Doctor(Engineering) Toyohashi University of Technology 1996/3 |
Informatics - Intelligent informatics Informatics - Perceptual information processing Informatics - Human interface and interaction |
Automatic Speech Recognition and Spoken Language Processing (SLP) Systems Robust Speech Recognition and Spoken Document Retrieval Systems Automatic Captioning and SLP for Lecture Recording and Multimedia Data Utilization Imagined Speech Recognition by Brainwave Signal |
Automatic Speech Recognition and Retrieval for Spontaneous Speech, Spoken Language Processing System, Automatic Speech Recognition for Noisy and Distant Speech, Automatic Captioning and Lecture Understanding Support System, Deep Learning Model for Speech and Language Processing, Imagined Speech Recognition by Brainwave Signal |
・IEEE
|
https://higo.msys.eng.shizuoka.ac.jp/ |
[1]. 1.音声メディア利活用のための音声情報処理技術/2.遠隔マイク収録や雑音環境下を想定した適応学習や自動字幕化支援技術 ( 2019(FY) - ) [Category] 7.地域連携 [URL] |
[1]. Adapting Large-Scale Pre-trained Models for Unified Dialect Speech Recognition Model Acta Physica Polonica A 146/4 413-418 (2024) [Refereed] refereed [Internationally co-authored papers] non-internationally co-authored paper [Lead author or co-author] author [Author] Takumi Toyama, Atsuhiko Kai, Yuta Kamiya, Naoki Takahashi [URL] [DOI] [2]. A Parameter-Efficient Multi-Step Fine-Tuning of Multilingual and Multi-Task Learning Model for Japanese Dialect Speech Recognition Proc. 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA) / 1-6 (2024) [Refereed] refereed [Internationally co-authored papers] non-internationally co-authored paper [Lead author or co-author] author [Author] Yuta Kamiya, Shogo Miwa, Atsuhiko Kai [URL] [DOI] [3]. Comparison of Large Pre-trained Models and Adaptation Methods for Japanese Dialects ASR Proc. IEEE 13th Global Conference on Consumer Electronics (GCCE) / 811-814 (2024) [Refereed] refereed [Internationally co-authored papers] non-internationally co-authored paper [Lead author or co-author] author [Author] Naoki Takahashi, Shogo Miwa, Yuta Kamiya, Takumi Toyama, Raufun Nahar, Atsuhiko Kai [URL] [DOI] [4]. Attention-based CNN and Relative Phase Feature Modeling for Improved Imagined Speech Recognition Proc. Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2023) / 8-14 (2023) [Refereed] refereed [Internationally co-authored papers] non-internationally co-authored paper [Lead author or co-author] author [Author] Yoshiki Niimura, Jun Takemoto, Atsuhiko Kai, Seiichi Nakagawa [URL] [DOI] [5]. Dialect Speech Recognition Modeling using Corpus of Japanese Dialects and Self-Supervised Learning-based Model XLSR Proc. INTERSPEECH 2023 / 4928-4932 (2023) [Refereed] refereed [Internationally co-authored papers] non-internationally co-authored paper [Lead author or co-author] author [Author] Shogo Miwa, Atsuhiko Kai [URL] [DOI]
