Data Generation from Robotic Performer for Chord Recognition

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2021/02/01

タイトル(英語): Data Generation from Robotic Performer for Chord Recognition

著者名: Gerelmaa Byambatsogt (Faculty of Computer Science and Electrical Engineering, Kumamoto University), Lodoiravsal Choimaa (National University of Mongolia Ulaanbaatar), Gou Koutaki (Faculty of Computer Science and Electrical Engineering, Kumamoto University

著者名(英語): Gerelmaa Byambatsogt (Faculty of Computer Science and Electrical Engineering, Kumamoto University), Lodoiravsal Choimaa (National University of Mongolia Ulaanbaatar), Gou Koutaki (Faculty of Computer Science and Electrical Engineering, Kumamoto University

キーワード: chord recognition，data synthesis，convolutional neural network (CNN)，robot，guitar

要約(英語): This paper presents a synthetic data generation method using a robot to create a substantial dataset. One important task in the field of learning-based recognition is to collect large amounts of high-quality training data. To increase the training dataset, many researches have used data augmentation methods. In musical recognition, data augmentation is implemented using digital signal processing methods including pitch-shifting and time-stretching. Data augmentation is a limited method because it depends on prior knowledge of the data and it cannot be performed all domains. We propose a new dataset collection method using a robot that automatically plays musical instruments, which enables high-quality data to be added to the training samples. We compare the results with two kinds of human dataset and a mixed dataset, which include human and robot datasets, using four kinds of convolutional neural networks (CNNs). The results indicate that the proposed method using CNNs analyzing the mixed dataset with a guitar-playing robot, can outperform CNNs using the human dataset.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.141 No.2 （2021） 特集I：IoT社会の進歩を促進するワイヤレス技術　　特集Ⅱ：ディジタル信号処理のためのシステム技術

本誌掲載ページ: 205-213 p

原稿種別: 論文／英語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/141/2/141_205/_article/-char/ja/