English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The tabla is a unique percussion instrument due to the combined harmonic andpercussive nature of its timbre, and the contrasting harmonic frequency rangesof its two drums. This allows a tabla player to uniquely emphasize parts of therhythmic cycle (theka) in order to mark the salient positions. An analysis ofthe loudness dynamics and timing deviations at various cycle positions is animportant part of musicological studies on the expressivity in tablaaccompaniment. To achieve this at a corpus-level, and not restrict it to thefew recordings that manual annotation can afford, it is helpful to have accessto an automatic tabla transcription system. Although a few systems have beenbuilt by training models on labeled tabla strokes, the achieved accuracy doesnot necessarily carry over to unseen instruments. In this article, we reportour work towards building an instrument-independent stroke classificationsystem for accompaniment tabla based on the more easily available tabla soloaudio tracks. We present acoustic features that capture the distinctivecharacteristics of tabla strokes and build an automatic system to predict thelabel as one of a reduced, but musicologically motivated, target set of fourstroke categories. To address the lack of sufficient labeled training data, weturn to common data augmentation methods and find the use of pitch-shiftingbased augmentation to be most promising. We then analyse the important featuresand highlight the problem of their instrument-dependence while motivating theuse of more task-specific data augmentation strategies to improve the diversityof training data.

Automatic Stroke Classification of Tabla Accompaniment in Hindustani Vocal Concert Audio