Milan Sečujski, PhD, was born in 1975, and currently works as Associate Professor at the Faculty of Technical Sciences, University of Novi Sad, Serbia, where he is a member of the Department for Power, Electronic and Telecommunications Engineering. He is engaged as a lecturer in Digital Signal Processing, Digital Filters as well as Acoustics and Audio Engineering.
His areas of scientific interest include computational linguistics, speech and language technologies, as well as human-machine interaction. In 2002 he earned the MSc degree with the thesis “Prosodic elements in text-to-speech synthesis in the Serbian language”. The result of the thesis research is the highest quality speech synthesizer in Serbian, with elements of natural intonation. This speech synthesis system has since been widely used, initially by the blind and visually impaired computer users, but its use has since spread into the domain of telecommunications services, where it has remained the most widely used speech system in Serbian and Croatian. In 2009 Milan Sečujski earned the PhD degree with the thesis “Automatic part-of-speech tagging in the Serbian language”, whose result is an improvement in the accuracy of automatic POS tagging in Serbian, which is important for many applications of language and speech technologies (text-to-speech synthesis and speech recognition, machine translation, dialogue systems, information retrieval etc.). He has participated and currently participates in a number of national and international projects.
His current research includes natural language processing as well as mathematical modeling of the prosodic features of speech, most notably for the purposes of expressive speech synthesis as well as speaker conversion in speech synthesis. Apart from his work in the domain of speech technology, he has made scientific contribuition in the field of physical acoustics as well. He has participated as a reviewer for several peer-reviewed journals (most notably “Applied Intelligence” and “Electronics and Electrical Engineering”) and scientific conferences (including SPECOM, COST events and a number of national conferences). He is a member of international organizations such as IEEE and Audio Engineering Society (AES).
() Research published in the top international journal
Popović, B., Janev, M., Pekar, D., Jakovljević, N., Gnjatović, M., Sečujski, M., Delić, V.: "A Novel Split-and-Merge Algorithm for Hierarchical Clustering of Gaussian Mixture Models", Applied Intelligence, 2012, Vol. 37, No. 3, ISSN: 0924-669X, pp. 377-389, DOI: 10.1007/s10489-011-0333-9.
() Research published in the top international journal
Cselyuszka, N., Sečujski, M., Engheta, N., Crnojević-Bengin, V.: "Temperature-controlled acoustic surface waves", New Journal of Physics, 2016, ISSN: 1367-2630, Vol.18 (DOI: 10.1088/1367-2630/18/10/103006)
() Research published in the top international journal
Lučić B., Ostrogonac S., Vujnović Sedlar N., Sečujski M.: Educational Applications for Blind and Partially Sighted Pupils Based on Speech Technologies for Serbian, doi:10.1155/2015/839252, The Scientific World JOURNAL, 2015, Vol. 2015, No 1, pp. 1-14, ISSN 1537-744X
() Research published in the prominent international journal
Nosek (Delić) T., Suzić S., Pekar D., Obradović R., Sečujski M., Delić V.: Cross-Lingual Neural Network Speech Synthesis Based on Multiple Embeddings, International Journal of Interactive Multimedia and Artificial Intelligence, 2021, Vol. 7, No. 2, pp. 110-120, ISSN 1989-1660
() Research published in the prominent international journal
Cselyuszka, N., Sečujski, M., Crnojević-Bengin, V.: “Novel negative mass density resonant metamaterial unit cell”, Physics Letters A, Vol. 379, No. 1-2, ISSN: 0375-9601, pp. 33-36, 2015.
() Research published in the prominent international journal
Cselyuszka, N., Sečujski, M., Crnojević-Bengin, V.: "Compressibility-Near-Zero Acoustic Metamaterial", Physics Letters A, 2014, ISSN: 0375-9601, Vol. 378, No. 16-17, pp. 1153-1156.
() Research published in the prominent international journal
Delić V., Perić Z., Sečujski M., Jakovljević N., Nikolić J., Mišković D., Simić N., Suzić S., Nosek (Delić) T.: Speech technology progress based on new machine learning paradigm, DOI: 10.1155/2019/4368036, Computational Intelligence and Neuroscience, 2019, Vol. 2019, pp. 1-19, ISSN 1687-5265
() Research published in the prominent international journal
Ostrogonac S., Pakoci E., Sečujski M., Mišković D.: Morphology-based vs Unsupervised Word Clustering for Training Language Models for Serbian, Acta Polytechnica Hungarica, Journal of Applied Sciences, 2019, Vol. 16, No 2, pp. 183-197, ISSN 1785-8860
() Research published in the prominent international journal
Suzić S., Nosek (Delić) T., Pekar D., Delić V., Sečujski M.: Style Transplantation in Neural Network-based Speech Synthesis, Acta Polytechnica Hungarica, Journal of Applied Sciences, 2019, Vol. 16, No 6, pp. 171-189, ISSN 1785-8860
() Research published in the international journal
Jakovljević N., Mišković D., Janev M., Sečujski M., Delić V.: Comparison of Linear Discriminant Analysis Approaches in Automatic Speech Recognition, DOI: 10.5755/j01.eee.19.7.5167, Elektronika Ir Elektrotechnika, 2013, Vol. 19, No 7, pp. 76-79, ISSN 1392-1215
() Research published in the international journal
Milan Sečujski, Radovan Obradović, Darko Pekar, Ljubomir Jovanov, Vlado Delić: ”AlfaNum System for Speech Synthesis in Serbian Language”, Lecture Notes in Artificial Intelligence – Subseries of Lecture Notes in Computer Science, 2002, pp. 237- 244, ISSN 0302-9743.
() Research published in the international journal
Bojović Ž., Perić Z., Delić V., Šećerov E., Sečujski M., Šenk V.: “Comparative Analysis of the Performance of Different Codecs in a live VoIP network using SIP protocol”, Electronics and electrical engineering, 2012, Vol. 117, No 1, pp. 37-42, ISSN 1392-1215.
() Research published in the international journal
Sečujski M., Cselyuszka N., Crnojević-Bengin V.: A Novel Approach to Density Near-Zero Acoustic Metamaterials, Advances in Materials Science and Engineering, 2015, Vol. 2015, No ID 626593, pp. 1-6, ISSN 1687-8434
() Research published in the international journal
Delić V., Bojanić M., Gnjatović M., Sečujski M., Jovičić S.: Discrimination capability of prosodic and spectral features for emotional speech recognition DOI: http://dx.doi.org/10.5755/j01.eee.18.9.2806, Electronics and electrical engineering, 2012, Vol. 18, No 9, pp. 51-54, ISSN 1392-1215
() Research published in the international journal
Ostrogonac, S., Pakoci, E., Sečujski, M, and Mišković, D.: "Morphology-based vs Unsupervised Word Clustering for Training Class N-gram Language Models for Serbian", Acta Polytechnica Hungarica, ISSN: 1785-8860, Vol. 16, No. 2, 2019, pp. 183-197.
() Research published in the international journal
Sečujski M., Pekar D., Suzić S., Smirnov A., Nosek (Delić) T.: Speaker/Style-Dependent Neural Network Speech Synthesis Based on Speaker/Style Embedding, Journal of Universal Computer Science, 2020, Vol. 26, No. 4, pp. 434-453, ISSN 0948-695X
() Research published in the journal of the international importance verified by the special resolution
Bojanić M., Delić V., Sečujski M.: Relevance of the types and the statistical properties of features in the recognition of basic emotions in speech, DOI: 10.2298/FUEE1403425B, Facta universitatis - series: Electronics and Energetics, 2014, Vol. 27, No 3, pp. 425-433, ISSN 0353-3670
() Research published in the journal of the international importance verified by the special resolution
Popović B., Knežević D., Sečujski M., Pekar D.: Automatic Prosody Generation in a Text-To-Speech System for Hebrew, Facta universitatis - series: Electronics and Energetics, 2014, Vol. 27, No 3, pp. 467-477, ISSN 0353-3670
() Report from the international meeting printed in its entirety
Sečujski M., Jakovljević N., Pekar D.: Automatic Prosody Generation for Serbo-Croatian Speech Synthesis Based on Regression Trees, 12. Interspeech - Annual Conference of the International Speech Communication Association, Firenca: ISCA, 28-31 Avgust, 2011, pp. 3157-3160
() Report from the international meeting printed in its entirety
Delić T., Gerazov B., Popović B., Sečujski M.: A Linguistic Interpretation of the Atom Decomposition of Fundamental Frequency Contour for American English, 18. SPECOM International Conference on Speech and Computer, Budimpešta: Springer, 2016, pp. 59-66, ISBN 978-3-319-43957-0
() Report from the international meeting printed in its entirety
Sečujski M., Gerazov B., Csapó T., Delić V., Garner P., Gjoreski A., Guennec D., Ivanovski Z., Melov A., Németh G., Stojković A., Szaszák G.: Design of a Speech Corpus for Research on Cross-Lingual Prosody Transfer, 18. SPECOM International Conference on Speech and Computer, Budimpešta: Springer, 23-27 Avgust, 2016, pp. 199-206, ISBN 978-3-319-43957-0