|
[1]. Spoken Language Processing and Natural Language Processing Corona Publishing Co., Ltd. (2018) [Book type]book(research) [Sole author, co-author, or author and editor] joint work [Author]中川 聖一(編著),甲斐 充彦,ほか8名共著 [Range] Chapter 7 [REP page number] 231-251 [Notes] 初版第3刷(増補版、2018年9月発行),
書評者:荒木健治先生(北海道大学大学院),
掲載場所:電子情報通信学会誌 2013年8月号 [2]. IEICE Knowledgebase - Forest of Knowledge The Institute of Electronics, Information and Communication Engineers (2018) [Book type]book(educational) [Sole author, co-author, or author and editor] contributor [Author]甲斐充彦 [REP page number] 8群1編4章 4-1担当(8ページ) [3]. Spoken Language Processing and Natural Language Processing Corona Publishing Co., Ltd. (2013) [Book type]book(research) [Sole author, co-author, or author and editor] joint work [Author]中川 聖一(編著),甲斐 充彦,ほか8名共著 [Range] Chapter 7 [REP page number] 201-220 [Notes] 初版第1刷(2013年3月発行),
書評者:荒木健治先生(北海道大学大学院),
掲載場所:電子情報通信学会誌 2013年8月号 [4]. Modern Speech Recognition Approaches with Case Studies InTech (2012) [Book type]book(research) [Sole author, co-author, or author and editor] joint work [Author]Longbiao Wang,Kyohei Odani,Atsuhiko Kai,Norihide Kitaoka,Seiichi Nakagawa [Notes] 共著担当箇所(Chapter 7, "Dereverberation Based on Spectral Subtraction by Multi-channel LMS Algorithm for Hands-free Speech Recognition", pp.155-174)
当書籍 [5]. Spoken Language Systems Ohmsha / IOS Press (2005) [Book type]book(research) [Sole author, co-author, or author and editor] joint work [Author]Seiichi Nakagawa,Atsuhiko Kaiほか55名 [Notes] 共著担当箇所(第4章129-142)
|
[1]. Assessing the Potential of Handcrafted Features for Imagined Speech Recognition Using Deep Learning Models The 17th International Conference on Brain Informatics (BI2024) (2024/12/) other [Presenter]Atsuhiko Kai, Yoshiki Niimura, Seiichi Nakagawa [2]. 日本語諸方言コーパスを利用した 全国地域方言の言語モデルおよび識別モデルの構築と比較分析 日本音響学会2024年秋季研究発表会 (2024/9/5) other [Presenter]神谷悠太, 甲斐充彦, Raufun Nahar, 中川聖一 [Notes] 日本音響学会 [3]. Attention-based CNN and Relative Phase Feature Modeling for Improved Imagined Speech Recognition Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2023) (2023/11/1) other [Presenter]Yoshiki Niimura, Jun Takemoto, Atsuhiko Kai, Seiichi Nakagawa [URL of the repository, etc.] [Notes] APSIPA [4]. Attention ベース CNN と相対位相特徴による EEG に基づく想起音声認識の改善 第10回サイレント音声認識ワークショップ(SSRW2023) (2023/10/15) other [Presenter]新村嘉基, 竹本 淳, 甲斐充彦, 中川聖一 [5]. ASR自動字幕の低コストな修正支援技術のリアルタイム化とオンライン評価 日本音響学会2023年秋季研究発表会 (2023/9/27) other [Presenter]片岡諒弥, 甲斐充彦 [Notes] 日本音響学会
|
[1]. joint (with other institution) leader ( 2015/7 ~ 2025/3 ) [2]. joint (with other institution) leader ( 2012/4 ~ 2014/5 ) [3]. funded (public) 高度な検索機能を備えた“つぶやき音声”によるコミュニケーションシステムの構築 leader ( 2011/12 ~ 2012/7 ) [Partners] 独立行政法人科学技術振興機構 [Notes] 研究成果最適展開支援プログラムA-STEP・FSステージ探索タイプ [4]. joint (with other institution) member ( 2009/10 ) [5]. joint (with other institution) Research on Spoken Language Interface System member ( 2000/4 ) |
