profile picture

Branislav Gerazov

Speech Technology and Biomedical Signal Processing Enhtusiast

Publications

This is a list of my work grouped by field. The list is non-exhaustive and in need of an update. For the chronological list click here.



Deep Learning

  1. Gerazov B. and M. Wagner, “ProsoBeast Prosody Annotation Tool,” submitted to Interspeech 2021, in ArXiv e-prints, 6 Apr 2021. https://arxiv.org/abs/2104.02397
  2. Xu A., D. van Niekerk, B. Gerazov, P.K. Krug, S. Prom-on, P. Birkholz, and Y. Xu, “Model-based exploration of linking between vowel articulatory space and acoustic space ,” submitted to Interspeech 2021.

  3. Gerazov B., G. Bailly, O. Mohammed, Y. Xu, and P. Garner, “A Variational Prosody Model for the decomposition and synthesis of speech prosody,” In ArXiv e-prints, 18 Mar 2019. https://arxiv.org/abs/1806.08685 [RG]

  4. Mitrovski F., B. Gerazov, Z. Ivanovski, and D. Tashkovski, “Towards a system for automatic media transcription in Macedonian,” 28th Telecommunications forum TELFOR 2020, Serbia, Belgrade, Nov 24 – 25, 2020.

  5. Chavdar M., B. Gerazov, Z. Ivanovski, and T. Kartalov, “Towards a system for automatic traffic sound event detection,” 28th Telecommunications forum TELFOR 2020, Serbia, Belgrade, Nov 24 – 25, 2020.

  6. Gerazov B., G. Bailly, O. Mohammed, Y. Xu, and P. Garner, “Embedding Context-Dependent Variations of Prosodic Contours using Variational Encoding for Decomposing the Structure of Speech Prosody,” Workshop on Prosody and Meaning: Information Structure and Beyond, Aix-en-Provence, France, 8 November 2018. [RG]

  7. Gerazov B., G. Bailly, and Y. Xu, “A Weighted Superposition of Functional Contours model for modelling contextual prominence of elementary prosodic contours,” in INTERSPEECH, 02 – 07 Sep, 2018. [RG]

  8. Gerazov B., G. Bailly, and Y. Xu, “The significance of scope in modelling tones in Chinese,” in Tonal Aspects of Languages, Berlin, Germany, 18 – 20 Jun, 2018. [RG]

  9. Gerazov B. and G. Bailly, “PySFC – A System for Prosody Analysis based on the Superposition of Functional Contours Prosody Model,” in Speech Prosody, Poznan, Poland, 13 – 16 Jun, 2018. [RG]

  10. Gerazov B. and R.C. Conceição, “Deep learning for tumour classification in homogeneous breast tissue in medical microwave imaging,” Smart Technologies, IEEE EUROCON 2017-17th International Conference on, pp. 564-569, 2017.[RG]

Machine Learning

  1. Szaszák G., M. Á. Tündik, and B. Gerazov, “Prosodic stress detection for fixed stress languages using formal atom decomposition and a statistical hidden Markov hybrid,” in Speech Communication, Elsevier, vol. 102, pp. 14-26, September 2018.

  2. Melov A., B. Gerazov, and Z. Ivanovski, “Delay based optimisation of an integrated online call recording speaker diarisation and identification system,” IEEE EUROCON 2017, Ohrid, Macedonia, 6-8 Jul 2017. [RG]

  3. M. Á. Tündik, B. Gerazov, A. Gjoreski, and G. Szaszák, “Atom Decomposition Based Stress Detection and Automatic Phrasing of Speech,” 7th IEEE International Conference on Cognitive Infocommunications – CogInfoCom 2016, Wroclaw, Poland, 16-18 October, 2016. [RG]
  4. Melov A., B. Gerazov, and Z. Ivanovski, “Overview of Text-Independent Speaker Identification,” ETAI, Struga, Macedonia, Sep 22-24, 2016. [RG]
  5. Szaszák G., M. Á. Tündik, B. Gerazov, and A. Gjoreski, “Combining Atom Decomposition of the F0 Track and HMM-based Phonological Phrase Modelling for Robust Stress Detection in Speech,” International Conference on Speech and Computer SPECOM, Budapest, Hungary, 23-27 Aug, 2016. [RG]
  6. Matovski B., B. Maksimovic, B. Gerazov, and J. Kosev, “A Dynamic Time Warping Based Macedonian Automatic Speech Recognition System for Smart Home Applications,” ETAI, Struga, Macedonia, Sep 22-24, 2016. [RG]
  7. Gerazov B., P. Gjorgi, M. Hristov, and Z. Ivanovski, “Towards speech emotion recognition in Macedonian,” ETAI, Ohrid, Macedonia, Sep 24–26, 2015. [RG]
  8. Gjoreski A., B. Gerazov, and Z. Ivanovski, “Atom-decomposition based analysis for the purpose of emphatic word detection,” ETAI, Ohrid, Macedonia, Sep 24–26, 2015. [RG]
  9. Stojkovic A., B. Gerazov, and Z. Ivanovski, “Emphatic Word Detection Based on Relative Phoneme Energies within Syllables,” ETAI, Ohrid, Macedonia, Sep 24-26, 2015. [RG]
  10. Melov A., B. Gerazov, and Z. Ivanovski, “Emphatic word detection based on syllable durations,” ETAI, Ohrid, Macedonia, Sep 24 – 26, 2015. [RG]
  11. Gerazov B., Z. Ivanovski, “A Speaker Independent Small Vocabulary Automatic Speech Recognition System in Macedonian”, TAKTONS 2013, Novi Sad, Serbia, Nov 13 – 16, 2013. [RG]
  12. Gerazov B., I. Kostadinovski, Z. Ivanovski, “Forensic Firearm Identification based on Gunshot Recordings”, ETAI 2013, Ohrid, Macedonia, Sep 26 – 28, 2013. [RG]
  13. Naskovska L., M. Ristova, B. Gerazov, V. Pop-Dimitrioska, T. Markovski, “Linguistic-Acoustic Analysis for Speaker Dialect Identification,” ETAI 2013, Ohrid, Macedonia, Sep 26 – 28, 2013. [RG]
  14. Gerazov B., Z. Ivanovski, “The Influence of the Number of States in Whole Word HMMs on ASR Performance”, Annual Journal of Electronics, Vol. 6, No. 1, ISSN 1314-0078, pp. 144-147, Sofia, 2012. [RG]
  15. Gerazov B., V. Pop-Dimitrijoska, Z. Ivanovski, and G. Apostolovska, “Use of Gaussian Mixture Models in Macedonian Forensic Speaker Identification”, 20th Telecommunications Forum TELFOR 2012, Belgrade, Serbia, Nov 20–22, 2012. [RG]
  16. Gerazov B., Z. Ivanovski, “Noise Robustness of Traditional Features for Macedonian Voice Dialing ASR”, ICT Innovations 2012 (Editors S. Markovski and M. Gusev), Web proceedings, ISSN 1857-7288, pp.605-612, Ohrid, Macedonia, Sep 12 – 15, 2012. [RG]
  17. Gerazov B., Z. Ivanovski, “Overview of Feature Selection for Automatic Speech Recognition”, AES 132th Convention, Budapest, Hungary, Apr 26 – 29, 2012. [RG]
  18. Gerazov B., Z. Ivanovski, “Prototype Automatic Speech Recognition System for a Voice Dialing Application for Macedonian”, Summer Symposium on Electronics and Signal Processing LEOS 2012, Mavrovo, Macedonia, Sep 14 – 15, 2012. (in Macedonian) [RG]
  19. Pop-Dimitrijoska V., G. Apostolovska, B. Gerazov, Z. Ivanovski and J. Jovanovski, “Forensic Speaker Identification Through Comparative Analysis of the Formant Frequencies of the Vowels in the Macedonian Language”, in Physica Macedonica, 2012, Vol. 61, pp. 79-84. ISSN 1409‐7168 [RG]
  20. Gerazov B., Z. Ivanovski, “Development of an Automatic Speech Recognition System for Macedonian for Vocal Control of Devices“, XL Scientific Conference, Ohrid, Macedonia, Jun 29 – 30 2013. (in Macedonian)

