Leveraging Pretrained Models for Automatic Speech Recognition in Psychotherapy Sessions
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3ADSEXBG9R" target="_blank" >RIV/00216208:11320/25:DSEXBG9R - isvavai.cz</a>
Result on the web
<a href="https://excel.fit.vutbr.cz/submissions/2023/016/16.pdf" target="_blank" >https://excel.fit.vutbr.cz/submissions/2023/016/16.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Leveraging Pretrained Models for Automatic Speech Recognition in Psychotherapy Sessions
Original language description
The DeePsy project aims to design and develop features that accurately model psychotherapeutic session dynamics, which can reveal subtle nuances essential for in-depth session analysis. However, these features are directly impacted by the accuracy of the preceding systems and are deemed unreliable with flawed Automatic Speech Recognition (ASR) systems.
Czech name
—
Czech description
—
Classification
Type
O - Miscellaneous
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů