Two decades of speaker recognition evaluation at the national institute of standards and technology

Greenberg, Craig S.; Mason, Lisa P.; Sadjadi, Seyed Omid; Reynolds, Douglas A.

doi:10.1016/j.csl.2019.101032

Cited by 50 publications

(43 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The t-DCF [4] extends the conventional DCF [17] used in speaker recognition studies. We briefly review each approach.…”

Section: Tandem Detection Cost Functions (T-dcfs)mentioning

confidence: 99%

“…Neither should be compromised, but the trade-offs between the two can be adjusted (by selecting different values of τ ), and there might be different preferences for their relative severity depending on the application. Performance is therefore gauged using a flexible, parameterized DCF [17], [19], DCF = ρ tar C asv miss P asv miss + ρ non C fa P asv fa = ρ tar C asv miss P asv miss + (1 − ρ tar )C fa P asv fa ,…”

Section: A Conventional Detection Cost Function (Dcf)-one System Two Classesmentioning

confidence: 99%

See 1 more Smart Citation

Optimizing Tandem Speaker Verification and Anti-Spoofing Systems

Kanervisto

Hautamäki

Kinnunen

et al. 2022

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

As automatic speaker verification (ASV) systems are vulnerable to spoofing attacks, they are typically used in conjunction with spoofing countermeasure (CM) systems to improve security. For example, the CM can first determine whether the input is human speech, then the ASV can determine whether this speech matches the speaker's identity. The performance of such a tandem system can be measured with a tandem detection cost function (t-DCF). However, ASV and CM systems are usually trained separately, using different metrics and data, which does not optimize their combined performance. In this work, we propose to optimize the tandem system directly by creating a differentiable version of t-DCF and employing techniques from reinforcement learning. The results indicate that these approaches offer better outcomes than finetuning, with our method providing a 20% relative improvement in the t-DCF in the ASVSpoof19 dataset in a constrained setting.

show abstract

“…The t-DCF [4] extends the conventional DCF [17] used in speaker recognition studies. We briefly review each approach.…”

Section: Tandem Detection Cost Functions (T-dcfs)mentioning

confidence: 99%

Section: A Conventional Detection Cost Function (Dcf)-one System Two Classesmentioning

confidence: 99%

Optimizing Tandem Speaker Verification and Anti-Spoofing Systems

Kanervisto

Hautamäki

Kinnunen

et al. 2022

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…• C fa ≡ C(ACCEPT|θ non ) -cost of accepting a nontarget trial; • C fa,spoof ≡ C(ACCEPT|θ spoof ) -cost of accepting a spoofed trial, where the first two correspond to the familiar notations used in NIST speaker recognition evaluation (SRE) campaigns [1], [2]. The third cost is specific to the new class of spoofing attacks.…”

Section: A Detection Costs and Priors (The Application)mentioning

confidence: 99%

“…Following the practice adopted in the NIST SREs [1], [2], it is preferable to report the normalized t-DCF given by:…”

Section: A Normalizing the Unconstrained T-dcfmentioning

confidence: 99%

See 1 more Smart Citation

Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification: Fundamentals

Kinnunen

Delgado

Evans

et al. 2020

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

Recent years have seen growing efforts to develop spoofing countermeasures (CMs) to protect automatic speaker verification (ASV) systems from being deceived by manipulated or artificial inputs. The reliability of spoofing CMs is typically gauged using the equal error rate (EER) metric. The primitive EER fails to reflect application requirements and the impact of spoofing and CMs upon ASV and its use as a primary metric in traditional ASV research has long been abandoned in favour of risk-based approaches to assessment. This paper presents several new extensions to the tandem detection cost function (t-DCF), a recent risk-based approach to assess the reliability of spoofing CMs deployed in tandem with an ASV system. Extensions include a simplified version of the t-DCF with fewer parameters, an analysis of a special case for a fixed ASV system, simulations which give original insights into its interpretation and new analyses using the ASVspoof 2019 database. It is hoped that adoption of the t-DCF for the CM assessment will help to foster closer collaboration between the anti-spoofing and ASV research communities.

show abstract