On Metric-based Deep Embedding Learning for Text-Independent Speaker Verification

Kashani, Hamidreza Baradaran; Reza, Shaghayegh; Rezaei, Iman Sarraf

doi:10.1109/icspis51611.2020.9349565

Cited by 1 publication

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In other biometrics domains (e.g., person re-identification [7], speaker verification [8]), a technique called metric learning (more specifically, deep metric learning) has seen great success. Metric learning aims to embed input data into a well-clustered embedding space, where embeddings from the same class are close together and embeddings from different classes are far apart.…”

Section: Introductionmentioning

confidence: 99%

Eye Know You: Metric Learning for End-to-end Biometric Authentication Using Eye Movements from a Longitudinal Dataset

Lohr¹,

Griffith²,

Komogortsev³

2021

Preprint

View full text Add to dashboard Cite

While numerous studies have explored eye movement biometrics since the modality's inception in 2004, the permanence of eye movements remains largely unexplored as most studies utilize datasets collected within a short time frame. This paper presents a convolutional neural network for authenticating users using their eye movements. The network is trained with an established metric learning loss function, multi-similarity loss, which seeks to form a well-clustered embedding space and directly enables the enrollment and authentication of out-of-sample users. Performance measures are computed on GazeBase, a task-diverse and publicly-available dataset collected over a 37-month period. This study includes an exhaustive analysis of the effects of training on various tasks and downsampling from 1000 Hz to several lower sampling rates. Our results reveal that reasonable authentication accuracy may be achieved even during a low-cognitive-load task or at low sampling rates. Moreover, we find that eye movements are quite resilient against template aging after 3 years.

show abstract

Section: Introductionmentioning

confidence: 99%