#author("2025-11-11T11:13:09+00:00","default:spadmin","spadmin")
#author("2025-11-11T11:14:32+00:00","default:spadmin","spadmin")
* 発表論文 - 2025 [#j580b137]
#contents
** 論文誌 [#f00f28ab]
+ Takato Fujimoto, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, "V2Coder: A Non-Autoregressive Vocoder Based on Hierarchical Variational Autoencoders," in IEEE Access, vol. 13, pp. 92833-92847, 2025. (Full paper peer reviewed) [[link>https://ieeexplore.ieee.org/document/11014058]]
&publication(2025/20250523_Journal_Access_Takato_Fujimoto_paper.pdf, paper);
+ Sathvik Udupa,Jesuraja Bandekar,Abhayjeet Singh,Deekshitha G,Saurabh Kumar, and Sandhya Badiger, ``LIMMITS'24: Multi-Speaker, Multi-Lingual INDIC TTS With Voice Cloning'' in IEEE Open Journal of Signal Processing, vol. 6, pp. 293-302, 2025
[[link>https://ieeexplore.ieee.org/document/10845816]]
** 国際会議 [#r32cf446]
+ Haruto Kikuchi, Takashi Nose, Yu Hayashizaki, Sumiharu Kobayashi, Kei Hashimoto, and Akinori Ito, ``JAFS: Construction of Japanese Anime Face and Speech Dataset for Cross-Modal Speech Synthesis,'' 2025 IEEE 14th Global Conference on Consumer Electronics (GCCE), pp. 798-799, Osaka, Japan, September, 2025. (Full paper peer reviewed)
+ %%%Haruto Kikuchi%%%, Takashi Nose, Yu Hayashizaki, Sumiharu Kobayashi, Kei Hashimoto, and Akinori Ito, ``JAFS: Construction of Japanese Anime Face and Speech Dataset for Cross-Modal Speech Synthesis,'' 2025 IEEE 14th Global Conference on Consumer Electronics (GCCE), pp. 798-799, Osaka, Japan, September, 2025. (Full paper peer reviewed)
+ %%%Takenori Yoshimura%%%, Shinji Takaki, Kazuhiro Nakamura, Keiichiro Oura, Takato Fujimoto, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``SSLZip: Simple autoencoding for enhancing self-supervised speech representations in speech generation,'' 13th ISCA Speech Synthesis Workshop, pp. 117-122, Leeuwarden, Netherlands, August, 2025. (Full paper peer reviewed)
&publication(2025/20250825_IConference_SSW_Takenori_Yoshimura_paper.pdf, paper);
&publication(2025/20250825_IConference_SSW_Takenori_Yoshimura_poster.pdf, poster);
+ %%%Masato Takagi%%%, Miku Nishihara, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda, ``PeriodCodec: A Pitch-Controllable Neural Audio Codec Using Periodic Signals for Singing Voice Synthesis,'' Interspeech 2025, pp. 4913-4917, Rotterdam, Netherlands, August 17-21, 2025, (Full paper peer reviewed)
&publication(2025/20250821_IConference_Interspeech_Masato_Takagi_paper.pdf, paper);
&publication(2025/20250821_IConference_Interspeech_Masato_Takagi_poster.pdf, poster);
** 研究会 [#d111e1c5]
+ %%%山田美晴%%%, 橋本佳, 南角吉彦, 徳田恵一， ``対照学習による顔画像と音声のモデル化に基づくクロスモーダル音声合成,'' 音声言語情報処理研究会, vol. 2025-SLP-156, no. 61, pp. 1-8, 東京, 日本, 2025年6月.
&publication(2025/20250614_TReport_SLP_Miharu_Yamada_paper.pdf, paper);
+ %%%菊池遥斗%%%, 能勢隆, 林崎由, 小林清流, 橋本佳, 伊藤 彰則, ``F2S-SBV2：任意のアニメ調キャラクター顔画像に適した話者性を有するテキスト音声合成の検討,'' 音声言語情報処理研究会, vol. 2025-SLP-156, no. 71, pp. 1-7, 東京, 日本, 2025年6月
&publication(2025/20250614_TReport_SLP_Haruto_Kikuchi_paper.pdf, paper);
+ %%%中塚恭平%%%, 橋本佳, 南角吉彦, 徳田恵一，``注意機構により目標話者音声を直接的に参照するzero-shot音声合成,'' 音声研究会, vol. 124, no. 391, SP2024-29, pp. 70-75, 沖縄, 日本, 2025年3月.
&publication(2025/20250302_TReport_SP_Kyohei_Nakatsuka_paper.pdf, paper);
&publication(2025/20250302_TReport_SP_Kyohei_Nakatsuka_slide.pptx, slide);
+ %%%佐藤恵哉%%%, 橋本佳, 南角吉彦, 徳田恵一，``Deformable Convolutional Networks に基づく話者照合,'' 音声研究会, vol. 124, no. 391, SP2024-29, pp. 40-45, 沖縄, 日本, 2025年3月.
&publication(2025/20250302_TReport_SP_Keiya_Sato_paper.pdf, paper);
&publication(2025/20250302_TReport_SP_Keiya_Sato_slide.pptx, slide);
** 全国大会 [#na57a424]
+ %%%今村優太%%%, 法野行哉，吉村建慶，橋本佳, 南角吉彦, 徳田恵一，``メルケプストラム合成フィルタを用いた周期・非周期分離型ニューラルボコーダ,'' 日本音響学会2025年秋季研究発表会, pp.1177-1180, 宮城, 日本, 2025年9月.
&publication(2025/20250911_DConference_ASJA_Imamura_Yuta_paper.pdf, paper);
&publication(2025/20250911_DConference_ASJA_Imamura_Yuta_abst.pdf, abst);
&publication(2025/20250911_DConference_ASJA_Imamura_Yuta_slide.pptx, slide);
+ %%%苅谷楓%%%, 藤本崇人，橋本佳，南角吉彦，徳田恵一，``日本語テキスト音声合成のための高低アクセントの直接推定に関する検討,'' 日本音響学会2025年秋季研究発表会, pp.1131-1134, 宮城, 日本, 2025年9月.
&publication(2025/20250910_DConference_ASJA_Kariya_Kaede_paper.pdf, paper);
&publication(2025/20250910_DConference_ASJA_Kariya_Kaede_abst.pdf, abst);
&publication(2025/20250910_DConference_ASJA_Kariya_Kaede_slide.pptx, slide);
+ %%%淺野友紀%%%, 橋本佳, 南角吉彦, 徳田恵一，``Rectified Flowを組み込んだ深層隠れセミマルコフモデルに基づく音声合成,'' 日本音響学会2025年春季研究発表会, pp.883-886, 埼玉, 日本, 2025年3月.
&publication(2025/1-2-2_0301.pdf, paper);
&publication(2025/asano.yuki_asj2025_spring_paper_abst_2025_1_15_3_50.pdf, abst);
&publication(2025/asano.yuki_asj2025_spring_slide_2025_3_17_5_40.pptx, slide);
+ %%%堀尾凌汰%%%, 橋本佳, 南角吉彦, 徳田恵一，``感情音声合成のための自己教師あり学習モデルによる音声表現抽出,'' 日本音響学会2025年春季研究発表会, pp.897-900, 埼玉, 日本, 2025年3月.
&publication(2025/20250317_DConference_ASJS_Ryota_Horio_paper.pdf, paper);
&publication(2025/20250317_DConference_ASJS_Ryota_Horio_abst.pdf, abst);
&publication(2025/20250317_DConference_ASJS_Ryota_Horio_slide.pptx, slide);
+ %%%高木真人%%%, 西原美玖, 法野行哉, 橋本佳, 南角吉彦, 徳田恵一，``歌声合成に適したNeural Audio Codec構成法の検討,'' 日本音響学会2025年春季研究発表会, pp. 947-950, 埼玉, 日本, 2025年3月.
&publication(2025/20250318_DConference_ASJS_Masato_Takagi_paper.pdf, paper);
&publication(2025/20250318_DConference_ASJS_Masato_Takagi_slide.pptx, slide);
&publication(2025/20250318_DConference_ASJS_Masato_Takagi_abst.pdf, abst);
+ %%%薫田基広%%%, 藤本崇人, 法野行哉, 吉村建慶, 橋本佳, 南角吉彦, 徳田恵一，``周期信号の位相情報を用いたフレーム駆動形ニューラルボコーダ,'' 日本音響学会2025年春季研究発表会, pp. 905-908, 埼玉, 日本, 2025年3月.
&publication(2025/20250317_DConference_ASJS_Motohiro_Kunda_paper.pdf, paper);
&publication(2025/20250317_DConference_ASJS_Motohiro_Kunda_slide.pptx, slide);
&publication(2025/20250317_DConference_ASJS_Motohiro_Kunda_abst.pdf, abst);
+ %%%飯田諒%%%, 橋本佳, 南角吉彦, 徳田恵一，``双方向の自己回帰構造を導入した深層隠れセミマルコフモデルに基づく音声合成,'' 日本音響学会2025年春季研究発表会, pp. 887-890, 埼玉, 日本, 2025年3月.
&publication(2025/20250317_DConference_ASJS_Ryo_Iida_paper.pdf, paper);
&publication(2025/20250317_DConference_ASJS_Ryo_Iida_slide.pptx, slide);
&publication(2025/20250317_DConference_ASJS_Ryo_Iida_abst.pdf, abst);
+ %%%三宅恭平%%%,藤本崇人, 橋本佳, 南角吉彦, 徳田恵一，``発話単位の潜在変数を導入した深層隠れセミマルコフモデルに基づく音声合成,'' 日本音響学会2025年春季研究発表会, pp. 879-882, 埼玉, 日本, 2025年3月.
&publication(2025/20250317_DConference_ASJS_Kyohei_Miyake_paper.pdf, paper);
&publication(2025/20250317_DConference_ASJS_Kyohei_Miyake_slide.pptx, slide);
&publication(2025/20250317_DConference_ASJS_Kyohei_Miyake_abst.pdf, abst);
+ %%%田牧宏都%%%, 橋本佳, 南角吉彦, 徳田恵一，``自然言語による声質制御のための音声・声質説明文ペアデータの作成・評価システムの検討,'' 日本音響学会2025年春季研究発表会, pp. 1039-1040, 埼玉, 日本, 2025年3月.
&publication(2025/20250317_DConference_ASJS_Tamaki_Hiroto_paper.pdf, paper);
&publication(2025/20250317_DConference_ASJS_Tamaki_Hiroto_poster.pptx, poster);
&publication(2025/20250317_DConference_ASJS_Tamaki_Hiroto_abst.pdf, abst);
** 学位論文 [#na57a425]
+ %%%淺野友紀%%%,
``Rectified Flowと深層隠れセミマルコフモデルの統合に基づく音声合成,''
卒業論文, 名古屋工業大学, 2025年2月.
//%%%Motohiro Kunda%%%, ``Text-to-Speech Synthesis Based on a Deep Hidden Semi-Markov Model Incorporating Rectified Flow'' Bachelor thesis, Nagoya institute of technology, February, 2025.
&publication(2025/asano.yuki_bachelor.pdf, paper);
&publication(2025/asano.yuki_bachelor.pptx, slide);
&publication(2025/asano.yuki_abst.pdf, abst);
+ %%%薫田基広%%%,
``周期信号の初期位相情報を用いたフレーム駆動形ニューラルボコーダ,''
卒業論文, 名古屋工業大学, 2025年2月.
//%%%Motohiro Kunda%%%, ``Frame-Level Neural Vocoder Utilizing Initial Phase Information of Periodic Signals'' Bachelor thesis, Nagoya institute of technology, February, 2025.
&publication(2025/20250218_Thesis_Bachelor_Motohiro_Kunda_paper.pdf, paper);
&publication(2025/20250218_Thesis_Bachelor_Motohiro_Kunda_slide.pptx, slide);
&publication(2025/20250218_Thesis_Bachelor_Motohiro_Kunda_abst.pdf, abst);
+ %%%苅谷楓%%%,
``日本語テキスト音声合成のためのニューラルネットワークによるアクセント推定,''
卒業論文, 名古屋工業大学, 2025年2月.
//%%%Kaede Kariya%%%, ``Accent Estimation Using Neural Networks for Japanese Text-to-Speech Synthesis'' Bachelor thesis, Nagoya institute of technology, February, 2025.
