Multilingual Grapheme-to-Phoneme Translation for Low-Resource Languages

Student: Tosi Lorenzo

Supervisor: Francis M. Tyers

Educational Programme: Computational Linguistics (Master)

Year of Graduation: 2021

In this work we try to compare results on dataset, augmented with linguistic data, network normalization and character byte encoding for Grapheme-2-Phoneme translation task to apply it in Speech recognition and synthesis networks. The results shows that using an recurrent transformer with conditioning on language and linguistic group data improves the results of a vanilla model, while the other techniques are irrelevant in the context of low-resources languages.

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