Roman Jarina

University of Žilina — SK

Computer Science · Physical Sciences

13h-index760citations86works1.12yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech and Audio Processing(50), Music and Audio Processing(39), Speech Recognition and Synthesis(26), Music Technology and Sound Studies(10), Emotion and Mood Recognition(7)

Publications85 total

Voice Authentication Prototype using Speaker Embeddings for Hands-On Demonstration
2025
The Role of Room Impulse Response in Educational Applications
2025
A Deep Learning Approach to Phonocardiogram Segmentation for Educational Applications
2025
THE ACOUSTICS OF FATRA HOUSE OF ARTS IN ZILINA, SLOVAKIA
Akustika·2025Open Access
Speech Emotion Recognition Using Transfer Learning: Integration of Advanced Speaker Embeddings and Image Recognition Models
Applied Sciences·2024· 8 citedOpen Access
Critical Review of Current Audiometric Screening Practices and the Impact of Hearing Loss on Preschool and School-Aged Children
2024
Efficient Low-Complexity Speaker Identification based on a SpeakerGAN Approach
2024
Enhancing Speech Emotion Recognition Using Transfer Learning from Speaker Embeddings
Lecture notes in computer science·2024· 1 cited
Deep speaker embeddings for Speaker Verification: Review and experimental comparison
Engineering Applications of Artificial Intelligence·2023· 30 cited
Hybrid binaural singing voice separation
2023· 1 cited
Dataset Conversion for Spiking Neural Networks
2023
Speech Command Recognition Based on Convolutional Spiking Neural Networks
2023· 9 cited
Converting Data for Spiking Neural Network Training
International Journal of Advanced Computer Science and Applications·2023Open Access
Attention Layers for Temporal RNN Modeling of Speech Emotions
2022
Frequency Response of Smartphones at the Upper Limit of the Audible Range
2022 ELEKTRO (ELEKTRO)·2022· 10 cited
Evaluation of blind source separation algorithms applied to music signals
2022 ELEKTRO (ELEKTRO)·2022· 1 cited
Sound event detection using class activation maps
2022 ELEKTRO (ELEKTRO)·2022
Towards efficiency of a subjective evaluation for music source separation
2022· 1 cited
Enhanced Speaker Embeddings with CNN-based Multi-scaling Features
2022
Exploiting hierarchy in environmental sound classification
2022· 3 cited
page 1 of 5Next →

Frequent Co-authors

Michal Chmulík(14), Eva Lieskovská(10), Maroš Jakubec(10), Michal Kuba(6), Jozef Polacký(5), Patrik Kamencay(4), Peter Kasák(4), Noel E. O’Connor(4), Seán Marlow(4), Peter Počta(4), Miroslav Gutten(4), Richard Orjesek(3), Noel Murphy(3), Martin Hric(3), Ján Olajec(3), Martin Paralič(3), Peter Brncal(3), Matej Kučera(3), Martina Zachariášová(2), M. S. S. Malik(2)