Thesis Defense - Çağıl Süslü (MSCS)

Çağıl Süslü - M.Sc.Computer Science

Assoc. Prof. Cenk Demiroğlu – Advisor

Date: 18.01.2021

Time: 14:00

Location: This meeting will be held ONLINE. Please send an e-mail to gizem.bakir@ozyegin.edu.tr in order to participate in this defense.

Uncertainty Assessment for

Speaker Verification Systems Using a

Bayesian Approach

Thesis Committee:

Assoc. Prof. Cenk Demiroğlu , Özyeğin University

Assoc. Prof. Hasan Sözer, Özyeğin University

Professor Ümit Güz, Işık University

Abstract:

The Automatic Speaker Verification (ASV) systems are developed to discriminate the genuine speakers from the spoofing attacks and they are also used as a security application in various industries (e.g., Banking and telephone-based systems). The spoofing countermeasure systems (SCS) are important for the ASV systems to protect themselves against spoofing attacks. In general, the SCSs are developed using the cross entropy loss function and the softmax classification layer to perform the best classification scores. Even though the softmax function is popularly used as a classification layer for the deep neural network tasks, it increases the uncertainty of the estimated class probabilities by squishing the probabilistic predictions of the predictive models.

The aim of this work was to decrease uncertainty of the conventional cross entropy metrics and softmax function SCS by using the Bayesian approach. To accomplish this, multiple SCSs were developed to outperform the base system of the Automatic Speaker Verification Spoofing and Countermeasures 2017 Challenge. The Bayesian approach was applied to the best model (e.g., the model which performed the lowest EER score) to decrease the uncertainty of the conventional cross entropy metrics and softmax function SCS. The uncertainty of the both systems were compared with the probability distribution function, AUC value and the ROC curve. As it can be observed from the ROC curve, the Bayesian network decreased the uncertainty of the conventional cross entropy metrics and softmax function SCS by increasing AUC value $14\%$. Also, the Bayesian network has provided the lowest EER score ($16.79\%$) by outperforming the base system of the ASV spoof 2017 challenge.

Bio: 

     Çağıl Süslü earned her B.Sc. degree in Business Administration at Özyeğin University. She has been pursuing her M.Sc. degree in Computer Science at Özyeğin university since September 2017, under the supervision of Dr. Murat Şensoy and since February 2019, under the supervision of Dr. Cenk Demiroğlu. She works on automatic speaker verification systems and speaker countermeasure systems in Dr. Cenk Demiroğlu’s Speech Processing laboratory. She is also interested in uncertainty measurement in deep neural network systems and the Bayesian theory.