Decoding Speech from ECoG with Machine Translation Models

dc.contributor.advisorShvai, Nadyia
dc.contributor.advisorWang, Bo
dc.contributor.authorBurakov, Roman
dc.date.accessioned2024-04-05T06:50:49Z
dc.date.available2024-04-05T06:50:49Z
dc.date.issued2023
dc.description.abstractThis paper explores the use and improvement of brain-computer interface (BCI)- based speech neuroprostheses, devices designed to enhance communication for individuals with speech disorders. Focusing on the machine learning aspect, we address the existing challenges associated with these systems, such as the limited vocabulary and simple algorithms of previous research and the individual variances in electrode implantation sites. Our approach reframes the decoding of speech from BCI as a machine translation problem and employs existing language models for semantic knowledge transfer. This research provides an extensive analysis of current neural speech decoding and multilingual neural machine translation methods, adapts the pre-existing M2M100 neural machine translation model for decoding ECoG data into text, and introduces a state-of-the-art model for neural speech decoding that improves upon current methods in semantic text reconstructions.en_US
dc.identifier.urihttps://ekmair.ukma.edu.ua/handle/123456789/28676
dc.language.isoenen_US
dc.statusfirst publisheden_US
dc.subjectWord Error Rateen_US
dc.subjectBLEU scoreen_US
dc.subjectBERTScoreen_US
dc.subjectdecoding speech with machine translation modelsen_US
dc.subjectacknowledgementsen_US
dc.subjectbachelor thesisen_US
dc.titleDecoding Speech from ECoG with Machine Translation Modelsen_US
dc.typeOtheren_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
Burakov_Bakalavrska_robota.pdf
Size:
6.56 MB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
Burakov_Bakalavrska_robota 2.pdf
Size:
290.79 KB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: