COMPARISON OF PHONETIC FEATURES OF SPEECH OF VARIOUS SPEAKERS USING MACHINE LEARNING METHODS

Student: Bersenyov Artyom

Supervisor:

Faculty: Faculty of Humanities (Nizhny Novgorod)

Educational Programme: Applied Linguistics and Text Analytics (Master)

Year of Graduation: 2024

Recently, the use of machine learning has become firmly embedded in our lives and has become widely used for various human needs. They have even learned to recognize human speech, although there are some limitations. Existing speech recognition methods are insufficiently precise to discern subtleties in pronunciation by native speakers of dialects or other language variants except the generally accepted one. In this study, a novel neural network will be created and trained in an effort to overcome this problem. The model will work and improve on the basis of a large number of selected audio data with known pronunciation variants of the English language. It is expected the main hypothesis regarding the capability of a neural network to differentiate pronunciation variances will be proven.

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