Pitch Estimation in Real Time: Revisiting SWIPE with Causal Windowing

Meier P, Strahl S, Schwär S, Müller M, Balke S (2025)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2025

Pages Range: 285-297

Conference Proceedings Title: Proceedings of the International Symposium on Computer Music Multidisciplinary Research (CMMR)

Event location: London, UK

DOI: 10.5281/zenodo.17496630

Abstract

Pitch estimation in real time is essential for a wide range of Music Information Retrieval (MIR) applications, including intonation monitoring, music education, and interactive systems. Many of these use cases, such as ensemble rehearsal settings, require low-latency, multichannel processing on resource-constrained devices. While recent neural approaches offer high accuracy, they often fall short in real-time performance due to computational demands. In this paper, we revisit the well-established SWIPE algorithm and introduce RT-SWIPE, a real-time variant enabled by using causal windowing. We further propose a delay-tolerant evaluation metric that extends Raw Pitch Accuracy (RPA) to account for algorithmic delays. Experimental results on synthetic signals and multi-track ensemble recordings demonstrate that RT-SWIPE provides a practical balance of latency, accuracy, and efficiency. Although our study focuses on wind orchestra scenarios, the method is broadly applicable to similar real-time settings.

Authors with CRIS profile

How to cite

APA:

Meier, P., Strahl, S., Schwär, S., Müller, M., & Balke, S. (2025). Pitch Estimation in Real Time: Revisiting SWIPE with Causal Windowing. In Proceedings of the International Symposium on Computer Music Multidisciplinary Research (CMMR) (pp. 285-297). London, UK, GB.

MLA:

Meier, Peter, et al. "Pitch Estimation in Real Time: Revisiting SWIPE with Causal Windowing." Proceedings of the International Symposium on Computer Music Multidisciplinary Research (CMMR), London, UK 2025. 285-297.

BibTeX: Download