all InfoSec news
Aura: Privacy-preserving augmentation to improve test set diversity in noise suppression applications. (arXiv:2110.04391v2 [eess.AS] UPDATED)
April 18, 2022, 1:20 a.m. | Xavier Gitiaux, Aditya Khant, Ebrahim Beyrami, Chandan Reddy, Jayant Gupchup, Ross Cutler
cs.CR updates on arXiv.org arxiv.org
Noise suppression models running in production environments are commonly
trained on publicly available datasets. However, this approach leads to
regressions due to the lack of training/testing on representative customer
data. Moreover, due to privacy reasons, developers cannot listen to customer
content. This `ears-off' situation motivates augmenting existing datasets in a
privacy-preserving manner. In this paper, we present \aura, a solution to make
existing noise suppression test sets more challenging and diverse while being
sample efficient. \aura is `ears-off' because it …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Cyber Threat Analyst
@ Peraton | Morrisville, NC, United States
Kyndryl Offensive Security Professional - Threat-Led Penetration Testing (TLPT) and Red Teaming
@ Kyndryl | Sao Paulo (KBR51645) WeWork Office
Consultant en Cyber Sécurité - Spécialiste PKI H/F
@ Devoteam | Levallois-Perret, France
Cloud Security Architect - Advisor (Remote)
@ Fannie Mae | Reston, VA, United States
OT Cybersecurity Engineer
@ SBM Offshore | Bengaluru, IN, 560071