# Speech Enhancement for Virtual Meetings on Cellular Networks

arXiv: https://arxiv.org/abs/2302.00868 · HTML: https://mlsanity.com/paper/2302.00868/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 2 Feb 2023.

## Builds on (most cited first, 7 of 7)

- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020)
- [Music Source Separation in the Waveform Domain](https://mlsanity.com/paper/1911.13254/) (2019)
- [FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement](https://mlsanity.com/paper/2010.15508/) (2020)
- [Convolutional-Recurrent Neural Networks for Speech Enhancement](https://mlsanity.com/paper/1805.00579/) (2018)
- [Online Monaural Speech Enhancement Using Delayed Subband LSTM](https://mlsanity.com/paper/2005.05037/) (2020)
- [Improving Speech Enhancement through Fine-Grained Speech Characteristics](https://mlsanity.com/paper/2207.00237/) (2022)

## Abstract (arXiv)

We study speech enhancement using deep learning (DL) for virtual meetings on cellular devices, where transmitted speech has background noise and transmission loss that affects speech quality. Since the Deep Noise Suppression (DNS) Challenge dataset does not contain practical disturbance, we collect a transmitted DNS (t-DNS) dataset using Zoom Meetings over T-Mobile network. We select two baseline models: Demucs and FullSubNet. The Demucs is an end-to-end model that takes time-domain inputs and outputs time-domain denoised speech, and the FullSubNet takes time-frequency-domain inputs and outputs the energy ratio of the target speech in the inputs. The goal of this project is to enhance the speech transmitted over the cellular networks using deep learning models.