Foreign accent conversion using transformers

Student: Koltiugin Maksim

Faculty: St. Petersburg School of Physics, Mathematics, and Computer Science

Educational Programme: Machine Learning and Data Analysis (Master)

Year of Graduation: 2024

Based on the results of the work done, a parallel dataset was synthesized. The generated dataset contains 200 different voices. For each voice, on average, there are about 40 minutes of speech - phrases of 4-10 seconds. The total duration of the generated dataset was 140 hours. The model architecture is proposed, the model is implemented and trained. The model copes with the task worse than the baseline. The reasons are analyzed and conclusions are drawn.

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