Speech Enhancement for Virtual Meetings on Cellular Networks
This work addresses speech quality issues for users in virtual meetings on cellular devices, but it appears incremental as it focuses on dataset collection and baseline evaluation without novel method development.
The paper tackles speech enhancement for virtual meetings on cellular networks by collecting a transmitted DNS dataset to address practical disturbances, and evaluates baseline models like Demucs and FullSubNet, but does not report specific performance numbers or results.
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.