In EDS ansehen

Four-way Classification of Tabla Strokes with Transfer Learning Using Western Drums

Gespeichert in:
Bibliographische Detailangaben
Titel: Four-way Classification of Tabla Strokes with Transfer Learning Using Western Drums
Autoren: Rohit M. Ananthanarayana, Amitrajit Bhattacharjee, Preeti Rao
Quelle: Transactions of the International Society for Music Information Retrieval, Vol 6, Iss 1, Pp 103–116-103–116 (2023)
Verlagsinformationen: Ubiquity Press, Ltd., 2023.
Publikationsjahr: 2023
Schlagwörter: stroke classification, automatic drum transcription, M1-5000, Information technology, transfer learning, T58.5-58.64, Music, tabla bols, data augmentation
Beschreibung: Motivated by the musicological relevance of tabla stroke categories in tabla accompaniment playing, we present an automatic four-way stroke classification system based on convolutional neural networks, while recognising the challenge of instrument- and style-independent classification with limited available labeled training data. Tabla stroke transcription has been traditionally viewed as a monophonic timbre recognition task given the variety of musically distinct single-drum and two-drum strokes that comprise the music. In this work, we adopt a more sound-production based approach by identifying a reduced set of ‘atomic’ strokes (damped, resonant treble and resonant bass) that serve as the primary level for classification. An advantage of this is the better exploitation of tabla training data and the potential for better generalization. The new viewpoint also facilitates exploring the acoustic similarity with Western drums via the investigation of transfer learning for the tabla task. We find that the drum pretraining learns features that are useful for our tabla stroke classification task. Further fine-tuning the model with the target tabla data leads to the expected improvements in performance, which, however, surpasses that achieved with a purely tabla-trained model for only one of the stroke categories.
Publikationsart: Article
Sprache: English
ISSN: 2514-3298
DOI: 10.5334/tismir.150
Zugangs-URL: https://doaj.org/article/2e15d6d510a94c66bd6ea8390800ae3b
Dokumentencode: edsair.doi.dedup.....2fd02e50f44c540e32b617a64889f1ed
Datenbank: OpenAIRE
Beschreibung
Abstract:Motivated by the musicological relevance of tabla stroke categories in tabla accompaniment playing, we present an automatic four-way stroke classification system based on convolutional neural networks, while recognising the challenge of instrument- and style-independent classification with limited available labeled training data. Tabla stroke transcription has been traditionally viewed as a monophonic timbre recognition task given the variety of musically distinct single-drum and two-drum strokes that comprise the music. In this work, we adopt a more sound-production based approach by identifying a reduced set of ‘atomic’ strokes (damped, resonant treble and resonant bass) that serve as the primary level for classification. An advantage of this is the better exploitation of tabla training data and the potential for better generalization. The new viewpoint also facilitates exploring the acoustic similarity with Western drums via the investigation of transfer learning for the tabla task. We find that the drum pretraining learns features that are useful for our tabla stroke classification task. Further fine-tuning the model with the target tabla data leads to the expected improvements in performance, which, however, surpasses that achieved with a purely tabla-trained model for only one of the stroke categories.
ISSN:25143298
DOI:10.5334/tismir.150