Sound Group


Sound Group pursues research on sound signal processing, such as environmental sound signal processing and acoustic signal processing collaborating with Toda laboratory dealing with sound media information processing to handle various sound signals, such as speech, music, environmental sounds, and bioacoustic signals. More details are shown here.



Creation of cooperative human augmentation techniques in sound media communication(音メディアコミュニケーションにおける共創型機能拡張技術の創出)


This project aims at creating fundamental techniques for augmenting the speech production function and the hearing function beyond physhical constraints based on cooperative actions between a user and a system. We will develop cooperatively augmented speech production and hearing techniques capable of low-latency real-time processing, involuntary system control, and intentional system control through human-machine interaction in a data-driven framework based on machine learning, making it possible to recover and enhance our speech production and hearing functions.(音メディアコミュニケーションにおいて、ユーザとシステムの共創的な働きかけに基づき、身体的制約を超えて発声・聴覚機能を拡張する基盤技術を創出します。機械学習に基づくデータ駆動型システムの枠組みにおいて、低遅延リアルタイム動作、不随意的なシステム挙動制御、インタラクションを通した意識的なシステム挙動制御を可能とする共創型発声・聴覚機能拡張基盤技術を構築し、発声・聴覚機能の回復・増強を達成します。)

PI: Tomoki Toda (戸田 智基)


Grants-in-Aid for Scientific Research (KAKENHI) projects, etc. Details are shown here.(科学研究費補助金など。 詳しくはこちら

Research topics

Sound media information processing(音メディア情報処理)

Towards the development of various sound media applications, such as augmented speech communication, learning assistance, creative activity enhancement, and disability support, we do research on sound media information processing, specifically speech processing, music processing, and environmental sound processing to make impossible possible beyond physical constraints. More details are shown here.(音声コミュニケーション支援,学習支援,創作支援,障害者支援などを対象として,物理的制約を超えて不可能を可能とする技術の実現を目指し,音声情報処理,音楽情報処理,音環境情報処理といった音メディア情報処理に関する研究を行っています。 詳しくはこちら