Dialogue Analysis with Graph-transformers

Student: Boltachev Aleksandr

Faculty: Faculty of Informatics, Mathematics, and Computer Science (HSE Nizhny Novgorod)

Educational Programme: Data Mining (Master)

Year of Graduation: 2021

Graph neural networks are a powerful tool for analyzing data presented in the form of graphs. Since many data in speech recognition pipelines can be represented as graphs, there have been several successful attempts to apply graph neural networks in such pipelines. In this paper, a study was carried out of the possible application of convolutional graph networks as a decoder in speech recognition pipelines.

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