Using Deep Learning for Detecting Spoofing Attacks on Speech Signals
Sound
2016-01-20 v2 Computation and Language
Cryptography and Security
Machine Learning
Machine Learning
Abstract
It is well known that speaker verification systems are subject to spoofing attacks. The Automatic Speaker Verification Spoofing and Countermeasures Challenge -- ASVSpoof2015 -- provides a standard spoofing database, containing attacks based on synthetic speech, along with a protocol for experiments. This paper describes CPqD's systems submitted to the ASVSpoof2015 Challenge, based on deep neural networks, working both as a classifier and as a feature extraction module for a GMM and a SVM classifier. Results show the validity of this approach, achieving less than 0.5\% EER for known attacks.
Cite
@article{arxiv.1508.01746,
title = {Using Deep Learning for Detecting Spoofing Attacks on Speech Signals},
author = {Alan Godoy and Flávio Simões and José Augusto Stuchi and Marcus de Assis Angeloni and Mário Uliani and Ricardo Violato},
journal= {arXiv preprint arXiv:1508.01746},
year = {2016}
}