Data Quality as Predictor of Voice Anti-Spoofing Generalization

03/26/2021
by   Bhusan Chettri, et al.
0

Voice anti-spoofing aims at classifying a given speech input either as a bonafide human sample, or a spoofing attack (e.g. synthetic or replayed sample). Numerous voice anti-spoofing methods have been proposed but most of them fail to generalize across domains (corpora) – and we do not know why. We outline a novel interpretative framework for gauging the impact of data quality upon anti-spoofing performance. Our within- and between-domain experiments pool data from seven public corpora and three anti-spoofing methods based on Gaussian mixture and convolutive neural network models. We assess the impacts of long-term spectral information, speaker population (through x-vector speaker embeddings), signal-to-noise ratio, and selected voice quality features.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

10/27/2020

One-class learning towards generalized voice spoofing detection

Human voices can be used to authenticate the identity of the speaker, bu...
06/11/2021

Visualizing Classifier Adjacency Relations: A Case Study in Speaker Verification and Voice Anti-Spoofing

Whether it be for results summarization, or the analysis of classifier f...
04/01/2019

ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks

We present JHU's system submission to the ASVspoof 2019 Challenge: Anti-...
01/23/2019

Generalization of Spoofing Countermeasures: a Case Study with ASVspoof 2015 and BTAS 2016 Corpora

Voice-based biometric systems are highly prone to spoofing attacks. Rece...
07/21/2021

A Tandem Framework Balancing Privacy and Security for Voice User Interfaces

Speech synthesis, voice cloning, and voice conversion techniques present...
06/25/2020

Dynamically Mitigating Data Discrepancy with Balanced Focal Loss for Replay Attack Detection

It becomes urgent to design effective anti-spoofing algorithms for vulne...
04/12/2019

KeyForge: Mitigating Email Breaches with Forward-Forgeable Signatures

Email breaches are commonplace, and they expose a wealth of personal, bu...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.