School of Data Science Department of Data Science
平3京大・工・航空卒,平5同大大学院工学研究科修士課程了,平25東工大大学院情報理工学研究科博士課程了,博士(工学).平5 NEC入社,平18同社主任研究員,平25同社主幹研究員.平29人工知能学会理事,令1京大大学院情報学研究科非常勤講師.令2より横浜市立大学データサイエンス学部教授.パターン認識,信号処理,機械学習の研究に興味をもつ.
Researcher Profile
Updated on 2025/05/10
平3京大・工・航空卒,平5同大大学院工学研究科修士課程了,平25東工大大学院情報理工学研究科博士課程了,博士(工学).平5 NEC入社,平18同社主任研究員,平25同社主幹研究員.平29人工知能学会理事,令1京大大学院情報学研究科非常勤講師.令2より横浜市立大学データサイエンス学部教授.パターン認識,信号処理,機械学習の研究に興味をもつ.
Doctor of Engineering ( 2013.3 Tokyo Institute of Technology )
Natural language processing
Automatic speech recognition
Deep learning
Signal processing
Artificial intelligence
Pattern recognition
Machine learning
Informatics / Intelligent robotics
Informatics / Perceptual information processing
Informatics / Intelligent informatics
Tokyo Institute of Technology Graduate School of Information Science and Engineering Department of Computer Science
2009.10 - 2013.3
Country: Japan
Kyoto University Graduate School of Engineering Department of Aeronautics
1991.4 - 1993.3
Country: Japan
Kyoto University Faculty of Engineering Department of Aeronautics
1987.4 - 1991.3
Country: Japan
Yokohama City University School of Data Science Professor
2020.9
Country:Japan
NEC Corporation Biometrics Research Laboratories Senior Principal Researcher
2018.3 - 2020.8
Country:Japan
NEC Corporation Data Science Research Laboratories Senior Principal Researcher
2016.4 - 2018.3
Country:Japan
NEC Corporation Information and Media Processing Laboratories Senior Principal Researcher
2015.4 - 2018.3
Country:Japan
NEC Corporation Information and Media Processing Laboratories Principal Researcher
2010.4 - 2013.3
Country:Japan
NEC Corporation Common Platform Software Laboratories Principal Researcher
2007.4 - 2010.3
Country:Japan
NEC Corporation Media and Information Research Laboratories Principal Researcher
2006.4 - 2007.3
Country:Japan
The Association for Natural Language Processing
2021.2
The Japanese Society for Artificial Intelligence
2017.10
IEEE
2013.3
日本音響学会
2004.12
電子情報通信学会
1993.6
ISO/IEC JTC1/SC29 WG1 JP Expert
2021.5
Committee type:Academic society
IEEE BigData2022 Organizing Committee Local Arrangement Co-chair
2020.12 - 2022.12
Committee type:Academic society
The Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA 2021) Sponsorship Co-chair
2019.12 - 2021.12
Committee type:Academic society
The Japanese Society for Artificial Intelligence Repsesentative
2019.6
Committee type:Academic society
The Speaker and Language Recognition Workshop (Odyssey 2020) General Co-chair
2018.6 - 2020.11
Committee type:Academic society
The Japanese Society for Artificial Intelligence Board Member
2017.6 - 2019.6
Committee type:Academic society
Industrial Membership Committee, Asia-Pacific Signal and Information Processing Association (APSIPA) Committee Member
2016.6 - 2018.6
Committee type:Academic society
電子情報通信学会音声研究専門委員会 研究専門委員
2013.5 - 2017.4
Committee type:Academic society
An Experimental Study on Text-independent Speaker Verification for Forensic Applications
Shigeki Ozawa, Akira Gotoh, Yuko Saito, Hiroki Matsuura, Takafumi Koshinaka
124 ( 391 ) 34 - 39 2025.3
検索エンジンを指向したLLMのアラインメント
益子怜, 木村賢, 越仲孝文
言語処理学会第31回年次大会 2025.3
Reading is Believing: Revisiting Language Bottleneck Models for Image Classification Reviewed
Honori Udo, Takafumi Koshinaka
2024 IEEE International Conference on Image Processing (ICIP) 943 - 949 2024.10
Editable Virtual Try-On Using Text Prompts
Kosuke Takemoto, Koshinaka Takafumi
2024.5
LLM生成コンテンツのSEO観点での品質評価
益子怜, 木村賢, 越仲孝文
言語処理学会年次大会発表論文集(Web) 30th 2024
Generalized Domain Adaptation Framework for Parametric Back-End in Speaker Recognition Reviewed
Qiongqiong Wang, Koji Okabe, Kong Aik Lee, Takafumi Koshinaka
IEEE Transactions on Information Forensics and Security 18 3936 - 3947 2023.6
Image Captioners Tell More Than Images Given to Them
有働帆乃璃, 越仲孝文
人工知能学会全国大会論文集(Web) 37th 2023.6
Response Generation to Low-Rated Reviews Combined with Sentiment Analysis
益子怜, 越仲孝文
人工知能学会全国大会論文集(Web) 37th 2023.6
Analysis of Consumers’ Feedback on a Japanese EC Site Focusing on the Relation between Review Text and Rating
小林義幸, 越仲孝文
人工知能学会全国大会論文集(Web) 36th 2022.6
Task-aware Warping Factors in Mask-based Speech Enhancement Reviewed
Qiongqiong Wang, Kong Aik Lee, Takafumi Koshinaka, Koji Okabe, Hitoshi Yamamoto
European Signal Processing Conference (EUSIPCO 2021) 2021.8
Xi-Vector Embedding for Speaker Recognition Reviewed
Kong Aik Lee, Qiongqiong Wang, Takafumi Koshinaka
IEEE Signal Processing Letters 28 1385 - 1389 2021.7
Using Multi-Resolution Feature Maps with Convolutional Neural Networks for Anti-Spoofing in ASV Reviewed
Qiongqiong Wang, Kong Aik Lee, Takafumi Koshinaka
Odyssey 2020 The Speaker and Language Recognition Workshop 2020.5
NEC-TT System for Mixed-Bandwidth and Multi-Domain Speaker Recognition. Reviewed
Kong Aik Lee, Hitoshi Yamamoto, Koji Okabe, Qiongqiong Wang, Ling Guo, Takafumi Koshinaka, Jiacen Zhang, Koichi Shinoda
Computer Speech and Language 61 101033 - 101033 2020.5
A Generalized Framework for Domain Adaptation of PLDA in Speaker Recognition Reviewed
Qiongqiong Wang, Koji Okabe, Kong Aik Lee, Takafumi Koshinaka
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2020.5
Study on comparison of individuality of ear canal shape
Riki Kimura, Shohei Yano, Rui Fujitsuka, Naoki Wakui, Takayuki Arakawa, Takafumi Koshinaka
148th Audio Engineering Society International Convention 2020
NEC-TT speaker verification system for SRE'19 CTS challenge
Kong Aik Lee, Koji Okabe, Hitoshi Yamamoto, Qiongqiong Wang, Ling Guo, Takafumi Koshinaka, Jiacen Zhang, Keisuke Ishikawa, Koichi Shinoda
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2020- 2227 - 2231 2020
Speaker Augmentation and Bandwidth Extension for Deep Speaker Embedding Reviewed
Hitoshi Yamamoto, Kong Aik Lee, Koji Okabe, Takafumi Koshinaka
Interspeech 2019 2019.9
The NEC-TT 2018 Speaker Verification System Reviewed
