YAMAGISHI Junichi
Field of Studies | Mathematical and Information Science |
---|---|
Program | Informatics |
Parent Institute | National Institute of Informatics |
Position | Professor |
Link | https://researchmap.jp/read0205283 https://nrid.nii.ac.jp/ja/nrid/1000070709352/ |
researchmap
Keyword
media forensics,biometrics,speaker verification,speaker recognition,Machine learning,Assistive Technology,Speech Synthesis,Speech Information Processing,Pattern recognition,Speech processing
Papers (Latest 5)
-
- From Sharpness to Better Generalization for Speech Deepfake Detection
- Publish year: 2025
- Journal: Interspeech 2025
- URL: https://researchmap.jp/read0205283/published_papers/49299692
-
- A Comparative Study on Proactive and Passive Detection of Deepfake Speech
- Publish year: 2025
- Journal: Interspeech 2025
- URL: https://researchmap.jp/read0205283/published_papers/49299750
-
- Mitigating Language Mismatch in SSL-Based Speaker Anonymization
- Publish year: 2025
- Journal: Interspeech 2025
- URL: https://researchmap.jp/read0205283/published_papers/49299782
-
- QualiSpeech: A Speech Quality Assessment Dataset with Natural Language Reasoning and Descriptions
- Publish year: 2025
- Journal: ACL 2025
- URL: https://researchmap.jp/read0205283/published_papers/49299907
-
- ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech
- Publish year: 2025
- Journal: Computer Speech & Language
- URL: https://researchmap.jp/read0205283/published_papers/50118384
KAKEN (Principal Investigator)
Research Projects (Latest 5)
-
- Privacy and fairness-aware speech dataset generation
- 2024-2026
- keywords: 音声情報処理, プライバシー, 公平性, 生成モデル, 生成データ
- URL: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-24K21324/
-
- Can AI Rakugoka entertain people? -Improved expressiveness of rakugo speech synthesis and automatic generation of storytelling
- 2021-2022
- keywords: 音声合成, 落語, 深層学習, 言語生成, 音声情報処理, 機械学習
- URL: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-21K19808/
-
- Explainable next-generation media forensics technologies based on fake media detection and automatic fact verification
- 2021-2024
- keywords: シンセティックメディア, ディープフェイク検出, 自動ファクトチェック, 音声情報処理, 自然言語処理, 機械学習, ディープフェイク, ファクトチェック, 深層学習, 説明可能AI, media clone, deepfake detection, fact checking
- URL: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-21H04906/
-
- Safe and secure speech information processing based on liveness detection and ASVspoof challenge
- 2018-2020
- keywords: 音声情報処理, 話者照合, 生体検知, 生体認証, 音声インタフェース, なりすまし, ASVspoofチャレンジ
- URL: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-18KT0051/
-
- Robust voice cloning technologies in noisy environments and its applications
- 2017-2019
- keywords: 音声情報処理, 音声合成, 深層学習, 話者適応, 音声強調, デジタルクローン, ディープラーニング
- URL: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-17H04687/
CiNii Articles (Latest 5)
-
- Joint Noise Reduction and Listening Enhancement for Full-End Speech Enhancement
- Author: Li, Haoyu, Liu, Yun, Yamagishi, Junichi
- Publish date: 2023-06-04
- Publisher: IEEE
- Journal: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Keywords: FOS: Computer and information sciences, Sound (cs.SD), Computer Science - Sound, Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Electrical Engineering and Systems Science - Audio and Speech Processing
- URL: https://cir.nii.ac.jp/crid/1870302168052853888
-
- XFEVER: Exploring Fact Verification across Languages
- Author: Kruengkrai Canasai, 山岸 順一
- Publish date: 2023
- Journal: Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING 2023)
- URL: https://cir.nii.ac.jp/crid/1010584168859834373
-
- DDS: A new device-degraded speech dataset for speech enhancement
- Author: Li, Haoyu, Yamagishi, Junichi
- Publish date: 2022-09-18
- Publisher: ISCA
- Journal: Interspeech 2022
- Keywords: FOS: Computer and information sciences, Sound (cs.SD), Computer Science - Sound, Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Electrical Engineering and Systems Science - Audio and Speech Processing
- URL: https://cir.nii.ac.jp/crid/1872553967739853312
-
- 自動事実検証 : FEVER Challenge参加から得た教訓
- Author: Kruengkrai Canasai, 山岸 順一
- Publish date: 2022-07
- Publisher: 東京 : 映像情報メディア学会
- Journal: 映像情報メディア学会誌 = The journal of the Institute of Image Information and Television Engineers
- Keywords: 自動事実検証, FEVER Challenge, Multi-level Attentionモデル
- URL: https://cir.nii.ac.jp/crid/1520292782182195584
-
- Deepfake生成と検出の現状
- Author: Trung-Nghia Le, Huy Hong Nguyen, 山岸 順一, 越前 功
- Publish date: 2022-07
- Publisher: 東京 : 映像情報メディア学会
- Journal: 映像情報メディア学会誌 = The journal of the Institute of Image Information and Television Engineers
- Keywords: deepfake
- URL: https://cir.nii.ac.jp/crid/1520292782180717184
CiNii Books (Latest 5)
-
- "Future Trends in Digital Face Manipulation and Detection", Book chapter, Handbook of Digital Face Manipulation and Detection
- Author: 山岸 順一
- Publish date: 2022
- Publisher: Springer
- URL: https://cir.nii.ac.jp/crid/1020021218906408320
-
- 映像情報メディア学会誌(2022年07月号)特集:インフォデミック時代のAIとサイバーセキュリティ "Deepfake生成と検出の現状"
- Author: 山岸 順一, 越前 功
- Publish date: 2022
- Publisher: 映像情報メディア学会
- URL: https://cir.nii.ac.jp/crid/1020861618187965313
-
- 映像情報メディア学会誌(2022年07月号)特集:インフォデミック時代のAIとサイバーセキュリティ, "Deepfake生成と検出の現状"
- Author: 山岸 順一, 越前 功
- Publish date: 2022
- Publisher: 映像情報メディア学会
- URL: https://cir.nii.ac.jp/crid/1020017193233185922
-
- Introduction to Voice Presentation Attack Detection and Recent Advances (Chapter 15, Handbook of Biometric Anti-Spoofing, 2nd edition)
- Author: 山岸 順一
- Publish date: 2019
- Publisher: Springer
- URL: https://cir.nii.ac.jp/crid/1020566775591421824
-
- おしゃべりなコンピュータ ―音声合成技術の現在と未来―
- Author: 山岸 順一, 徳田 恵一, 戸田 智基
- Publish date: 2015
- Publisher: 丸善ライブラリ
- URL: https://cir.nii.ac.jp/crid/1020000782240153856