Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2103.12152

Musical Mix Clarity Predication using Decomposition and Perceptual Masking Thresholds

Andrew Parker·Steven Fenton
View original source ↗Read source document ↗Export metadata ↓

Abstract

Objective measurement of perceptually motivated music attributes has application in both target driven mixing and mastering methodologies and music information retrieval. This work proposes a perceptual model of mix clarity which decomposes a mixed input signal into transient, steady-state, and residual components. Masking thresholds are calculated for each component and their relative relationship is used to determine an overall masking score as the model's output. Three variants of the model were tested against subjective mix clarity scores gathered from a controlled listening test. The best performing variant achieved a Spearman's rank correlation of rho = 0.8382 (p<0.01). Furthermore, the model output was analysed using an independent dataset generated by progressively applying degradation effects to the test stimuli. Analysis of the model suggested a close relationship between the proposed model and the subjective mix clarity scores particularly when masking was measured using linearly spaced analysis bands. Moreover, the presence of noise-like residual signals was shown to have a negative effect on the perceived mix clarity.

Explore related subjects

cs.SDeess.AS

Keep this discovery

BibTeXRIS

Andrew Parker, Steven Fenton. 2021-03-22. Musical Mix Clarity Predication using Decomposition and Perceptual Masking Thresholds. https://doi.org/10.3390/app11209578

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↗