Branko Marković

Prof. Dr. Branko Marković

orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
12 September 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JGJovan Galić
Jovan Galić
BMBranko Marković
Branko Marković
ĐGĐorđe Grozdić
Đorđe Grozdić
Branislav PopovićBranislav Popović
Branislav Popović
SSSlavko Sajic
Slavko Sajic
Modern Automatic Speech Recognition (ASR) systems are primarily designed to recognize normal speech. Due to a considerable acoustic mismatch between normal speech and whisper, ASR systems suffer from a significant loss of performance in whisper recognition. Creating large databases of whispered speech is expensive and time-consuming, so research studies explore the synthetic generation using pre-existing normal or whispered speech databases. The impact of standard audio data augmentation techniques on the accuracy of isolated-word recognizers based on Hidden Markov Models (HMM) and Convolutional Neural Networks (CNN) is examined in this research study. Furthermore, the study explores the potential of inverse filtering as an augmentation strategy for producing pseudo-whisper speech. The Whi-Spe speech database, containing recordings in normal and whisper phonation, is utilized for data augmentation, while the internally recorded speech database, developed specifically for this study, is employed for testing purposes. Experimental results demonstrate statistically significant improvement in performance when employing data augmentation strategies and inverse filtering.

1 January 2014
Verified
Book Chapter
Closed access
PDF file
JGJovan Galić
Jovan Galić
SJSlobodan T. Jovičić
Slobodan T. Jovičić
ĐGĐorđe Grozdić
Đorđe Grozdić
BMBranko Marković
Branko Marković

22 November 2017 in Journal of Communications Technology and Electronics
Verified
Journal Article
Closed access
PDF file
BMBranko Marković
Branko Marković
JGJ. Galić
J. Galić
ÐGÐ. Grozdić
Ð. Grozdić
SJS. T. Jovičić
S. T. Jovičić
MMM. Mijić
M. Mijić
This paper presents the results on whispered speech recognition using gammatone filterbank cepstral coefficients for speaker dependent mode. The isolated words used for this experiment are taken from

25 November 2025
Verified
Conference Paper
Closed access
BMBranko Marković
Branko Marković
VLVeljko Lončarević
Veljko Lončarević
JGJovan Galić
Jovan Galić
This paper presents the implementation of 1DCNN for whispered speech recognition. At the front end, MFCCs were used to construct feature vectors, while the back end employed a 1D-CNN for training, validation, and testing. Speech patterns were taken from the Whi-Spe database, considering two speakers (one male and one female). Four types of feature vectors were examined through different scenarios: Normal/Normal, Whisper/Whisper, Normal/Whisper, and Whisper/Normal. The results confirm the effectiveness of 1DCNN for speech recognition.

31 July 2024
Verified
Conference Paper
Closed access
UČUniverzitet U Kragujevcu - Fakultet Tehničkih Nauka Čačak
Univerzitet U Kragujevcu - Fakultet Tehničkih Nauka Čačak
BMBranko Marković
Branko Marković
Đorđe DamnjanovićĐorđe Damnjanović
Đorđe Damnjanović
In this paper the results of normal and whispered speech recognition based on DWT (Discrete Wavelet Transformation) are presented. The feature vectors are obtained based on Daubechies sub-band energy. The experiments are performed using a part of the Whi-Spe database (one female and one male speaker). A back-end of the ASR system is based on DTW (Dynamic Time Warping) algorithm. The following scenarios are analyzed: normal/normal, whisper/whisper, normal/whisper and whisper/normal in the speaker dependent mode. The results confirmed the usefulness of Wavelet transformation in speech recognition.

1 January 2024
Verified
Conference Paper
Closed access
BMBranko Marković
Branko Marković
MVMilan Vesković
Milan Vesković
This paper will present the results of speech recognition based on different Daubechies wavelet orders. Two speakers (one female and one male) were analyzed in two speech modes: normal and whisper. The patterns are used from the Whi-Spe database. As an input to the recognition system, the Daubechies wavelet feature vectors with different orders were used. As a back-end of the system, the standard Dynamic Time Warping method was considered. The results are given in the form of tables and histograms. They suggest which order of Daubechies is the most convenient for this kind of speech recognition.