A Computationally Efficient and Practically Feasible Two Microphones Blind Speech Separation Method

TL;DR

This paper introduces a computationally efficient two-microphone blind speech separation method that leverages data-driven localization to enable real-time applications like hearing aids, demonstrated on a smartphone device.

Contribution

It proposes a novel approach combining localization with IVA to reduce computational load, making blind speech separation feasible for real-world, real-time use.

Findings

Significant reduction in computational complexity.

Effective separation of speech and noise in real-world scenarios.

Validated on smartphone device with positive subjective and objective results.

Abstract

Traditionally, Blind Speech Separation techniques are computationally expensive as they update the demixing matrix at every time frame index, making them impractical to use in many Real-Time applications. In this paper, a robust data-driven two-microphone sound source localization method is used as a criterion to reduce the computational complexity of the Independent Vector Analysis (IVA) Blind Speech Separation (BSS) method. IVA is used to separate convolutedly mixed speech and noise sources. The practical feasibility of the proposed method is proved by implementing it on a smartphone device to separate speech and noise in Real-World scenarios for Hearing-Aid applications. The experimental results with objective and subjective tests reveal the practical usability of the developed method in many real-world applications.