Kong Aik Lee, Hitoshi Yamamoto, Koji Okabe, Qiongqiong Wang, Ling Guo, Takafumi Koshinaka, Jiacen Zhang, Koichi Shinoda
Interspeech 2019 2019.9
Unleashing the Unused Potential of i-Vectors Enabled by GPU Acceleration Reviewed
Ville Vestman, Kong Aik Lee, Tomi H. Kinnunen, Takafumi Koshinaka
Interspeech 2019 2019.9
The CORAL+ Algorithm for Unsupervised Domain Adaptation of PLDA Reviewed
Kong Aik Lee, Qiongqiong Wang, Takafumi Koshinaka
ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019.5
Feature selection and its evaluation in binaural ear acoustic authentication
Masaki Yasuhara, Shohei Yano, Takayuki Arakawa, Takafumi Koshinaka
AES 146th International Convention 2019
Attention Mechanism in Speaker Recognition: What Does it Learn in Deep Speaker Embedding? Reviewed
Qiongqiong Wang, Koji Okabe, Kong Aik Lee, Hitoshi Yamamoto, Takafumi Koshinaka
2018 IEEE Spoken Language Technology Workshop (SLT) 2018.12
Shivangi Mahto, Takayuki Arakawa, Takafumi Koshinaka
2018 26th European Signal Processing Conference (EUSIPCO) 2018.9
Attentive Statistics Pooling for Deep Speaker Embedding Reviewed
Koji Okabe, Takafumi Koshinaka, Koichi Shinoda
Interspeech 2018 2018.9
DNN Based Speaker Embedding Using Content Information for Text-Dependent Speaker Verification Reviewed
Subhadeep Dey, Takafumi Koshinaka, Petr Motlicek, Srikanth Madikeri
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018.4
Robust i-vector extraction tightly coupled with voice activity detection using deep neural networks Reviewed
Hitoshi Yamamoto, Koji Okabe, Takafumi Koshinaka
2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) 2017.12
Unsupervised Discriminative Training of PLDA for Domain Adaptation in Speaker Verification Reviewed
Qiongqiong Wang, Takafumi Koshinaka
Interspeech 2017 2017.8
i-Vector Transformation Using a Novel Discriminative Denoising Autoencoder for Noise-Robust Speaker Recognition Reviewed
Shivangi Mahto, Hitoshi Yamamoto, Takafumi Koshinaka
Interspeech 2017 2017.8
誤差の周波数拡散と加算平均処理による耳音紋認証の精度向上 Reviewed
矢野 昌平, 荒川 隆行, 越仲 孝文, 今岡 仁, 入澤 英毅
信学論A J100-A ( 4 ) 161 - 168 2017.4
Fast and accurate personal authentication using ear acoustics Reviewed
Takayuki Arakawa, Takafumi Koshinaka, Shohei Yano, Hideki Irisawa, Ryoji Miyahara, Hitoshi Imaoka
2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA) 2016.12
Domain adaptation using maximum likelihood linear transformation for PLDA-based speaker verification Reviewed
Qiongqiong Wang, Hitoshi Yamamoto, Takafumi Koshinaka
2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2016.3
Denoising autoencoder-based speaker feature restoration for utterances of short duration Reviewed
Hitoshi Yamamoto, Takafumi Koshinaka
Interspeech 2015 2015.9
Speech/acoustic analysis technology - Its application in support of public solutions
Takafumi Koshinaka, Osamu Hoshuyama, Yoshifumi Onishi, Ryosuke Isotani, Masahiro Tani
NEC Technical Journal 9 ( 1 ) 82 - 85 2015.1
Anomaly detection of motors with feature emphasis using only normal sounds Reviewed
