文, 名古屋工業大学, 2022年2月.
//%%%Yuta Katayama%%%, ``SPEAKER VERIFICATION BASED ON SEQUENTIAL VARIATIONAL AUTOENCODER INTRODUCING DEEP METRIC LEARNING,'' Bachelor thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220215_Thesis_Bachelor_Yuta_Katayama_paper.pdf, paper);
&publication(2022/20220215_Thesis_Bachelor_Yuta_Katayama_slide.pptx, slide);
&publication(2022/20220215_Thesis_Bachelor_Yuta_Katayama_abst.pdf, abst);
+ %%%都築伸武%%%,
``周波数ワーピングに基づいた声質変更を可能とするニューラルボコーダ構成法,''
卒業論文, 名古屋工業大学, 2022年2月.
//%%%Nobutake Tsuzuki%%%, ``NEURAL VOCODER CONFIGURATION METHOD THAT ENABLES VOICE QUALITY CHANGE BASED ON FREQUENCY WARPING,'' Bachelor thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220215_Thesis_Bachelor_Nobutake_Tsuzuki_paper.pdf, paper);
&publication(2022/20220215_Thesis_Bachelor_Nobutake_Tsuzuki_slide.pptx, slide);
&publication(2022/20220215_Thesis_Bachelor_Nobutake_Tsuzuki_abst.pdf, abst);
+ %%%堀尾凌汰%%%,
``Transformerに基づくEnd-to-End音声合成における最適モデル構造の検討,''
卒業論文, 名古屋工業大学, 2022年2月.
//%%%Ryota Horio%%%, ``OPTIMIZING MODEL STRUCTURES OF END-TO-END SPEECH SYNTHESIS BASED ON TRANSFORMER NETWORK,'' Bachelor thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220215_Thesis_Bachelor_Ryota_Horio_paper.pdf, paper);
&publication(2022/20220215_Thesis_Bachelor_Ryota_Horio_slide.pptx, slide);
&publication(2022/20220215_Thesis_Bachelor_Ryota_Horio_abst.pdf, abst);
+ %%%川村莉子%%%,
``Sequential Variational Autoencoderに基づく話者認識における半教師あり学習法,''
卒業論文, 名古屋工業大学, 2022年2月.
//%%%Riko Kawamura%%%, `` A SEMI-SUPERVISED LEARNING METHOD FOR SPEAKER RECOGNITION BASED ON SEQUENTIAL VARIATIONAL AUTOENCODER,'' Bachelor thesis, Nagoya institute of technology, February, 2022.
&publication(2022/20220215_Thesis_Bachelor_Riko_Kawamura_paper.pdf, paper);
&publication(2022/20220215_Thesis_Bachelor_Riko_Kawamura_slide.pptx, slide);
&publication(2022/20220215_Thesis_Bachelor_Riko_Kawamura_abst.pdf, abst);
+ %%%車田智哉%%%,
``生成モデルの構造を組み込んだSequential Variational Autoencoderに基づく話者認識,'' 修士論文, 名古屋工業大学, 2022年2月.
//%%% Tomoya Kurumada %%%, ``SPEAKER RECOGNITION BASED ON SEQUENTIAL VARIATIONAL AUTOENCODERS INCOPORATING STRUCTURES OF GENERATIVE MODELS, Master thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220209_Thesis_Master_Tomoya_Kurumada_paper.pdf, paper);
&publication(2022/20220209_Thesis_Master_Tomoya_Kurumada_slide.pptx, slide);
&publication(2022/20220209_Thesis_Master_Tomoya_Kurumada_abst.pdf, abst);
+ %%%岩田康平%%%,
``勾配ブースティング決定木を用いた音声合成手法,''
修士論文, 名古屋工業大学, 2022年2月.
//%%% %%%, ``SPEECH SYNTHESIS BASED ON GRADIENT BOOSTING DECISION TREES,'' February, 2022.
&publication(2022/20220209_Thesis_Master_Kohei_Iwata_paper.pdf, paper);
&publication(2022/20220209_Thesis_Master_Kohei_Iwata_slide.pptx, slide);
&publication(2022/20220209_Thesis_Master_Kohei_Iwata_abst.pdf, abst);
+ %%%厚地俊哉%%%,
``音声プライバシー保護を目的としたノンパラレル声質変換による話者匿名化,''
修士論文, 名古屋工業大学, 2022年2月.
//%%% Shunya Atsuchi %%%, ``SPEAKER ANONYMIZATION USING NON-PARALLEL VOICE CONVERSION FOR SPEECH PRIVACY PROTECTION, Master thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220209_Thesis_Master_Shunya_Atsuchi_paper.pdf, paper);
&publication(2022/20220209_Thesis_Master_Shunya_Atsuchi_slide.pptx, slide);
&publication(2022/20220209_Thesis_Master_Shunya_Atsuchi_abst.pdf, abst);
+ %%%成田哲郎%%%,
``ニューラルネットワークを用いた音声符号化におけるモデル構造の調査,''
修士論文, 名古屋工業大学, 2022年2月.
//%%% Tetsuro Narita %%%, ``INVESTIGATION OF MODEL STRUCTURES IN SPEECH CODING BASED ON NEURAL NETWORKS, Master thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220209_Thesis_Master_Tetsuro_Narita_paper.pdf, paper);
&publication(2022/20220209_Thesis_Master_Tetsuro_Narita_slide.pptx, slide);
&publication(2022/20220209_Thesis_Master_Tetsuro_Narita_abst.pdf, abst);
+ %%%前川遼太朗%%%,
``楽譜情報を用いた統計的楽器演奏音合成の検討,''
修士論文, 名古屋工業大学, 2022年2月.
//%%% %%%, ``STATISTICAL INSTRUMENT-PLAYING SOUND SYNTHESIS FROM MUSICAL SCORES, 2022.
&publication(2022/20220209_Thesis_Master_Ryotaro_Maekawa_paper.pdf, paper);
&publication(2022/20220209_Thesis_Master_Ryotaro_Maekawa_slide.pptx, slide);
&publication(2022/20220209_Thesis_Master_Ryotaro_Maekawa_abst.pdf, abst);
+ %%%西村愛理%%%,
``出力遅延と時間伸縮変換を考慮したリアルタイム声質変換,''
修士論文, 名古屋工業大学, 2022年2月.
//%%%Airi Nishimura%%%, ``REAL-TIME VOICE CONVERSION CONSIDERING OUTPUT LATENCY AND TIME-WARPING TRANSFORMATION, Master thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220209_Thesis_Master_Airi_Nishimura_paper.pdf, paper);
&publication(2022/20220209_Thesis_Master_Airi_Nishimura_slide.pptx, slide);
&publication(2022/20220209_Thesis_Master_Airi_Nishimura_abst.pdf, abst);
+ %%%佐々木一匡%%%,
``声質・声の高さ・話速を変更可能なニューラルボコーダ構成法,''
修士論文, 名古屋工業大学, 2022年2月.
//%%%Kazumasa Sasaki%%%, ``NEURAL VOCODERS WHICH CAN CONTROL VOICE CHARACTERISTICS, AVERAGE PITCH AND SPEAKING RATE , Master thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220209_Thesis_Master_Kazumasa_Sasaki_paper.pdf, paper);
&publication(2022/20220209_Thesis_Master_Kazumasa_Sasaki_slide.pptx, slide);
&publication(2022/20220209_Thesis_Master_Kazumasa_Sasaki_abst.pdf, abst);
+ %%%平光啓祐%%%,
``深層学習に基づく音声合成における顔画像を用いたクロスモーダル話者適応,''
修士論文, 名古屋工業大学, 2022年2月.
//%%%Keisuke Hiramitsu%%%, ``CROSS-MODAL SPEAKER ADAPTATION USING FACE IMAGES IN SPEECH SYNYHESIS BASED ON DEEP LEARNING , Master thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220209_Thesis_Master_Keisuke_Hiramitsu_paper.pdf, paper);
&publication(2022/20220209_Thesis_Master_Keisuke_Hiramitsu_slide.pptx, slide);
&publication(2022/20220209_Thesis_Master_Keisuke_Hiramitsu_abst.pdf, abst);
+ %%%久野宏彰%%%,
``音声合成における希少な発話スタイルの転移学習,''
修士論文, 名古屋工業大学, 2022年2月.
