SavedAdd your journal

Journals / Konservatoryum / 2026 / Cilt: 13 Sayı: 1

A Comparative Analysis of the Piano Sustain Pedal’s Effect Based on Audio Features

Pianoda Sustain Pedal Etkisinin Ses Özniteliklerine Dayalı Karşılaştırmalı Analizi

İsmet Emre Yücel(AMASYA ÜNİVERSİTESİ)0000-0001-7018-3349
Pages
58–72
Publication Date
2026-06-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Considering the limitations of the study, the results show that the pedal effect produced medium and above effect sizes, particularly in spectral slope, maximum autocorrelation, and low-order MFCC coefficients.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study quantitatively examines how the use of a sustain pedal alters the audio features of piano recordings based on MIDI data.
📊
Key Findings & Data:In data production, 10 MIDI recordings of Frédéric Chopin's Polonaise works were reproduced in two conditions—with and without pedals—using a piano VST, while preserving the same performance data.
💡
Conclusion & Impact:Considering the limitations of the study, the results show that the pedal effect produced medium and above effect sizes, particularly in spectral slope, maximum autocorrelation, and low-order MFCC coefficients.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Sustain pedal · piyano · akustik öznitelikler

Abstract

This study quantitatively examines how the use of a sustain pedal alters the audio features of piano recordings based on MIDI data. In data production, 10 MIDI recordings of Frédéric Chopin's Polonaise works were reproduced in two conditions—with and without pedals—using a piano VST, while preserving the same performance data. For each piece, pedal timings were taken into account, and pairs of segments (with and without pedals) were created from the corresponding MIDI files, each at least 1 second in length. For each segment, time-domain (RMS, peak envelope, ZCR, ACF/MaxACF, tonal power ratio), spectral (flux, centroid, spread, slope, rolloff, crest factor, skewness, kurtosis), and cepstral (MFCC 1–13) features were calculated separately. Pedaled–unpedaled comparisons were evaluated using a paired sample t-test, and Cohen's dz effect size was used to interpret the findings against the large sample effect. Considering the limitations of the study, the results show that the pedal effect produced medium and above effect sizes, particularly in spectral slope, maximum autocorrelation, and low-order MFCC coefficients. The findings suggest candidate inputs for pedal detection and explainable feature-based models.

Özet

Bu çalışma MIDI verilerinden elde edilen piyano kayıtlarında sustain pedal kullanımının neden olduğu etkileri ses öznitelikleri üzerinden nicel olarak incelemektedir. Veri üretiminde Frédéric Chopin’in Polonez eserlerine ait 10 adet MIDI kaydı aynı performans verisi korunarak bir piyano VST’si (Virtual Studio Technology) ile pedallı ve pedalsız olacak şekilde iki koşulda yeniden üretilmiştir. Her eser için pedal zamanlamaları göz önünde bulundurularak ilgili MIDI dosyalarından her biri en az 1 sn uzunluğunda olacak şekilde eşleştirilmiş (pedallı ve pedalsız) segment çiftleri oluşturulmuştur. Her segment için zaman düzlemi (RMS, tepe zarfı, ZCR, ACF/MaxACF, tonal güç oranı), izgesel (akı, merkez, yayılım, eğim, rolloff, crest factor, çarpıklık, basıklık) ve kepstral (MFCC 1–13) öznitelikler ayrı ayrı hesaplanmıştır. Pedallı–pedalsız karşılaştırmaların eşleştirilmiş örneklem t-testi (paired-sample t-test) ile değerlendirilmiştir, büyük örneklem etkisine karşı bulguların yorumunda Cohen’s 𝑑z etki büyüklüğü esas alınmıştır. Çalışmanın kısıtlılıkları göz önünde bulundurulduğunda sonuçlar pedal etkisinin özellikle izgesel eğim, maksimum otokorelasyon ve düşük mertebeli MFCC katsayılarında orta düzey ve üzeri etki büyüklükleri ürettiğini göstermektedir. Bulgular, pedal tespiti ve açıklanabilir öznitelik temelli modeller için aday girdiler önermektedir.