[1]. 方言音声データの分析と検索を可能にする諸方言に普遍な音声言語処理基盤モデルの構築 ( 2024/4 ~ 2027/3 ) Grant-in-Aid for Scientific Research (B) leader [2]. 音声言語刺激と脳波の同時収録による脳波特徴表現獲得と想起音声認識 ( 2022/4 ~ 2025/3 ) Challenging Research(Exploratory) leader [3]. 実環境音声認識のための深層学習と人手を併用する音声言語知識拡充フレームワーク ( 2018/4 ~ 2023/3 ) Grant-in-Aid for Scientific Research (C) leader [4]. 音声ドキュメント内の検索とフィードバックに基づく高度なインデキシング機能の実現 ( 2013/4 ~ 2016/3 ) Grant-in-Aid for Scientific Research (C) leader [5]. 対話音声認識における環境や話し方の影響評定を備えた音声理解システムの研究 ( 2011/4 ~ 2012/3 ) Grant-in-Aid for Scientific Research (C) leader
|
[1]. 大規模音声基盤モデルを用いた長期録音資源のクリーン化と音声検索精度の向上 (2023/11 - 2024/10 ) [Offer orgnization] 天野工業技術研究所 [System name] 2023年度研究助成金 [Role] principal investigator [2]. (2014/10 - 2015/9 ) [Offer orgnization] 浜松科学技術研究振興会 [System name] 平成26年度村田基金研究助成金 [3]. 実世界環境における雑音・残響の動的変化に頑健な遠隔発話の音声認識 (2009/4 - 2010/3 ) [Offer orgnization] 浜松科学技術研究振興会 [System name] 科学技術研究助成金 [4]. 安全・便利な車内情報システムインタフェース (2007/9 - 2011/8 ) [Offer orgnization] 独立行政法人新エネルギー・産業技術総合開発機構(NEDO) [System name] 産業技術研究助成事業 [5]. 話し言葉音声理解システムのための多角的な信頼度分析に基づく仮説検証法の開発 (2005/3 - 2006/3 ) [Offer orgnization] (財)中部電力基礎技術研究所 [System name] 研究助成
|
[1]. IEEE GCCE2021 Outstanding Paper Award Robust Query-by-example Spoken Term Detection for Unknown Words Using Speech Retrieval-oriented E2E ASR Modeling (2021/10) [Winner] Takumi Kurokawa, Atsuhiko Kai [Association] IEEE Consumer Technology Society [Notes] 2021 IEEE 10th Global Conference on Consumer Electronics (GCCE2021) [2]. (2013/9) [Notes] 日本オペレーションズ・リサーチ学会 [3]. (1996/1) [Notes] 社団法人電子情報通信学会東海支部 [4]. (1995/1) [Notes] 財団法人電気通信普及財団
|
[1]. 対話理解装置 [Application Number] 2004204788 (2010/10/22) [Patent Number] 4610249 [2]. 対話理解装置 [Application Number] 2003-40053 (2009/4/17) [Patent Number] 4293340 |
[1]. 第23回東海地区音声関連研究室修士論文中間発表会 (2019/8) [Role at conference, etc.] is leader [Site of conference, etc.] 静岡大学浜松キャンパス [Notes] 共催:電子情報通信学会東海支部、日本音響学会東海支部、映像情報メディア学会東海支部
参加大学:東海地区の11大学、参加者約150名
[2]. 日本音響学会2013年秋季研究発表会 (2013/9) [Role at conference, etc.] other [Site of conference, etc.] 愛知県豊橋市 [Notes] 実行委員 [3]. Nanyang Technological Universityとの合同研究発表会 (2012/11) [Role at conference, etc.] is leader [Site of conference, etc.] シンガポール [Notes] 工学部プロジェクト「海外研究機関との研究室交流による国際的リーダーシップ人材育成」(SSSVプログラム)
[4]. 第14回東海地区音声関連研究室修論中間発表会 (2010/8) [Role at conference, etc.] other [Site of conference, etc.] 静岡大学浜松キャンパス [Notes] 学会主催者(静岡大学音声関連研究室後援:人工知能学会、電子情報通信学会東海支部、日本音響学会東海支部、情報処理学会東海支部、映像情報メディア学会東海支部)
|
[1]. 学術雑誌等の編集(電子情報通信学会「Special Section on Robust Speech Processing in Realistic Environment」英文論文小特集) (2007/6 - 2008/3 ) [Notes] 編集委員
|