ICKAN: A deep musical instrument classification model incorporating Kolmogorov-Arnold network
Abstract Musical instrument classification, as a fundamental task in music information retrieval (MIR), has broad applications in music analysis, education, and content management. However, existing research primarily focuses on short monophonic samples for classification, which fails to capture the...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-09493-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849402887183007744 |
|---|---|
| author | Jiaxiang Zheng Moxi Cao Chongbin Zhang |
| author_facet | Jiaxiang Zheng Moxi Cao Chongbin Zhang |
| author_sort | Jiaxiang Zheng |
| collection | DOAJ |
| description | Abstract Musical instrument classification, as a fundamental task in music information retrieval (MIR), has broad applications in music analysis, education, and content management. However, existing research primarily focuses on short monophonic samples for classification, which fails to capture the timbral variation characteristics in real performance scenarios. Meanwhile, traditional deep learning models still have limitations in extracting complex timbral features. To address these challenges, this paper proposes ICKAN, a deep instrument classification model that incorporates the Kolmogorov-Arnold Network (KAN), and constructs a large-scale dataset containing 30,824 complete musical phrases. Experimental results demonstrate that ICKAN achieves a classification accuracy of 95.74% in a 20-class instrument classification task with 10-second audio segments, significantly outperforming current methods. This research introduces learnable nonlinear activation functions and comprehensive musical segments, offering new insights into improving the accuracy and practicality of instrument classification and contributing valuable references for the advancement of music information retrieval technology. The code and dataset are available at https://github.com/NMLAB8/ICKAN . |
| format | Article |
| id | doaj-art-3019ba9190c745a992388fcf5b92e1db |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-3019ba9190c745a992388fcf5b92e1db2025-08-20T03:37:24ZengNature PortfolioScientific Reports2045-23222025-07-0115111910.1038/s41598-025-09493-yICKAN: A deep musical instrument classification model incorporating Kolmogorov-Arnold networkJiaxiang Zheng0Moxi Cao1Chongbin Zhang2Kangwon National UniversityKangwon National UniversityDepartment, Nanjing University of the ArtsAbstract Musical instrument classification, as a fundamental task in music information retrieval (MIR), has broad applications in music analysis, education, and content management. However, existing research primarily focuses on short monophonic samples for classification, which fails to capture the timbral variation characteristics in real performance scenarios. Meanwhile, traditional deep learning models still have limitations in extracting complex timbral features. To address these challenges, this paper proposes ICKAN, a deep instrument classification model that incorporates the Kolmogorov-Arnold Network (KAN), and constructs a large-scale dataset containing 30,824 complete musical phrases. Experimental results demonstrate that ICKAN achieves a classification accuracy of 95.74% in a 20-class instrument classification task with 10-second audio segments, significantly outperforming current methods. This research introduces learnable nonlinear activation functions and comprehensive musical segments, offering new insights into improving the accuracy and practicality of instrument classification and contributing valuable references for the advancement of music information retrieval technology. The code and dataset are available at https://github.com/NMLAB8/ICKAN .https://doi.org/10.1038/s41598-025-09493-yMusical instrument classificationMusic information retrievalKolmogorov-Arnold networkDeep learningAudio feature extraction |
| spellingShingle | Jiaxiang Zheng Moxi Cao Chongbin Zhang ICKAN: A deep musical instrument classification model incorporating Kolmogorov-Arnold network Scientific Reports Musical instrument classification Music information retrieval Kolmogorov-Arnold network Deep learning Audio feature extraction |
| title | ICKAN: A deep musical instrument classification model incorporating Kolmogorov-Arnold network |
| title_full | ICKAN: A deep musical instrument classification model incorporating Kolmogorov-Arnold network |
| title_fullStr | ICKAN: A deep musical instrument classification model incorporating Kolmogorov-Arnold network |
| title_full_unstemmed | ICKAN: A deep musical instrument classification model incorporating Kolmogorov-Arnold network |
| title_short | ICKAN: A deep musical instrument classification model incorporating Kolmogorov-Arnold network |
| title_sort | ickan a deep musical instrument classification model incorporating kolmogorov arnold network |
| topic | Musical instrument classification Music information retrieval Kolmogorov-Arnold network Deep learning Audio feature extraction |
| url | https://doi.org/10.1038/s41598-025-09493-y |
| work_keys_str_mv | AT jiaxiangzheng ickanadeepmusicalinstrumentclassificationmodelincorporatingkolmogorovarnoldnetwork AT moxicao ickanadeepmusicalinstrumentclassificationmodelincorporatingkolmogorovarnoldnetwork AT chongbinzhang ickanadeepmusicalinstrumentclassificationmodelincorporatingkolmogorovarnoldnetwork |