Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds

Hanbin Bae, Pavel Andreev, Azat Saginbaev, Nicholas Babaev, Won-Jun Lee +2 more
9/27/2024
eess.AScs.AIcs.SD

No official code found. Best implementation: qianjr2002/WaveUNetLSTM (4 stars, MIT, last commit 2026-01-07).

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.

View on arXivView PDF

Code Implementations(1)

qianjr2002/WaveUNetLSTMCommunity59%
MIT

Unofficial implementation of the baseline Wave-U-Net + LSTM model for Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds.

41PythonJan 7, 20269 months agoMIT

Similar Papers

SUBARU: A Practical Approach to Power Saving in Hearables Using SUB-Nyquist Audio Resolution Upsampling

81% match2025

IMSE: Efficient U-Net-based Speech Enhancement using Inception Depthwise Convolution and Amplitude-Aware Linear Attention

80% match2025

FINALLY: fast and universal speech enhancement with studio-like quality

79% match2026

Effects of Dataset Sampling Rate for Noise Cancellation through Deep Learning

78% match2024

Look Once to Hear: Target Speech Hearing with Noisy Examples

78% match1 repo6102024

xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement

78% match1 repo602025

Cite this paper

@article{bae2024speech,
  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},
  year   = {2024},
  eprint = {2409.18705},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.18705v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.18705.svg)](https://codeofpaper.com/paper/2409.18705)

Discussion