Yumi Ono, Yoshifumi Onishi, Takafumi Koshinaka, Soichiro Takata, Osamu Hoshuyama
2013 IEEE International Conference on Acoustics, Speech and Signal Processing 2013.5
A study on semantic indexing for spoken document retrieval Reviewed
Takafumi Koshinaka
Tokyo Institute of Technology ( 甲第9187号 ) 2013.3
Shuji Komeiji, Takayuki Arakawa, Takafumi Koshinaka
2012 IEEE Spoken Language Technology Workshop (SLT) 2012.12
Online Speaker Clustering Using Incremental Learning of an Ergodic Hidden Markov Model Reviewed
Takafumi KOSHINAKA, Kentaro NAGATOMO, Koichi SHINODA
IEICE Transactions on Information and Systems E95.D ( 10 ) 2469 - 2478 2012.10
Efficient Estimation Method of Scaling Factors among Probabilistic Models in Speech Recognition Reviewed
ONISHI Yoshifumi, EMORI Tadashi, KOSHINAKA Takafumi, SHINODA Koichi
The IEICE transactions on information and systems (Japanese edetion) J95-D ( 5 ) 1276 - 1285 2012.5
Committee-Based Active Learning for Speech Recognition Reviewed
Yuzo HAMANAKA, Koichi SHINODA, Takuya TSUTAOKA, Sadaoki FURUI, Tadashi EMORI, Takafumi KOSHINAKA
IEICE Transactions on Information and Systems E94-D ( 10 ) 2015 - 2023 2011.11
Speech modeling based on committee-based active learning Reviewed
Yuzo Hamanaka, Koichi Shinoda, Sadaoki Furui, Tadashi Emori, Takafumi Koshinaka
2010 IEEE International Conference on Acoustics, Speech and Signal Processing 2010.3
Online speaker clustering using incremental learning of an ergodic hidden Markov model Reviewed
Takafumi Koshinaka, Kentaro Nagatomo, Koichi Shinoda
2009 IEEE International Conference on Acoustics, Speech and Signal Processing 2009.4
Open-vocabulary spoken-document retrieval based on query expansion using related web documents Reviewed
Makoto Terao, Takafumi Koshinaka, Shinichi Ando, Ryosuke Isotani, Akitoshi Okumura
Interspeech 2008 2008.9
Takafumi Koshinaka, Akitoshi Okumura, Ryosuke Isotani
Electronics and Communications in Japan (Part II: Electronics) 90 ( 12 ) 1 - 11 2007.12
KOSHINAKA Takafumi, OKUMURA Akitoshi, ISOTANI Ryosuke
The IEICE transactions on information and systems J89-D ( 9 ) 2113 - 2122 2006.9
Takafumi Koshinaka, Ken-ichi Iso, Akitoshi Okumura
Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005. 2005.3
A Stochastic Model for Handwritten Word Recognition Using Context Dependency Between Character Patterns Reviewed
Takafumi Koshinaka, Daisuke Nishiwaki, Keiji Yamada
The 6th International Conference on Document Analysis and Recognition (ICDAR 2001) 2001.9
Pressure waves in a separated gas-liquid layer in a horizontal duct with a step Reviewed
Takafumi Koshinaka, Shigeki Morioka
Fluid Dynamics Research 12 ( 6 ) 323 - 333 1993.12
Reading Is Believing: Revisiting Language Bottleneck Models for Image Classification
Honori Udo, Takafumi Koshinaka
2024.6
Generalized domain adaptation framework for parametric back-end in speaker recognition
Qiongqiong Wang, Koji Okabe, Kong Aik Lee, Takafumi Koshinaka
2023.5
Image Captioners Sometimes Tell More Than Images They See
Honori Udo, Takafumi Koshinaka
2023.5
国際会議 Odyssey 2020 開催報告 Invited
越仲 孝文, リー コンエイク, 篠田 浩一
電子情報通信学会 情報・システムソサイエティ誌 26 ( 2 ) 23 - 24 2021.8
Linear Discriminant Analysis Considering Worst-case Variance Ratio and Its Application to Ear Acoustic Authentication
伊藤良峻, 越仲孝文
日本音響学会研究発表会講演論文集(CD-ROM) 2020 2020
I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences
Kong Aik Lee, Ville Hautamaki, Tomi Kinnunen, Hitoshi Yamamoto, Koji Okabe, Ville Vestman, Jing Huang, Guohong Ding, Hanwu Sun, Anthony Larcher, Rohan Kumar Das, Haizhou Li, Mickael Rouvier, Pierre-Michel Bousquet, Wei Rao, Qing Wang, Chunlei Zhang, Fahimeh Bahmaninezhad, Hector Delgado, Jose Patino, Qiongqiong Wang, Ling Guo, Takafumi Koshinaka, Jiacen Zhang, Koichi Shinoda, Trung Ngo Trong, Md Sahidullah, Fan Lu, Yun Tang, Ming Tu, Kah Kuan Teh, Huy Dat Tran, Kuruvachan K. George, Ivan Kukanov, Florent Desnous, Jichen Yang, Emre Yilmaz, Longting Xu, Jean-Francois Bonastre, Chenglin Xu, Zhi Hao Lim, Eng Siong Chng, Shivesh Ranjan, John H. L. Hansen, Massimiliano Todisco, Nicholas Evans
2019.4
声認証技術がもたらす安全・安心で便利な社会 (バイオメトリクスを用いた社会価値創造特集) Invited
越仲 孝文, リー コンエイク
NEC技報 71 ( 2 ) 2019.3
人間の耳には聴こえない音で個人を識別する耳音響認証技術 Invited
荒川 隆行, 越仲 孝文
月刊自動認識 2019.3
A study of observation fluctuation reduction method for car acoustic authentication
安原雅貴, 荒川隆行, 越仲孝文, 矢野昌平
人工知能学会全国大会論文集(Web) 33rd 2019
話者クラスタリングを用いた話者照合手法のNIST SRE18における比較評価
GUO Ling, 山本仁, 岡部浩司, 越仲孝文
日本音響学会研究発表会講演論文集(CD-ROM) 2019 2019
単一話者検出に最適化した話者クラスタリングを用いる話者照合
GUO Ling, 山本仁, 越仲孝文
日本音響学会研究発表会講演論文集(CD-ROM) 2019 2019
複数の話者が混在する環境下のスコア統合に基づく話者照合
GUO Ling, 山本仁, LEE Kong Aik, 越仲孝文
日本音響学会研究発表会講演論文集(CD-ROM) 2018 2018
PROMISING TECHNOLOGY : Technique of ear acoustic authentication Invited
37 ( 439 ) 18 - 22 2017.10
ヒアラブル技術によるヒューマン系IoTソリューションの取り組みと展望 (デジタルビジネスを支えるIoT特集) Invited
古谷 聡, 越仲 孝文, 大杉 孝司
NEC技報 70 ( 1 ) 47 - 51 2017.9
外耳道音響特性を用いた高精度個人認証
荒川隆行, 矢野昌平, 越仲孝文, 入澤英毅, 今岡仁
日本音響学会研究発表会講演論文集(CD-ROM) 2016 2016
i-vectorの重み付き次元圧縮と区分回帰による年齢推定
児島一郁, 山本仁, 越仲孝文
日本音響学会研究発表会講演論文集(CD-ROM) 2016 2016
音声・音響分析技術とパブリックソリューションへの応用 (社会の安全・安心を支えるパブリックソリューション特集) Invited
越仲 孝文, 宝珠山 治, 大西 祥史, 磯谷 亮介, 谷 真宏
NEC技報 67 ( 1 ) 86 - 89 2014.11
正常音スペクトルモデルに基づく機器異常検知方式における特徴量強調の効果
小野友督, 宝珠山治, 大西祥史, 越仲孝文
日本音響学会研究発表会講演論文集(CD-ROM) 2014 2014
話者認識の国際動向 (小特集: 話者認識に関する研究の動向) Invited Reviewed
越仲 孝文, 篠田 浩一
日本音響学会誌 69 ( 7 ) 2013.7
GMM-SVMによるテキスト非依存話者識別
谷真宏, 大西祥史, 越仲孝文
日本音響学会研究発表会講演論文集(CD-ROM) 2013 2013
Current situations and issues of speaker recognition technologies
網野加苗, 石原俊一, 小川哲司, 長内隆, 黒岩眞吾, 越仲孝文, 篠田浩一, 柘植覚, 西田昌史, 松井知子, WANG Longbiao
電子情報通信学会技術研究報告 112 ( 450(SP2012 115-131) ) 2013
正常音の知識のみを利用した機器の異常検知
小野友督, 大西祥史, 越仲孝文, 高田宗一朗
日本音響学会研究発表会講演論文集(CD-ROM) 2012 2012
音声・映像情報の構造化と検索 (小特集: 音声・映像認識連携への取り組み) Invited Reviewed
越仲 孝文, 大網 亮磨, 細見 格, 今岡 仁
情報処理 52 ( 1 ) 2011.10
雑音抑圧法とモデル適応法の重み付き組み合わせに基づく耐雑音音声認識手法
古明地秀治, 荒川隆行, 越仲孝文
日本音響学会研究発表会講演論文集(CD-ROM) 2011 2011
複数マイクロフォンを用いた音声区間検出
大西祥史, 越仲孝文, 篠田浩一
日本音響学会研究発表会講演論文集(CD-ROM) 2011 2011
A hybrid method of noise suppression and model adaptation for robust speech recognition
IEICE technical report 110 ( 356 ) 49 - 54 2010.12
A Hybrid method of Noise Suppression and Model Adaptation for Robust Speech Recognition
古明地秀治, 荒川隆行, 越仲孝文
電子情報通信学会技術研究報告 110 ( 357(SP2010 88-102) ) 49 - 54 2010.12
A Hybrid method of Noise Suppression and Model Adaptation for Robust Speech Recognition
2010 ( 9 ) 1 - 6 2010.12
裁判員裁判向け音声認識システム (音声認識ソリューション・製品特集) Invited
越仲 孝文, 江森 正, 大西 祥史
NEC技報 63 ( 1 ) 41 - 90 2010.2
オンライン話者クラスタリング技術と議事録作成支援への応用 (音声認識ソリューション・製品特集) Invited
越仲 孝文, 長友 健太郎
NEC技報 63 ( 1 ) 84 - 87 2010.2
法廷における音声認識システムの開発-音響モデル及び言語モデル-
谷真宏, 北出祐, 江森正, 大西祥史, 越仲孝文, 佐藤研治
日本音響学会研究発表会講演論文集(CD-ROM) 2010 2010
法廷における音声認識システムの開発-システム概要-
越仲孝文, 江森正, 大西祥史, 北出祐, 谷真宏, 佐藤研治
日本音響学会研究発表会講演論文集(CD-ROM) 2010 2010
法廷における音声認識システムの開発-オンライン話者適応の構成-
大西祥史, 江森正, 谷真宏, 北出祐, 長友健太郎, 越仲孝文, 佐藤研治
日本音響学会研究発表会講演論文集(CD-ROM) 2010 2010
法廷における音声認識システムの開発-閲覧性向上のための諸技術の開発-
北出祐, 大西祥史, 江森正, 谷真宏, 越仲孝文, 佐藤研治
日本音響学会研究発表会講演論文集(CD-ROM) 2010 2010
法廷における音声認識システムの開発-複数マイクロフォンを用いた音声検出-
江森正, 辻川剛範, 大西祥史, 越仲孝文, 谷真宏, 北出祐, 佐藤研治
日本音響学会研究発表会講演論文集(CD-ROM) 2010 2010
Active learning using multiple recognizers for speech recognition
濱中悠三, 江森正, 越仲孝文, 越仲孝文, 篠田浩一, 古井貞煕
電子情報通信学会技術研究報告 109 ( 355(NLC2009 12-32) ) 19 - 23 2009.12
Active learning using multiple recognizers for speech recognition
HAMANAKA YUZO, EMORI TADASHI, KOSHINAKA TAKAFUMI, SHINODA KOICHI, FURUI SADAOKI
2009 ( 4 ) 1 - 5 2009.12
Online speaker clustering using an ergodic HMM and its application to meeting minute generation
越仲孝文, 長友健太郎, 佐藤研治
電子情報通信学会技術研究報告 3rd ( 376(MVE2009 79-129) ) 53 - 58 2009
音声認識のためのコミッティを用いた能動学習
濱中悠三, 江森正, 越仲孝文, 越仲孝文, 篠田浩一, 古井貞熙
日本音響学会研究発表会講演論文集(CD-ROM) 2009 2009
エルゴードHMMのインクリメンタル学習によるオンライン話者クラスタリング
越仲孝文, 長友健太郎, 佐藤研治
日本音響学会研究発表会講演論文集(CD-ROM) 2008 2008
Speaker Selection for Unsupervised Speaker Adaptation based on HMM Sufficient Statistics
谷真宏, 江森正, 大西祥史, 越仲孝文, 篠田浩一
情報処理学会研究報告 2007 ( 129(SLP-69) ) 85 - 89 2007.12
Speaker Selection for Unsupervised Speaker Adaptation based on HMM Sufficient Statistics
TANI Masahiro, EMORI Tadashi, OHNISHI Yoshifumi, KOSHINAKA Takafumi, SHINODA Koichi
IEICE technical report 107 ( 406 ) 85 - 89 2007.12
WEB文書を活用したニュース映像検索システム
寺尾真, 越仲孝文, 安藤真一, 磯谷亮輔, 奥村明俊
音声ドキュメント処理ワークショップ講演論文集 1st 2007
G_010 An audio-visual information retrieval system using related text documents
TERAO Makoto, KOSHINAKA Takafumi, ANDO Shinichi, ISOTANI Ryosuke, OKUMURA Akitoshi
FIT 2006 ( 2 ) 373 - 374 2006.8
話し言葉における発話速度を隠れ変数にもつ継続時間長モデル
越仲孝文
日本音響学会研究発表会講演論文集 2005 2005
An HMM - based text segmentation method using variational Bayes approach
KOSHINAKA Takafumi, ISO Ken-ichi, OKUMURA Akitoshi
IPSJ SIG Notes 2004 ( 57 ) 49 - 54 2004.5
An HMM-based text segmentation method using variational Bayes approach
越仲孝文, 磯健一, 奥村明俊
電子情報通信学会技術研究報告 104 ( 87(SP2004 15-18) ) 19 - 24 2004.5
HMMの変分ベイズ学習によるテキストの話題分割法の検討
越仲孝文, 磯健一
日本音響学会研究発表会講演論文集 2004 2004
A Handwritten Word Recognition Method Using Context Dependency with Continuous HMM.
