Modern Voice Authentication Systems

Student: Artyom Bekyan

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2024

As deep learning develops, bypassing voice authentication systems becomes easier. One of the significant problems is connected with the great variety of possible attacks, making Out-Of-Domain (OOD) generalization crucial. This paper proposes a novel framework that achieves this goal by using multi-task learning. Unlike the previous approach, our framework applies to the models that use raw waveform as the front-end. The experimental results show that it can significantly improve the model prediction quality.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses