The DET curve in assessment of detection task performance

Martín, Alvin F.; Doddington, George R.; Kamm, Teresa M.; Ordowski, Mark; Przybocki, Mark A.

doi:10.21437/eurospeech.1997-504

Cited by 838 publications

(51 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These vectors are formed of 12 LPCC and the Energy on log scale plus first and second derivatives. The results are presented as DET curves [4] showing false rejection rates as a function of false acceptance rates. Figure 2 presents a summary of the results obtained with the discriminative criterion.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Neighborhood effects on spoken word recognition in Japanese

Mariéthoz¹,

Genoud²,

Bimbot³

et al. 1999

6th European Conference on Speech Communication and Technology

View full text Add to dashboard Cite

In speaker verification, two independent stochastic models, i.e. a client model and a non-client (world) model, are generally used to verify the claimed identity using a likelihood ratio score. This paper investigates a variant of this approach based on a common hidden process for both models. In this framework, both models share the same topology, which is conditioned by the underlying phonetic structure of the utterance. Then, two different output distributions are defined corresponding to the client vs. world hypotheses. Based on this idea, a synchronous decoding algorithm and the corresponding training algorithm are derived. Our first experiments on the SESP telephone database indicate a slight improvement with respect to a baseline system using independent alignments. Moreover, synchronous alignment offers a reduced complexity during the decoding process. Interesting perspectives can be expected.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Neighborhood effects on spoken word recognition in Japanese

Mariéthoz¹,

Genoud²,

Bimbot³

et al. 1999

6th European Conference on Speech Communication and Technology

View full text Add to dashboard Cite

show abstract

“…Meng et al [8] questioned if we could use keystroke dynamics as a biometric by building a training interface and make users train themselves in simulating another person's password typing rhythm. In this study they used two groups, each one contained 8-character length passwords and they used an easy and a complex one.…”

Section: Related Workmentioning

confidence: 99%

Fixed-Text vs. Free-Text Keystroke Dynamics for User Authentication

Zeid¹,

ElKamar²,

Hassan³

2022

Engineering Research Journal - Faculty of Engineering (Shoubra)

View full text Add to dashboard Cite

There are many physical biometrics such as iris patterns and fingerprints. There are also interactive gestures like how a person types on a keyboard, moves a mouse, holds a phone, or even taps a touch screen. Keystroke dynamics or typing dynamics is an automatic method that confirms the identity of an individual based on the manner and the way of the user typing on a keyboard. There are two types of keystroke systems, Fixed-text system, and free-text system and each of them has it is own importance. In this research paper, we are investigating the possibility of classifying individuals using features extracted from their keystroke dynamics with two different datasets: (1) fixed-text dataset with different difficulty levels and (2) free-text dataset with no restrictions what a user types on the keyboard. Investigation was done using several classification techniques: RandomForest (RF), Support Vector Machines (SVM), BayesNet (BN), and K-Nearest Neighbors (KNN). The highest accuracy achieved with the fixed-text dataset was 98.8% using RF for classification while the highest achieved accuracy with the freetext dataset was 87.58 % using RF classifier.

show abstract

“…Perhaps the most commonly used performance visualising tool in the literature is the Decision Error Trade-off (DET) curve [22], which is actually a Receiver Operator Curve (ROC) curve plotted on a non-linear scale. It has been pointed out [3] that two DET curves resulted from two systems are not comparable because such comparison does not take into account how the thresholds are selected.…”

Section: Visualising the Performancementioning

confidence: 99%

A Score-Level Fusion Benchmark Database for Biometric Authentication

Poh

Bengio

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Fusing the scores of several biometric systems is a very promising approach to improve the overall system's accuracy. Despite many works in the literature, it is surprising that there is no coordinated effort in making a benchmark database available. It should be noted that fusion in this context consists not only of multimodal fusion, but also intramodal fusion, i.e., fusing systems using the same biometric modality but different features, or same features but using different classifiers. Building baseline systems from scratch often prevents researchers from putting more efforts in understanding the fusion problem. This paper describes a database of scores taken from experiments carried out on the XM2VTS face and speaker verification database. It then proposes several fusion protocols and provides some state-of-the-art tools to evaluate the fusion performance.

show abstract

The DET curve in assessment of detection task performance

Cited by 838 publications

References 2 publications

Neighborhood effects on spoken word recognition in Japanese

Neighborhood effects on spoken word recognition in Japanese

Fixed-Text vs. Free-Text Keystroke Dynamics for User Authentication

A Score-Level Fusion Benchmark Database for Biometric Authentication

Contact Info

Product

Resources

About