An Overview of Automatic Speaker Verification System

Naika, Ravika

doi:10.1007/978-981-10-7245-1_59

Cited by 15 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the main biometric techniques can already handle noisy environments robustly [2], [3], their vulnerability to malicious spoofing attacks is still a serious concern nowadays [4], [5]. Our focus in this work is on spoofing detection for automatic speaker verification (ASV) [6], in which an impostor could gain fraudulent access to a system or resource (e.g., bank account) by presenting speech resembling the voice of a genuine user.…”

Section: Introductionmentioning

confidence: 99%

On Joint Optimization of Automatic Speaker Verification and Anti-Spoofing in the Embedding Space

Gomez-Alanis

Gonzalez-Lopez

Dubagunta

et al. 2021

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

Biometric systems are exposed to spoofing attacks which may compromise their security, and voice biometrics based on automatic speaker verification (ASV), is no exception. To increase the robustness against such attacks, anti-spoofing systems have been proposed for the detection of replay, synthesis and voice conversion-based attacks. However, most proposed antispoofing techniques are loosely integrated with the ASV system. In this work, we develop a new integration neural network which jointly processes the embeddings extracted from ASV and antispoofing systems in order to detect both zero-effort impostors and spoofing attacks. Moreover, we propose a new loss function based on the minimization of the area under the expected (AUE) performance and spoofability curve (EPSC), which allows us to optimize the integration neural network on the desired operating range in which the biometric system is expected to work. To evaluate our proposals, experiments were carried out on the recent ASVspoof 2019 corpus, including both logical access (LA) and physical access (PA) scenarios. The experimental results show that our proposal clearly outperforms some well-known techniques based on the integration at the score-and embeddinglevel. Specifically, our proposal achieves up to 23.62% and 22.03% relative equal error rate (EER) improvement over the best performing baseline in the LA and PA scenarios, respectively, as well as relative gains of 27.62% and 29.15% on the AUE metric.Index Terms-Automatic speaker verification (ASV), spoofing detection, embeddings, integration of ASV and anti-spoofing, expected performance and spoofability curve (EPSC).

show abstract

Section: Introductionmentioning

confidence: 99%

On Joint Optimization of Automatic Speaker Verification and Anti-Spoofing in the Embedding Space

Gomez-Alanis

Gonzalez-Lopez

Dubagunta

et al. 2021

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

show abstract

“…Based on the total variability space, the GMM mean supervector containing speaker and channel information in the speech data can be expressed as = + M m Tw (1) where m is the mean supervector of the universal background model (UBM) independent of the speaker and channel; T is the total variability space which is defined by the total variability matrix; and w is a low-dimensional latent variable that obeys the normal distribution, known as the total variability factor vector, or identity vector (i-vector). Total variability factor analysis can be regarded as a feature-extraction module.…”

Section: Total Variability Factor Analysismentioning

confidence: 99%

“…Speaker verification is a subtask of speaker recognition, whose purpose is to verify whether a segment of speech is spoken by a designated speaker [1] [2]. Total variability factor analysis has been widely used in speaker verification [3] [4] [5] [6].…”

Section: Introductionmentioning

confidence: 99%

Locality Preserving Discriminant Projection for Speaker Verification

Chen¹,

Cao²,

Cao³

2020

JCC

View full text Add to dashboard Cite

“…Voice biometrics aims to authenticate the identity claimed by a given individual based on the speech samples measured from his/her voice. Automatic speaker verification (ASV) [1] is the conventional way to put voice biometrics into practical usage. However, in recent years, ASV technology has been shown to be at risk of security threats performed by impostors who want to gain fraudulent access by presenting speech resembling the voice of a legitimate user [2,3].…”

Section: Introductionmentioning

confidence: 99%

Adversarial Transformation of Spoofing Attacks for Voice Biometrics

Gomez-Alanis¹,

González²,

Peinado³

2021

IberSPEECH 2021

View full text Add to dashboard Cite

Voice biometric systems based on automatic speaker verification (ASV) are exposed to spoofing attacks which may compromise their security. To increase the robustness against such attacks, anti-spoofing or presentation attack detection (PAD) systems have been proposed for the detection of replay, synthesis and voice conversion based attacks. Recently, the scientific community has shown that PAD systems are also vulnerable to adversarial attacks. However, to the best of our knowledge, no previous work have studied the robustness of full voice biometrics systems (ASV + PAD) to these new types of adversarial spoofing attacks. In this work, we develop a new adversarial biometrics transformation network (ABTN) which jointly processes the loss of the PAD and ASV systems in order to generate white-box and black-box adversarial spoofing attacks. The core idea of this system is to generate adversarial spoofing attacks which are able to fool the PAD system without being detected by the ASV system. The experiments were carried out on the ASVspoof 2019 corpus, including both logical access (LA) and physical access (PA) scenarios. The experimental results show that the proposed ABTN clearly outperforms some well-known adversarial techniques in both white-box and black-box attack scenarios.

show abstract

An Overview of Automatic Speaker Verification System

Cited by 15 publications

References 13 publications

On Joint Optimization of Automatic Speaker Verification and Anti-Spoofing in the Embedding Space

On Joint Optimization of Automatic Speaker Verification and Anti-Spoofing in the Embedding Space

Locality Preserving Discriminant Projection for Speaker Verification

Adversarial Transformation of Spoofing Attacks for Voice Biometrics

Contact Info

Product

Resources

About