Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 1611.05182

Detecting tala Computationally in Polyphonic Context - A Novel Approach

Susmita Bhaduri·Anirban Bhaduri·Dipak Ghosh
View original source ↗Read source document ↗Export metadata ↓

Abstract

In North-Indian-Music-System(NIMS),tabla is mostly used as percussive accompaniment for vocal-music in polyphonic-compositions. The human auditory system uses perceptual grouping of musical-elements and easily filters the tabla component, thereby decoding prominent rhythmic features like tala, tempo from a polyphonic composition. For Western music, lots of work have been reported for automated drum analysis of polyphonic composition. However, attempts at computational analysis of tala by separating the tabla-signal from mixed signal in NIMS have not been successful. Tabla is played with two components - right and left. The right-hand component has frequency overlap with voice and other instruments. So, tala analysis of polyphonic-composition, by accurately separating the tabla-signal from the mixture is a baffling task, therefore an area of challenge. In this work we propose a novel technique for successfully detecting tala using left-tabla signal, producing meaningful results because the left-tabla normally doesn't have frequency overlap with voice and other instruments. North-Indian-rhythm follows complex cyclic pattern, against linear approach of Western-rhythm. We have exploited this cyclic property along with stressed and non-stressed methods of playing tabla-strokes to extract a characteristic pattern from the left-tabla strokes, which, after matching with the grammar of tala-system, determines the tala and tempo of the composition. A large number of polyphonic(vocal+tabla+other-instruments) compositions has been analyzed with the methodology and the result clearly reveals the effectiveness of proposed techniques.

Explore related subjects

cs.SD

Keep this discovery

BibTeXRIS

Susmita Bhaduri, Anirban Bhaduri, Dipak Ghosh. 2016-11-16. Detecting tala Computationally in Polyphonic Context - A Novel Approach. https://doi.org/10.21767/2349-3917.100030

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Xiaomi-CocktailASR-1 Technical Report

Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party problem remains a critical bottleneck for further advancing ASR. Existing TS-ASR methods, including end-to-end architectures with speaker embeddings and latest LLM-based explorations suffer from degraded single-speaker performance and the inability to reject when the target speaker is absent. In this paper, we propose Xiaomi-CocktailASR-1, an LLM-based end-to-end TS-ASR architecture. By utilizing reference speech as voiceprint prompts, it directly transcribes the target speaker's speech without requiring speech separation. Xiaomi-CocktailASR-1 maintains competitive performance in single-speaker scenarios, comparable to mainstream ASR models. It also features a negative sample rejection capability, outputting empty text when the target speaker is absent from the mixed speech. Additionally, Xiaomi-CocktailASR-1 supports a Chain-of-Thought (CoT) reasoning mode to provide explicit reasoning steps. Extensive experiments on various synthetic and real-world multispeaker benchmarks demonstrate that Xiaomi-CocktailASR-1 achieves state-of-the-art performance, effectively addressing the cocktail party problem through a unified architecture that balances multispeaker and single-speaker recognition accuracy, along with rejection capability.

cs.SD↗
arXiv2026

EConv-TasNet: Efficient Conv-TasNet for Effective Speech Separation

Conv-TasNet has served as a strong baseline for time-domain speech separation, and many studies have extended it with advanced architectures such as dual-path networks, U-Nets, and attention mechanisms. However, these methods often introduce high computational cost and complexity, limiting their deployment in resource-constrained scenarios. To address this issue, we propose eConv-TasNet, an efficient variant of Conv-TasNet that improves both effectiveness and efficiency without relying on resource-intensive modules. The proposed model consists of a group-wise early-splitting (GES) module and a multi-group feature aggregation (MGFA) module. GES generates discriminative speaker embeddings at intermediate stages, while MGFA progressively aggregates these group-level representations for refined mask estimation. Experimental results show that eConv-TasNet reduces model size by 22.4%, accelerates inference by 18.9%, and improves SI-SNRi by 14.0%-28.0% across three public benchmarks. Moreover, it achieves competitive performance compared with state-of-the-art methods while requiring significantly fewer parameters and lower inference cost. These results demonstrate a favorable efficiency-effectiveness trade-off for edge deployment.

cs.SD↗