🔖

Cite This Article

Yücel, İ. E. (2026). A Comparative Analysis of the Piano Sustain Pedal’s Effect Based on Audio Features. Konservatoryum, Cilt: 13 Sayı: 1, 58–72. https://doi.org/10.26650/CONS2026-1904180

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (18)

  1. Banowetz, J. (1985). The pianist’s guide to pedaling. Indiana University Press. google scholar
  2. Benetos, E., Dixon, S., Giannoulis, D., Kirchhoff, H., & Klapuri, A. (2013). Automatic music transcription: Challenges and future directions. Journal of Intelligent Information Systems, 41(3), 407–434. https://doi.org/10.1007/s10844-013-0258-3 google scholar
  3. Cohen, J. (1988). Statistical power analysis for the behavioral sciences (2nd. Ed.). Lawrence Erlbaum. google scholar
  4. Fletcher, N. H., & Rossing, T. D. (1998). The physics of musical instruments (2nd. Ed.). Springer. google scholar
  5. Han, J., Kamber, M., & Pei, J. (2011). Data mining: Concepts and techniques (3rd Ed.). Elsevier. google scholar
  6. Hawthorne, C., Stasyuk, A., Roberts, A., Simon, I., Huang, C. Z. A., Dieleman, S., Elsen, E., Engel, J., & Eck, D. (2018). Onsets and frames: Dual-objective piano transcription. Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), 50–57. google scholar
  7. Kim, T. K. (2015). T test as a parametric statistic. Korean Journal of Anesthesiology, 68(6), 540–546. https://doi.org/10.4097/kjae.2015.68.6.540 google scholar
  8. Kong, Q., Li, B., Song, X., Wan, Y., & Wang, Y. (2021). High-resolution piano transcription with pedals by regressing onset and offset times. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 3707–3717. https://doi.org/10.1109/TASLP.2021.31211991 google scholar
  9. Kunst der Fuge. (t.y.). Chopin MIDI files. https://www.kunstderfuge.com/chopin.htm google scholar
  10. Liang, B., Fazekas, G., & Sandler, M. (2019). Transfer learning for piano sustain-pedal detection. Proceedings of the International Joint Conference on Neural Networks (IJCNN), 1–6. https://doi.org/10.1109/IJCNN.2019.8852266 google scholar
  11. Müller, M. (2015). Fundamentals of music processing. Springer. https://doi.org/10.1007/978-3-319-21945-5 google scholar
  12. Native Instruments (t.y.). Noire: User manual. https://www.native-instruments.com/fileadmin/ni_media/downloads/manuals/NOIRE_Manual.pdf google scholar
  13. Rosenblum, S. P. (1993). Pedaling the piano: A brief survey from the eighteenth century to the present. Performance Practice Review, 6(2), 158–178. https://doi.org/10.5642/perfpr.199306.02.08 google scholar
  14. Rosenblum, S. P. (1996). Some enigmas of Chopin's pedal indications: What do the sources tell us? Journal of Musicological Research, 16(1), 41–61. https://doi.org/10.1080/01411899608574724 google scholar
  15. Schutz, A., Bertin, N., Slock, D. T., David, B., & Badeau, R. (2008). Piano forte pedal analysis and detection. In Proceedings of the 124th Convention of AES. Amsterdam google scholar
  16. Tracey, B., Volfson, D., Glass, J., Haulcy, R., Kostrzebski, M., Adams, J., Kangarloo, T., Brodtmann, A., Dorsey, E. R., & Vogel, A. (2023). Towards interpretable speech biomarkers: Exploring MFCCs. Scientific Reports, 13(1), Madde 22787. https://doi.org/10.1038/s41598-023-49352-2 google scholar
  17. Weinreich, G. (1977). Coupled piano strings. The Journal of the Acoustical Society of America, 62(6), 1474–1484. https://doi.org/10.1121/1.381677 google scholar
  18. Yurtsever, U., & Yücel, İ. E. (2025). Comparative analysis of machine learning approaches for drum set component classification in music technology. Applied Artificial Intelligence, 39(1). https://doi.org/10.1080/08839514.2025.2581352 google scholar