越仲孝文, 西脇大輔, 山田敬嗣
電子情報通信学会技術研究報告 99 ( 649(PRMU99 231-245) ) 2000
文字パタン間の依存性を考慮した文字列の学習と認識
越仲孝文, 西脇大輔, 山田敬嗣
電子情報通信学会大会講演論文集 1999 1999
A Slant Correction Method for Character Strings Based on Certainty Measure to Slant Estimation.
越仲孝文, 西脇大輔, 山田敬嗣
電子情報通信学会大会講演論文集 1997 1997
Handwritten Kana Recognition using Inverse Recall Neuralnets.
越仲孝文, 西脇大輔, 山田敬嗣
電子情報通信学会大会講演論文集 1996 ( Society D ) 1996
A Segmentation and Recognition Method for Specific Chinese Numerics and Symbols.
越仲孝文, 西脇大輔, 山田敬嗣
電子情報通信学会大会講演論文集 1995 ( Sogo Pt 7 ) 1995
機械学習を用いた胸部X線画像左右反転防止システム開発の検討
岡田圭伍, 越仲孝文, 平野高望, 本寺哲一, 安田光慶, 加藤京一
第39回日本診療放射線技師学術大会 2023.10
NECシンガポール研究所と音声・音響解析への取組み Invited
谷 真宏, 仙田 裕三, 近藤 玲史, 越仲 孝文
情報処理学会音声言語処理研究会(SIG-SLP) 2015.10
音で耳を測る,新しい個人認証技術 Invited
越仲 孝文
センシング技術応用研究会 第201回研究例会 2017.11
インダストリーセッション Invited
庄境 誠, 西村 雅史, 大淵 康成, 河村 聡典, 越仲 孝文
情報処理学会音声言語情報処理研究会(SIG-SLP) 2014.3
話者認識技術の現状と課題 Invited
小川 哲司, 長内 隆, 黒岩 眞吾, 越仲 孝文, 篠田 浩一, 西田 昌史
電子情報通信学会音声研究会(SP) 2013.3
音で耳を測る,新しい個人認証技術 Invited
越仲 孝文, 矢野 昌平
第6回バイオメトリクスと認識・認証シンポジウム (SBRA2016) 2016.11
学術奨励賞
2000.3 電子情報通信学会
音声に内在する個人性の言語的側面に関する研究
Grant number:21K11967 2021.4 - 2024.3
日本学術振興会 科学研究費助成事業 基盤研究(C)
越仲 孝文
Grant amount:\4160000 ( Direct Cost: \3200000 、 Indirect Cost:\960000 )
本研究では、音声に含まれる個人性のうち、これまであまり研究されてこなかった言語的な個人性、すなわちテキスト情報に現れる書き手の特徴について明らかにする。研究成果は、音声通話やネット投稿のなりすましのような犯罪の防止などに有用である。
初年度は、テキストからその筆者を予測する文書分類問題を想定し、ベースラインシステムの構築に注力した。すなわち、テキストから特徴量を抽出する処理、および特徴量を所定の筆者クラスに分類する処理を実行するプログラムを作成した。前者は、基本単位であるトークンの出現頻度に基づくTF-IDF特徴量を抽出する。後者はロジスティック回帰や多層パーセプトロン(MLP)に基づく分類器である。また、特徴抽出と分類を統合した、深層ニューラルネットワークによるend-to-endシステムも構築した。こちらは長短期記憶(LSTM)機構を備える双方向リカレントニューラルネット(bidirectional RNN)および注意機構を備えるTransformerなどのモデルを含む。End-to-endシステムでは、ニューラルネットの隠れ層から入力テキストの分散表現(埋め込みベクトル)を得ることも可能である。
公開データセットである「青空文庫」から作品数の多い著名筆者10人を選び、日本語作品の段落単位での分類実験を実施した。段落総数は約33,000である。深層ニューラルネットに基づくシステムの分類精度が65%で最も高く、TF-IDF特徴量を用いる従来型システムの52%を大きく上回った。関連する研究成果を人工知能学会全国大会(JSAI2022)で発表予定。
実験の効率化のために、NVIDIA RTX A6000搭載のGPUサーバ1台を購入した。また、将来の国際会議や雑誌での論文発表に備えてLanguage Data Consortium (LDC)の音声言語データを入手した。
Improvement of likelihood ratio measurement in a forensic speaker identification based on Bayesian statistics
Grant number:21510185 2009 - 2012
Japan Society for the Promotion of Science Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)
OSANAI Takashi, KAMADA Toshiaki, MAKINAE Hisanori, AMINO Kanae, PHIL Rose
Grant amount:\4290000 ( Direct Cost: \3300000 、 Indirect Cost:\990000 )
In the forensic science field, in order to help the suitable judgment by judges, it is important to show the degree of a possibility that a suspected person is a criminal. In order to show this possibility, the likelihood ratio based on Bayesian statistics is used widely. In recent years, research which uses this likelihood ratio for forensic speaker recognition is carried out. However, by the conventional method, only a part of the given speech data is used. In this study, I proposed the likelihood ratio measurement which can be used without making useless the given speech data, and confirmed the effectiveness of using it
Data Mining
2021.4 Institution:Yokohama City University
Automatic Speech Recognition
2020.12 Institution:Takushoku University
Statistics and Probability Theory
2020.9 Institution:Yokohama City University
Advanced Natural Language Processing
2020.9 Institution:Yokohama City University
Speech Information Processing
2019.12 Institution:Hosei University
Advanced Artificial Intelligence
2019.11 - 2020.11 Institution:Kyoto University
Advanced Data Science
2017.11 - 2020.11 Institution:Kobe University
International Joint Conference on Neural Networks (IJCNN)
Role(s): Peer review
IEEE 2025.3
ACM Transactions on Multimedia Computing Communications and Applications
Role(s): Peer review
Association for Computing Machinery (ACM) 2023.5
IEEE BigData2022 Local Arrangement Co-chair
Role(s): Planning, management, etc.
IEEE Computer Society 2022.12
ICASSP 2022 Session Chair
Role(s): Panel moderator, session chair, etc.
IEEE Signal Processing Society 2022.5
APSIPA ASC 2021 Sponsorship Co-chair
Role(s): Planning, management, etc.
Asia-Pacific Signal and Information Processing Association (APSIPA) 2021.12
ICASSP 2021 Session Chair
Role(s): Panel moderator, session chair, etc.
IEEE Signal Processing Society 2021.6
ICASSP 2020 Session Chair
Role(s): Panel moderator, session chair, etc.
IEEE Signal Processing Society 2020.5
Computer Speech and Language
Role(s): Peer review
International Speech Communication Association (ISCA) 2019.5
Signal Processing Letters
Role(s): Peer review
IEEE Signal Processing Society 2019.4
Automatic Speech Recognition and Understanding Workshop (ASRU)
Role(s): Peer review
IEEE Signal Processing Society 2017.6
Spoken Language Technology Workshop (SLT)
Role(s): Peer review
IEEE Signal Processing Society 2016.6
情報処理学会論文誌査読委員
Role(s): Peer review
情報処理学会 2016.5
International Conference on Audio, Speech, and Signal Processing (ICASSP)
Role(s): Peer review
IEEE Signal Processing Society 2015.9
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
Role(s): Peer review
Asia-Pacific Signal and Information Processing Association (APSIPA) 2015.7
電子情報通信学会 英文論文誌D (IEICE Trans. on Inf. & Syst.)
Role(s): Peer review
電子情報通信学会 2014.6
Speech Communication
Role(s): Peer review
International Speech Communication Association (ISCA) 2013.4
The Annual Conference of the International Speech Communication Association (INTERSPEECH)
Role(s): Peer review
International Speech Communication Association (ISCA) 2010.5