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: 2024/12/01タイトル(英語): Proposal and Evaluation of a Pitch Estimation Model Based on Reconstruction of the Spectrum of Input Sound by Using Timbre Information and Pitch Information著者名: 川 凌司（名城大学大学院理工学研究科），坂野 秀樹（名城大学大学院理工学研究科），旭 健作（名城大学大学院理工学研究科）著者名(英語): Ryoji Kawa (Graduate School of Science and Technology, Meijo University), Hideki Banno (Graduate School of Science and Technology, Meijo University), Kensaku Asahi (Graduate School of Science and Technology, Meijo University)キーワード: 自動採譜，多重音高推定，音楽情報検索，深層学習 automatic music transcription，multi-pitch estimation，music information retrieval，deep learning要約(英語): Automatic music transcription (AMT) is a task that automatically generates music score from the sound of music. Pitch estimation is one of the most important technology in AMT, and its accuracy strongly affects the quality of AMT. Although its accuracy is improving thanks to deep neural networks nowadays, pitch estimation for multi-instrumental music is still a challenging task, because there are many difficulties caused by numerous and complicated timbre patterns in multi-instrumental music. In this paper, we propose a pitch estimation model based on the reconstruction of the spectrum of input sound which can reduce the effect of timbre complexity on pitch estimation. The experimental result indicated that the proposed model improved the average precision by 8.8 points compared to the conventional method.本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.144 No.12 （2024） 特集：電気・電子・情報関係学会東海支部連合大会本誌掲載ページ: 1136-1142 p原稿種別: 論文／日本語電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/144/12/144_1136/_article/-char/ja/
