prikaz prve stranice dokumenta Prepoznavanje glasovnih naredbi u skladištu
Access restricted to students and staff of home institution
master's thesis
Prepoznavanje glasovnih naredbi u skladištu
2023. urn:nbn:hr:166:991403
Mravak, Marina
University of Split
Faculty of Science
Department of Informatics

Cite this document

Mravak, M. (2023). Prepoznavanje glasovnih naredbi u skladištu (Master's thesis). Split: University of Split, Faculty of Science. Retrieved from https://urn.nsk.hr/urn:nbn:hr:166:991403

Mravak, Marina. "Prepoznavanje glasovnih naredbi u skladištu." Master's thesis, University of Split, Faculty of Science, 2023. https://urn.nsk.hr/urn:nbn:hr:166:991403

Mravak, Marina. "Prepoznavanje glasovnih naredbi u skladištu." Master's thesis, University of Split, Faculty of Science, 2023. https://urn.nsk.hr/urn:nbn:hr:166:991403

Mravak, M. (2023). 'Prepoznavanje glasovnih naredbi u skladištu', Master's thesis, University of Split, Faculty of Science, accessed 23 April 2024, https://urn.nsk.hr/urn:nbn:hr:166:991403

Mravak M. Prepoznavanje glasovnih naredbi u skladištu [Master's thesis]. Split: University of Split, Faculty of Science; 2023 [cited 2024 April 23] Available at: https://urn.nsk.hr/urn:nbn:hr:166:991403

M. Mravak, "Prepoznavanje glasovnih naredbi u skladištu", Master's thesis, University of Split, Faculty of Science, Split, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:166:991403

Please login to the repository to save this object to your list.
Metadata
TitlePrepoznavanje glasovnih naredbi u skladištu
Title (english)Speech command recognition in a warehouse environment
AuthorMarina Mravak
MentorSaša Mladenović (mentor)
Committee memberSaša Mladenović (predsjednik povjerenstva)
Committee memberDivna Krpan (član povjerenstva)
Committee memberGoran Zaharija (član povjerenstva)
GranterUniversity of Split
Faculty of Science
(Department of Informatics)
Split
Defense date and country2023-09-19, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Prepoznavanje glasovnih naredbi pojavilo se kao obećavajuće rješenje za pojednostavljenje skladišnih operacija. Ovim radom provodi se pregled literature kako bi se istražila postojeća istraživanja u prepoznavanju govora u općim domenama, uključujući sustave za upravljanje skladištem. Predstavljen je model koji se temelji na dubokom učenju, arhitekturi konvolucijske neuronske mreže (CNN) usmjerene na skup podataka Google Speech Commands. Izvedba modela procjenjuje se kao vrlo slična optimiziranim postojećim metodama. Prikupljanje novog skupa podataka pokazuje nezadovoljavajuće rezultate i identificira nedostatke u pristupu. Ističe se važnost standardizacije i ostavlja prostor za unapređenje izvedbe modela u stvarnim scenarijima.
Abstract (english)
Speech recognition has emerged as a promising solution for the simplification of warehouse operations. This paper conducts a literature review to examine existing research in speech recognition in general domains, including warehouse management system. A model based on deep learning convolutional neural network architecture, centered on the Google Speech Commands dataset, is presented. The estimated performance of the model does not deviate significantly from the optimized existing methods. The collection of new data reveals unsatisfactory results and exposes gaps in the approach. Emphasizing the importance of standardization suggests opportunities for enhancing model performance in real-world scenarios.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:166:991403
Study programmeTitle: Data Science and Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra podatkovne znanosti i inženjerstva (magistar/magistra podatkovne znanosti i inženjerstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2023-09-20 07:07:33