Single-Channel Distance-Based Source Separation for Mobile GPU in Outdoor and Indoor Environments

TL;DR

This paper introduces a novel distance-based source separation model optimized for mobile GPUs, specifically targeting outdoor environments, and demonstrates significant improvements in energy efficiency and real-time processing.

Contribution

The study presents a new outdoor-focused DSS model using advanced techniques like conformer blocks and linear RSA, optimized for mobile GPU deployment.

Findings

Enhanced separation performance in outdoor environments.

Improved energy efficiency on mobile devices.

Real-time inference capability achieved.

Abstract

This study emphasizes the significance of exploring distance-based source separation (DSS) in outdoor environments. Unlike existing studies that primarily focus on indoor settings, the proposed model is designed to capture the unique characteristics of outdoor audio sources. It incorporates advanced techniques, including a two-stage conformer block, a linear relation-aware self-attention (RSA), and a TensorFlow Lite GPU delegate. While the linear RSA may not capture physical cues as explicitly as the quadratic RSA, the linear RSA enhances the model's context awareness, leading to improved performance on the DSS that requires an understanding of physical cues in outdoor and indoor environments. The experimental results demonstrated that the proposed model overcomes the limitations of existing approaches and considerably enhances energy efficiency and real-time inference speed on mobile devices.