&publication(2025/20250218_Thesis_Bachelor_Kaede_Kariya_paper.pdf, paper);
&publication(2025/20250218_Thesis_Bachelor_Kaede_Kariya_slide.pptx, slide);
&publication(2025/20250218_Thesis_Bachelor_Kaede_Kariya_abst.pdf, abst);
+ %%%柏木勇飛%%%,
``音声特徴を制御可能な深層隠れセミマルコフモデルに基づく音声合成における非周期性指標の適用,'' 卒業論文, 名古屋工業大学, 2025年2月.
//%%%Yuhi Kashiwagi%&%, ``Applying Aperiodicity Features to Controllable Speech Synthesis Based on Deep Hidden Semi-Markov Models'' Bachelor thesis, Nagoya institute of technology, February, 2025.
&publication(2025/20250218_Thesis_Bachelor_Yuhi_Kashiwagi_paper.pdf, paper);
&publication(2025/20250218_Thesis_Bachelor_Yuhi_Kashiwagi_slide.pptx, slide);
&publication(2025/20250218_Thesis_Bachelor_Yuhi_Kashiwagi_abst.pdf, abst);
+ %%%佐藤恵哉%%%,
``Deformable Convolutional Networks を用いた話者照合の検討,''
卒業論文, 名古屋工業大学, 2025年2月.
//%%%Keiya Sato%%%, ``Investigation of Speaker Verification Using Deformable Convolutional Networks'' Bachelor thesis, Nagoya institute of technology, February, 2025.
&publication(2025/20250218_Thesis_Bachelor_Keiya_Sato_paper.pdf, paper);
&publication(2025/20250218_Thesis_Bachelor_Keiya_Sato_slide.pptx, slide);
&publication(2025/20250218_Thesis_Bachelor_Keiya_Sato_abst.pdf, abst);
+ %%%今村優太%%%,
``微分可能なメルケプストラム合成フィルタを用いたニューラルボコーダ,''
卒業論文, 名古屋工業大学, 2025年2月.
//%%%Motohiro Kunda%%%, ``Neural Vocoder Embedding A DifferentiableMel-Cepstrum Synthesis Filter'' Bachelor thesis, Nagoya institute of technology, February, 2025.
&publication(2025/20250218_Thesis_Bachelor_Yuta_Imamura_paper.pdf, paper);
&publication(2025/20250218_Thesis_Bachelor_Yuta_Imamura_slide, slide);
&publication(2025/20250218_Thesis_Bachelor_Yuta_Imamura_abst.pdf, abst);
+ %%%井川恭輔%%%,
``SpecAugmentを用いたニューラルボコーダの学習法,''
卒業論文, 名古屋工業大学, 2025年2月.
//%%%Kyosuke Ikawa%%%, ``Training Methods for Neural Vocoders Using SpecAugment'' Bachelor thesis, Nagoya institute of technology, February, 2025.
&publication(2025/20250218_Thesis_Bachelor_Kyosuke_Ikawa_paper.pdf, paper);
&publication(2025/20250218_Thesis_Bachelor_Kyosuke_Ikawa_slide.pptx, slide);
&publication(2025/20250218_Thesis_Bachelor_Kyosuke_Ikawa_abst.pdf, abst);
+ %%%高木真人%%%,
``周期信号を用いた基本周波数制御可能なNeural Audio Codec構成法,''
卒業論文, 名古屋工業大学, 2025年2月.
//%%%Masato Takagi%%%, ``Neural Audio Codecs for Controlling Fundamental Frequency Using Periodic Signals'' Bachelor thesis, Nagoya institute of technology, February, 2025.
&publication(2025/20250224_Thesis_Bachelor_Masato_Takagi_paper.pdf, paper);
&publication(2025/20250224_Thesis_Bachelor_Masato_Takagi_slide.pptx, slide);
&publication(2025/20250224_Thesis_Bachelor_Masato_Takagi_abst.pdf, abst);
+ %%%山下敦生%%%,
``聴覚フィードバック制御を導入したリアルタイム声質変換のための自己発声骨導音のアクティブノイズキャンセリング,'' 卒業論文, 名古屋工業大学, 2025年2月.
