• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Performance Information Analysis for Creating Performance Expression Model of Classical Piano Music

Research Project

Project/Area Number 20K12119
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 62040:Entertainment and game informatics-related
Research InstitutionUniversity of Tsukuba

Principal Investigator

Mizutani Tetsuya  筑波大学, システム情報系, 講師 (70209758)

Project Period (FY) 2020-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2022: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2021: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2020: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Keywords音楽情報学 / 演奏表情 / 演奏分析 / オンセット検出 / 暗意実現モデル / クラシック音楽 / 演奏表情解析 / 演奏表情モデル / 人工知能
Outline of Research at the Start

本研究課題は,コンピュータによる表情豊かな音楽演奏の生成のための演奏表情モデルの確立を目標とする研究の一環である.
クラシック楽曲などの調性音楽においては,表情豊かな演奏を生成する最大の要因は,楽譜に付加されている表情記号とともに,楽譜の認知科学的な分析により得られる楽曲構造,特に緊張弛緩構造や隣り合った和音間の誘引構造であるという仮説のもと,クラシックのピアノ楽曲を対象に,楽曲構造および表情記号と実際の演奏との関係を,多数の実演奏をもとに機械学習などの手法を用いて解析し,表情豊かな演奏生成のためのモデルの確立を目指す.

Outline of Final Research Achievements

I have analyzed performance information for the generation of performance expression models of classical piano music and studied the technologies required for the analysis. Specifically, I have designed a prototype of a data cleansing system for extracting performance expressions from music performance information and music score information. And I have studied methods to reduce the computational complexity of accurately detecting the onset of sound in waveform data, as well as the robustness and accuracy of the system.I have also analyzed performance expressions based on implicit realization models instead of musical models such as GTTM and TPS, which are precise but computationally expensive and require in-depth musical knowledge.

Academic Significance and Societal Importance of the Research Achievements

本研究ではクラシックのピアノ音楽に関して,演奏表情を主に強弱と緩急の変化で表現されるものととらえ,その演奏表情モデルを解析した.演奏表情モデルを明らかにすることで,音楽鑑賞および演奏への理解が深まる.また,本研究で特に重要視した「オンセット検出」は,演奏表情を導出ための基本的概念であり,この検出が瞬時に正確に容易に行うことができれば豊かな表情のついた自動演奏などの応用範囲が格段に広がる.

Report

(4 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • 2020 Research-status Report
  • Research Products

    (4 results)

All 2022 2021 2020

All Presentation (4 results) (of which Int'l Joint Research: 4 results)

  • [Presentation] Peak Picking Multiple Onset Detection Functions Using Recurrent Neural Networks2022

    • Author(s)
      Xuan Mobai、Mizutani Tetsuya
    • Organizer
      ICCCM '22: the 10th International Conference on Computer and Communications Management
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Audio Feature Extraction for DTW-based Audio-to-Score Alignment2022

    • Author(s)
      Ding Yifan、Tetsuya Mizutani
    • Organizer
      ICCCM '22: the 10th International Conference on Computer and Communications Management
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] A Linear Regression Analysis of Musical Expressions using the Implication-Realization Model2021

    • Author(s)
      Mizutani, Tetsuya and Sasaki Shigefumi
    • Organizer
      ICCCM '21: The 2021 9th International Conference on Computer and Communications Management
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] A Data Cleansing System for Musical Expression Analysis2020

    • Author(s)
      Tetsuya Mizutani、Kei Hasegawa
    • Organizer
      ICCCM'20: 2020 The 8th International Conference on Computer and Communications Management
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2020-04-28   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi