Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds
Abstract
This paper introduces a speech enhancement solution tailored for true wireless stereo (TWS) earbuds on-device usage. The solution was specifically designed to support conversations in noisy environments, with active noise cancellation (ANC) activated. The primary challenges for speech enhancement models in this context arise from computational complexity that limits on-device usage and latency that must be less than 3 ms to preserve a live conversation. To address these issues, we evaluated several crucial design elements, including the network architecture and domain, design of loss functions, pruning method, and hardware-specific optimization. Consequently, we demonstrated substantial improvements in speech enhancement quality compared with that in baseline models, while simultaneously reducing the computational complexity and algorithmic latency.
Cite
@article{arxiv.2409.18705,
title = {Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds},
author = {Hanbin Bae and Pavel Andreev and Azat Saginbaev and Nicholas Babaev and Won-Jun Lee and Hosang Sung and Hoon-Young Cho},
journal= {arXiv preprint arXiv:2409.18705},
year = {2024}
}
Comments
Accepted by Interspeech 2024