//%%%Atsuki Yamashita%&%, ``Active Canceling of Self-voiced Bone-conducted Sounds for Real-time Voice Conversion with Auditory Feedback Control'' Bachelor thesis, Nagoya institute of technology, February, 2025.
&publication(2025/20250218_Thesis_Bachelor_Atsuki_Yamashita_paper.pdf, paper);
&publication(2025/20250218_Thesis_Bachelor_Atsuki_Yamashita_slide.pptx, slide);
&publication(2025/20250218_Thesis_Bachelor_Atsuki_Yamashita_abst.pdf, abst);
+ %%%川崎健生%%%,
``顔画像を用いたクロスモーダル音声合成における事前学習モデルの利用法の検討,''
卒業論文, 名古屋工業大学, 2025年2月.
//%%%Kensei Kawasaki%%%, ``Examining the Use of Pre-trained Models in Cross-modal Speech Synthesis from Facial Images'' Bachelor thesis, Nagoya institute of technology, February, 2025.
&publication(2025/20250218_Thesis_Bachelor_Kensei_Kawasaki_paper.pdf, paper);
&publication(2025/20250218_Thesis_Bachelor_Kensei_Kawasaki_slide.pptx, slide);
&publication(2025/20250218_Thesis_Bachelor_Kensei_Kawasaki_abst.pdf, abst);
+ %%%渡邊達哉%%%,
``Guided Attentionを組み込んだTransformer Decoderに基づく音声合成の検討,''
卒業論文, 名古屋工業大学, 2025年2月.
//%%%Tatsuya watanabe%%%, ``A Study on Speech Synthesis Based on Transformer Decoder with Guided Attention'' Bachelor thesis, Nagoya institute of technology, February, 2025.
&publication(2025/20250218_Thesis_Bachelor_Tatsuya_Watanabe_paper.pdf, paper);
&publication(2025/20250218_Thesis_Bachelor_Tatsuya_Watanabe_slide.pptx, slide);
&publication(2025/20250218_Thesis_Bachelor_Tatsuya_Watanabe_abst.pdf, abst);
+ %%%花井謙志郎%%%,
``ベクトル量子化変分オートエンコーダを用いた事前学習に基づく自動車操作信号からのドライバ状態推定,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Kenshiro Hanai%%%, ``Driver State Estimation from Automotive Operation Signals Based on Pre-Training Using Vector Quantized Variational Autoencoders'' Master thesis, Nagoya Institute of Technology, February, 2025.
&publication(2025/20250212_Thesis_Master_Kenshiro_Hanai_paper.pdf, paper);
&publication(2025/20250212_Thesis_Master_Kenshiro_Hanai_slide.pptx, slide);
&publication(2025/20250212_Thesis_Master_Kenshiro_Hanai_abst.pdf, abst);
+ %%%水野優%%%,
``大規模データによる自己教師あり学習モデルを用いた音声表現抽出に基づく話者照合,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Yu Mizuno%%%, ``Speaker Verification Based on Speech Representation Extraction Using Self-Supervised Learning Models Trained on Large-Scale Data'' Master thesis, Nagoya Institute of Technology, February, 2025.
&publication(2025/20250212_Thesis_Master_Yu_Mizuno_paper.pdf, paper);
&publication(2025/20250212_Thesis_Master_Yu_Mizuno_slide.pptx, slide);
&publication(2025/20250212_Thesis_Master_Yu_Mizuno_abst.pdf, abst);
+ %%%臼井嵩人%%%,
``深層隠れセミマルコフモデルに基づく音声合成における学習基準に関する検討,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Takato Usui%%%, ``A Study of Learning Criteria for Deep Hidden Semi-Markov Model Based Speech Synthesis'' Master thesis, Nagoya Institute of Technology, February, 2025.
&publication(2025/20250212_Thesis_Master_Takato_Usui_paper.pdf, paper);
&publication(2025/20250212_Thesis_Master_Takato_Usui_slide.pptx, slide);
&publication(2025/20250212_Thesis_Master_Takato_Usui_abst.pdf, abst);
+ %%%佐藤鈴夏%%%,
``特徴分離に基づいた基本周波数制御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, 2025年2月.
//%%%Suzuka Satoh%%%, ``Neural Vocoders Based on Disentangled Representation Learning for Controlling Fundamental Frequency'' Master thesis, Nagoya Institute of Technology, February, 2025.
