Vuk Stanojev

Vuk Stanojev

Auto-generated profile, based on publicly available information

Vuk Stanojev

University of Novi Sad

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 February 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
NSNikola Simić
Nikola Simić
SSSiniša Suzić
Siniša Suzić
NMNemanja Milošević
Nemanja Milošević
VSVuk Stanojev
Vuk Stanojev
TNTijana Nosek
Tijana Nosek
DBDragana Bajović
Dragana Bajović
Human–machine interaction covers a range of applications in which machines should understand humans’ commands and predict their behavior. Humans commonly change their mood over time, which affects the way we interact, particularly by changing speech style and facial expressions. As interaction requires quick decisions, low latency is critical for real-time processing. Edge devices, strategically placed near the data source, minimize processing time, enabling real-time decision-making. Edge computing allows us to process data locally, thus reducing the need to send sensitive information further through the network. Despite the wide adoption of audio-only, video-only, and multimodal emotion recognition systems, there is a research gap in terms of analyzing lightweight models and solving privacy challenges to improve model performance. This motivated us to develop a privacy-preserving, lightweight, CNN-based (CNNs are frequently used for processing audio and video modalities) audiovisual emotion recognition model, deployable on constrained edge devices. The model is further paired with a federated learning protocol to preserve the privacy of local clients on edge devices and improve detection accuracy. The results show that the adoption of federated learning improved classification accuracy by ~2%, as well as that the proposed federated learning-based model provides competitive performance compared to other baseline audiovisual emotion recognition models.

22 November 2024
Verified
Book Chapter
Closed access
PDF file
TNTijana Nosek
Tijana Nosek
SSSiniša Suzić
Siniša Suzić
MSMilan Sečujski
Milan Sečujski
VSVuk Stanojev
Vuk Stanojev
DPDarko Pekar
Darko Pekar
Vlado DelićVlado Delić
Vlado Delić


1 January 2025
Verified
Conference Paper
Closed access
Vlado DelićVlado Delić
Vlado Delić
MSMilan Sečujski
Milan Sečujski
SSSiniša Suzić
Siniša Suzić
TNTijana Nosek
Tijana Nosek
VSVuk Stanojev
Vuk Stanojev
Progress in speech technology development over the past decade has been based on deep learning, and their application is a typical example of what we understand as artificial intelligence. Developing speech technologies for a language is motivated by the need to provide that language with a voice in the era of artificial intelligence, that is, enable spoken communication with machines in that language. This paper presents efforts to build such technologies for Serbian and related languages, outlining major achievements and initial broad applications. It also discusses emerging trends shaped by the growing influence of artificial intelligence in industry and education.

19 September 2026
Verified
Book Chapter
Closed access
PDF file
MSMilan Sečujski
Milan Sečujski
AVAleksandar Vujinović
Aleksandar Vujinović
AKAleksandar Kovačević
Aleksandar Kovačević
NSNikola Simić
Nikola Simić
VSVuk Stanojev
Vuk Stanojev
Vlado DelićVlado Delić
Vlado Delić

13 October 2025
Verified
Book Chapter
Closed access
PDF file
VSVuk Stanojev
Vuk Stanojev
TNTijana Nosek
Tijana Nosek
SSSiniša Suzić
Siniša Suzić
DPDarko Pekar
Darko Pekar
Vlado DelićVlado Delić
Vlado Delić
MSMilan Sečujski
Milan Sečujski