Baseline Systems for the First Spoofing-Aware Speaker Verification Challenge: Score and Embedding Fusion - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Baseline Systems for the First Spoofing-Aware Speaker Verification Challenge: Score and Embedding Fusion

Abstract

Deep learning has brought impressive progress in the study of both automatic speaker verification (ASV) and spoofing countermeasures (CM). Although solutions are mutually dependent, they have typically evolved as standalone sub-systems whereby CM solutions are usually designed for a fixed ASV system. The work reported in this paper aims to gauge the improvements in reliability that can be gained from their closer integration. Results derived using the popular ASVspoof2019 dataset indicate that the equal error rate (EER) of a state-of-the-art ASV system degrades from 1.63% to 23.83% when the evaluation protocol is extended with spoofed trials.%subjected to spoofing attacks. However, even the straightforward integration of ASV and CM systems in the form of score-sum and deep neural network-based fusion strategies reduce the EER to 1.71% and 6.37%, respectively. The new Spoofing-Aware Speaker Verification (SASV) challenge has been formed to encourage greater attention to the integration of ASV and CM systems as well as to provide a means to benchmark different solutions.

Dates and versions

hal-03652819 , version 1 (27-04-2022)

Identifiers

Cite

Hye-Jin Shim, Hemlata Tak, Xuechen Liu, Hee-Soo Heo, Jee-Weon Jung, et al.. Baseline Systems for the First Spoofing-Aware Speaker Verification Challenge: Score and Embedding Fusion. Odyssey 2022 - The Speaker and Language Recognition Workshop, Jun 2022, Beijing, China. ⟨hal-03652819⟩
81 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More