Research Projects, Papers, Books, etc.

From Solo to Symphony: Bidirectional Music Modeling with Generative AI

Author: Yigitcan Özer (Principal Investigator)

• #Music processing
• #Instrument sounds

Reasoning before Explanation for Speech Deepfake Detection using Audio Large Language Models

Author: Wang Xin (Principal Investigator)

Research on multimedia processing based on broadcast video archives in the era of AI-generated data overload

Authors: Junichi Yamagishi (Principal Investigator), Minoru Kuribayashi (Co-Investigator), Yusuke Yasuda (Co-Investigator)

Toward a Universal Deepfake Audio Detector: Robust Deepfake Detection of Speech and Non-Speech in Real-World Conditions

Author: Wanying Ge (Principal Researcher)

Trusted Speech Dataset Generation

Author：Emmanuel Vincent (Multispeech, Inria, France) Junichi Yamagishi (NII, Japan)

Voice Communication Sciences (VoCS)

Author：

Research and development into the detection, evaluation, and systemization of false information

Author: Junichi Yamagishi (Subcontracted, Project Representative: Fujitsu Ltd.)

Developing and Demonstrating Technology to Detect Fake Information and Misinformation in Various Media, Including the Latest Deepfakes

Author: Yuki Okada (Project Representative, DataGrid Inc.), Isao Echizen (National Institute of Informatics), Junichi Yamagishi (National Institute of Informatics), Yusuke Yasuda (Nagoya University)

Privacy and fairness-aware speech dataset generation

Author: Junichi Yamagishi (Principal Researcher)

Accelerating the Social Implementation and Social Implementation of Fake Media Detection Technology

Author: Junichi Yamagishi (Principal Researcher)