//%%%Hiroaki Kuno%%%, ``TRANSFER LEARNING OF RARE SPEAKING STYLES IN SPEECH SYNTHESIS , Master thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220209_Thesis_Master_Hiroaki_Kuno_paper.pdf, paper);
&publication(2022/20220209_Thesis_Master_Hiroaki_Kuno_slide.pptx, slide);
&publication(2022/20220209_Thesis_Master_Hiroaki_Kuno_abst.pdf, abst);
+ %%%木村俊介%%%,
``幾何学的変動に頑健な画像認識のためのAttention機構に基づく深層学習モデル,''
修士論文, 名古屋工業大学, 2022年2月.
//%%%Shunsuke Kimura%%%, ``DEEP NEURAL NETWORKS BASED ON ATTENTION MECHANISMS FOR ROBUST IMAGE RECOGNITION AGAINST GEOMETRIC VARIATIONS,'' Master thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220209_Thesis_Master_Shunsuke_Kimura_paper.pdf, paper);
&publication(2022/20220209_Thesis_Master_Shunsuke_Kimura_slide.pptx, slide);
&publication(2022/20220209_Thesis_Master_Shunsuke_Kimura_abst.pdf, abst);
+ %%%大谷眞史%%%,
``深層生成モデルに基づく音声合成におけるクロスリンガル話者適応,''
修士論文, 名古屋工業大学, 2022年2月.
//%%%Masafumi Otani%%%, ``CROSS-LINGUAL SPEAKER ADAPTATION IN SPEECH SYNTHESIS BASED ON DEEP GENERATIVE MODELS,'' Master thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220209_Thesis_Master_Masafumi_Otani_paper.pdf, paper);
&publication(2022/20220209_Thesis_Master_Masafumi_Otani_slide.pptx, slide);
&publication(2022/20220209_Thesis_Master_Masafumi_Otani_abst.pdf, abst);
+ %%%小林睦%%%,
``車内音声対話のための統計モデルに基づくドライバ認知負荷推定,''
修士論文, 名古屋工業大学, 2022年2月.
//%%%Atsushi Kobayashii%%%, ``ESTIMATION OF DRIVER COGNITIVE LOAD BASED ON STATISTICAL MODELS FOR VOICE INTERACTION IN AUTOMOBILES,'' Master thesis, Nagoya Institute of Technology, February, 2022.
&publication(2022/20220209_Thesis_Master_Atsushi_Kobayashi_paper.pdf, paper);
&publication(2022/20220209_Thesis_Master_Atsushi_Kobayashi_slide.pptx, slide);
&publication(2022/20220209_Thesis_Master_Atsushi_Kobayashi_abst.pdf, abst);
** 講演 [#f58d14fc]
+ 徳田恵一, ``音声合成技術の発展と未来 －個人的視点から雑談風に,'' JST CREST「共創型音メディア機能拡張」中間シンポジウム 2022, December, 2022.（招待講演）
//20221217
** プレプリント [#t650b610]
+ Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Singing Voice Synthesis Based on a Musical Note Position-Aware Attention Mechanism,'' arXiv preprint arXiv:2102.07786, December, 2022.
&publication(2022/20221228_Preprint_arXiv_Yukiya_Hono_paper.pdf, paper);
[[link>https://arxiv.org/abs/2212.13703]]
+ Takenori Yoshimura, Shinji Takaki, Kazuhiro Nakamura, Keiichiro Oura, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Embedding a differentiable mel-cepstral synthesis filter to a neural speech synthesis system,'' arXiv preprint arXiv:2211.11222, November, 2022.
&publication(2022/20221121_Preprint_arXiv_Takenori_Yoshimura_paper.pdf, paper);
[[link>https://arxiv.org/abs/2211.11222]]
+ Kentaro Mitsui, Tianyu Zhao, Kei Sawada, Yukiya Hono, Yoshihiko Nankaku, and Keiichi Tokuda, ``End-to-End Text-to-Speech Based on Latent Representation of Speaking Styles Using Spontaneous Dialogue,'' arXiv preprint arXiv:2108.02776, June, 2022.
&publication(2022/20220624_Preprint_arXiv_Kentaro_Mitsui_paper.pdf, paper);
[[link>https://arxiv.org/abs/2206.12040]]
//** 著書 [#t58b17b3]
//** その他 [#u12e6a23]
**過去の発表論文 [#ifa8da9a]
#ls2(ホーム/発表論文/,reverse);
