Tandem spoofing-robust automatic speaker verification based on time-domain embeddings
Authors:
- Avishai WeizmanAWAvishai Weizman
- Yehuda Ben-ShimolYBYehuda Ben-Shimol
- Itshak LapidotILItshak Lapidot
Preprint
Abstract
Spoofing-robust automatic speaker verification (SASV) systems are a crucial technology for the protection against spoofed speech. In this study, we focus on logical access attacks and introduce a novel approach to SASV tasks. A novel representation of genuine and spoofed speech is employed, based on the probability mass function (PMF) of waveform amplitudes in the time domain. This methodology generates novel time embeddings derived from the PMF of selected groups within the training set. This paper highlights the role of gender segregation and its positive impact on performance. We propose a countermeasure (CM) system that employs time-domain embeddings derived from the PMF of spoofed and genuine speech, as well as gender recognition based on male and female time-based embeddings. The method exhibits notable gender recognition capabilities, with mismatch rates of 0.94% and 1.79% for males and females, respectively. The male and female CM systems achieve an equal error rate (EER) of 8.67% and 10.12%, respectively. By integrating this approach with traditional speaker verification systems, we demonstrate improved generalization ability and tandem detection cost function evaluation using the ASVspoof2019 challenge database. Furthermore, we investigate the impact of fusing the time embedding approach with traditional CM and illustrate how this fusion enhances generalization in SASV architectures.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- Gender Recognition from Speech Signal Using CNN, KNN, SVM and RFProcedia Computer Science, 2024
- Voice spoofing detection for multiclass attack classification using deep learningMachine Learning with Applications, 2023
- Automatic speaker verification systems and spoof detection techniques: review and analysisInternational Journal of Speech Technology, 2021
- ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speechComputer Speech & Language, 2020
- Advances in anti-spoofing: from the perspective of ASVspoof challengesAPSIPA Transactions on Signal and Information Processing, 2020
- Constant Q cepstral coefficients: A spoofing countermeasure for automatic speaker verificationComputer Speech & Language, 2017
- An overview of voice conversion systemsSpeech Communication, 2017
- 50 years of biometric research: Accomplishments, challenges, and opportunitiesPattern Recognition Letters, 2016
- The NIST speaker recognition evaluation – Overview, methodology, systems, results, perspectiveSpeech Communication, 2000
- Biometric identification through hand geometry measurementsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000