kth.sePublications
Change search
Link to record
Permanent link

Direct link
Falk, Simon
Publications (1 of 1) Show all publications
Falk, S., Sturm, B. & Ahlbäck, S. (2023). Automatic legato transcription based on onset detection. In: SMC 2023: Proceedings of the Sound and Music Computing Conference 2023. Paper presented at 20th Sound and Music Computing Conference, SMC 2023, Hybrid, Stockholm, Sweden, Jun 15 2023 - Jun 17 2023 (pp. 214-221). Sound and Music Computing Network
Open this publication in new window or tab >>Automatic legato transcription based on onset detection
2023 (English)In: SMC 2023: Proceedings of the Sound and Music Computing Conference 2023, Sound and Music Computing Network , 2023, p. 214-221Conference paper, Published paper (Refereed)
Abstract [en]

This paper focuses on the transcription of performance expression and in particular, legato slurs for solo violin performance. This can be used to improve automatic music transcription and enrich the resulting notations with expression markings. We review past work in expression detection, and find that while legato detection has been explored its transcription has not. We propose a method for demarcating the beginning and ending of slurs in a performance by combining pitch and onset information produced by ScoreCloud (a music notation software with transcription capabilities) with articulated onsets detected by a convolutional neural network. To train this system, we build a dataset of solo bowed violin performance featuring three different musicians playing several exercises and tunes. We test the resulting method on a small collection of recordings of the same excerpt of music performed by five different musicians. We find that this signal-based method works well in cases where the acoustic conditions do not interfere largely with the onset strengths. Further work will explore data augmentation for making the articulation detection more robust, as well as an end-to-end solution. 

Place, publisher, year, edition, pages
Sound and Music Computing Network, 2023
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:kth:diva-327112 (URN)2-s2.0-85171797881 (Scopus ID)
Conference
20th Sound and Music Computing Conference, SMC 2023, Hybrid, Stockholm, Sweden, Jun 15 2023 - Jun 17 2023
Funder
EU, Horizon 2020, 864189
Note

Part of ISBN 9789152773727

QC 20230525

Available from: 2023-05-19 Created: 2023-05-19 Last updated: 2024-01-09Bibliographically approved
Organisations

Search in DiVA

Show all publications