&publication(2025/20250212_Thesis_Master_Suzuka_Sato_paper.pdf, paper);
&publication(2025/20250212_Thesis_Master_Suzuka_Sato_slide.pptx, slide);
&publication(2025/20250212_Thesis_Master_Suzuka_Sato_abst.pdf, abst);
+ %%%福田至音%%%,
``基本周波数の制御性を考慮した歌声合成のためのニューラルボコーダ学習法,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Shion Fukuda%%%, ``Neural Vocoder Training Methods for Singing Voice Synthesis Considering Controllability of Fundamental Frequencies,'' Master thesis, Nagoya institute of technology, February, 2024.
&publication(2025/20250210_Thesis_Master_Shion_Fukuda_paper.pdf, paper);
&publication(2025/20250210_Thesis_Master_Shion_Fukuda_slide.pptx, slide);
&publication(2025/20250210_Thesis_Master_Shion_Fukuda_abst.pdf, abst);
+ %%%勅使河原勇希%%%,
``深層隠れマルコフモデルに基づくEnd-to-End音声合成の検討,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Yuki Teshigawara%%%, ``A Study of End-to-End Speech Synthesis Based on Deep Hidden Semi-Markov Models,'' Master thesis, Nagoya institute of technology, February, 2024.
&publication(2025/20250210_Thesis_Master_Yuki_Teshigawara_paper.pdf, paper);
&publication(2025/20250210_Thesis_Master_Yuki_Teshigawara_slide.pptx, slide);
&publication(2025/20250210_Thesis_Master_Yuki_Teshigawara_abst.pdf, abst);
+ %%%長谷川郁弥%%%,
``自己教師あり学習による特徴抽出に基づいた深層学習に基づく歌声変換,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Ikuya Hasegawa%%%, ``Singing Voice Conversion Based On Self-surpervised Representation Learning'' Master thesis, Nagoya institute of technology, February, 2024.
&publication(2025/20250212_Thesis_Master_Ikuya_Hasegawa_paper.pdf, paper);
&publication(2025/20250212_Thesis_Master_Ikuya_Hasegawa_slide.pptx, slide);
&publication(2025/20250212_Thesis_Master_Ikuya_Hasegawa_abst.pdf, abst);
+ %%%長谷川太一%%%,
``顔画像を用いたクロスモーダル音声合成における半教師あり学習の検討,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Taichi Hasegawa%%%, ``Exploring Semi-Supervised Learning in Cross-Modal Speech Synthesis from Facial Images'' Master thesis, Nagoya institute of technology, February, 2024.
&publication(2025/20250210_Thesis_Master_Taichi_Hasegawa_paper.pdf, paper);
&publication(2025/20250210_Thesis_Master_Taichi_Hasegawa_slide.pptx, slide);
&publication(2025/20250210_Thesis_Master_Taichi_Hasegawa_abst.pdf, abst);
+ %%%堀尾凌汰%%%,
``感情音声合成のための自己教師あり学習モデルによる参照音声からの音声表現抽出,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Ryota Horio%%%, ``Emotional Speech Synthesis Based on Speech Representation Extraction from Reference Speech Using a Self-Supervised Learning Model'' Master thesis, Nagoya institute of technology, February, 2024.
&publication(2025/20250210_Thesis_Master_Ryota_Horio_paper.pdf, paper);
&publication(2025/20250210_Thesis_Master_Ryota_Horio_slide.pptx, slide);
&publication(2025/20250210_Thesis_Master_Ryota_Horio_abst.pdf, abst);
+ %%%山田洸太朗%%%,
``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ニューラル音声合成システムの敵対的学習,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Kotaro Yamada%%%, ``Adversarial Training of Neural Speech Synthesis Systems Embedding a Differentiable Mel-Cepstrum Synthesis Filter'' Master thesis, Nagoya institute of technology, February, 2024.
&publication(2025/20250210_Thesis_Master_Kotaro_Yamada_paper.pdf, paper);
&publication(2025/20250210_Thesis_Master_Kotaro_Yamada_slide.pptx, slide);
&publication(2025/20250210_Thesis_Master_Kotaro_Yamada_abst.pdf, abst);
+ %%%島崎秀太%%%,
``深層学習に基づく歌声に着目した楽曲推薦法の検討,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Shuta Shimazaki%%%, ``Investigation of Deep Learning based Music Recommendation Methods Focusing on Singing Voice Characteristics'' Master thesis, Nagoya institute of technology, February, 2024.
&publication(2025/20250210_Thesis_Master_Shuta_Shimazaki_paper.pdf, paper);
&publication(2025/20250210_Thesis_Master_Shuta_Shimazaki_slide.pptx, slide);
&publication(2025/20250210_Thesis_Master_Shuta_Shimazaki_abst.pdf, abst);
+ %%%中山航輔%%%,
``ニューラルオーディオコーデックに基づく音響信号の再生速度・ピッチの変換手法に関する検討,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Kosuke Nakayama%%%, ``Investigation of Neural Audio Codec Based Speech Conversion Methods for Controlling Playback Speed and Pitch of Acoustic Signals'' Master thesis, Nagoya institute of technology, February, 2024.
&publication(2025/20250210_Thesis_Master_Kosuke_Nakayama_paper.pdf, paper);
&publication(2025/20250210_Thesis_Master_Kosuke_Nakayama_slide.pptx, slide);
&publication(2025/20250210_Thesis_Master_Kosuke_Nakayama_abst.pdf, abst);
+ %%%小林悠佑%%%,
``階層化生成モデルに基づくEnd-to-End複数話者音声合成の検討,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Yusuke Kobayashi%%%, ``A Study of End-to-End Multi-Speaker Speech Synthesis Based on a Hierarchical Generative Model'' Master thesis, Nagoya institute of technology, February, 2025.
&publication(2025/20250210_Thesis_Master_Yusuke_Kobayashi_paper.pdf, paper);
&publication(2025/20250210_Thesis_Master_Yusuke_Kobayashi_slide.pptx, slide);
&publication(2025/20250210_Thesis_Master_Yusuke_Kobayashi_abst.pdf, abst);
+ %%%中邑草太%%%,
``オンラインコミュニケーションのための触覚・音声のクロスモーダルインタフェース,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Nakamura Sota%%%, ``A Haptic and Speech Cross-Modal Interface for Online Communication'' Master thesis, Nagoya institute of technology, February, 2025.
&publication(2025/20250210_Thesis_Master_Sota_Nakamura_paper.pdf, paper);
&publication(2025/20250210_Thesis_Master_Sota_Nakamura_slide.pptx, slide);
&publication(2025/20250210_Thesis_Master_Sota_Nakamura_abst.pdf, abst);
+ %%%中塚恭平%%%,
``注意機構を用いて目標話者音声を直接的に参照するzero-shot音声合成,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Nakatsuka Kyohei%%%, ``Zero-shot speech synthesis with direct reference to the target speaker’s voice using an attention mechanism'' Master thesis, Nagoya institute of technology, February, 2025.
&publication(2025/20250210_Thesis_Master_Kyohei_Nakatsuka_paper.pdf, paper);
&publication(2025/20250210_Thesis_Master_Kyohei_Nakatsuka_slide.pptx, slide);
&publication(2025/20250210_Thesis_Master_Kyohei_Nakatsuka_abst.pdf, abst);
+ %%%伊藤哲平%%%,
``言語特徴の潜在変数を用いた深層隠れセミマルコフモデルに基づく音声合成,''
修士論文, 名古屋工業大学, 2025年2月.
//%%%Teppei Ito%%%, ``Speech Synthesis Based on Deep Hidden Semi-Markov Models Using Linguistic Latent Variables'' Master thesis, Nagoya institute of technology, February, 2025.
&publication(2025/20250212_Thesis_Master_Teppei_Ito_paper.pdf, paper);
&publication(2025/20250212_Thesis_Master_Teppei_Ito_slide.pptx, slide);
&publication(2025/20250212_Thesis_Master_Teppei_Ito_abst.pdf, abst);
//** 講演 [#f58d14fc]
//** プレプリント [#t650b610]
//** 著書 [#t58b17b3]
//** その他 [#u12e6a23]
**過去の発表論文 [#ifa8da9a]
#ls2(ホーム/発表論文/,reverse);