Signal Processing

  1. Gerazov B., D. van Niekerk, A. Xu, P.K. Krug, P. Birkholz, and Y. Xu, “Evaluating Features and Metrics for High-Quality Simulation of Early Vocal Learning of Vowels,” submitted to Interspeech 2021, in ArXiv e-prints, 2 Apr 2021. https://arxiv.org/abs/2005.09986

  2. Van Niekerk D.R., A. Xu, B. Gerazov, P.K. Krug, P. Birkholz, Y. Xu, “Finding intelligible consonant-vowel sounds using high-quality articulatory synthesis,” in INTERSPEECH, Shanghai, China, 25 – 29 Oct 2020. pdf

  3. Honnet P.-E., B. Gerazov, A. Gjoreski, and P. Garner, “Intonation modelling using a muscle model and perceptually weighted matching pursuit,” in Speech Communication, Elsevier, vol. 97, pp. 81-93, March 2018. [pdf] [RG]

  4. Gerazov B., A. Gjoreski, A. Melov, P.-E. Honnet, Z. Ivanovski and P. Garner, “Unified Prosody Model based on Atom Decomposition for Emphasis Detection,” ETAI, Struga, Macedonia, Sep 22-24, 2016. [RG]
  5. Gerazov B. and P. N. Garner, “An agonist-antagonist pitch production model,” International Conference on Speech and Computer SPECOM, Budapest, Hungary, 23-27 Aug, 2016. [RG]
  6. Delic T., B. Gerazov, B. Popovic, and M. Secujski, “A Linguistic Interpretation of the Atom Decomposition of Fundamental Frequency Contour for American English,” International Conference on Speech and Computer SPECOM, Budapest, Hungary, 23-27 Aug, 2016. [RG]
  7. Gerazov B. and Z. Ivanovski, “Kernel power flow orientation coefficients for noise-robust speech recognition,” IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), vol. 23, no. 2, pp. 407-419, 2015. [RG]
  8. Gerazov B. and P. Garner, “An investigation of muscle models for physiologically based intonation modelling,” TELFOR 2015, Belgrade, Serbia, Nov 24–25, 2015. [RG]

  9. Gerazov B., P.-E. Honnet, A. Gjoreski, and P. N. Garner, “Weighted correlation based atom decomposition intonation modelling,” in Proceedings of Interspeech, Dresden, Germany, Sep 6 – 10, pp. 1601-1605, 2015. [RG]

  10. Honnet P.-E., B. Gerazov, and P. N. Garner, “Atom decomposition-based intonation modelling,” in Proceedings of the IEEE ICASSP, Brisbane, Australia, Apr 19 – 24, 2015. [RG]

  11. Gerazov B. and S. Markovska-Simoska, “EEGpy: A system for the analysis of coherence in EEG data used in the assessment of ADHD,” ETAI, Struga, Macedonia, Sep 22-24, 2016. [RG]
  12. Gerazov B., A. Gjoreski, and Z. Ivanovski , “Implementation of optimized matching pursuit techniques in WCAD intonation modelling,” 3rd International Acoustics and Audio Engineering Conference TAKTONS, Novi Sad, Serbia, Nov 18-21 2015. [RG]
  13. Gjoreski A., B. Gerazov, and Z. Ivanovski , “Joint Atom-Decomposition Based Analysis of Energy and Intonation for Emphatic Word Detection,” 3rd International Acoustics and Audio Engineering Conference TAKTONS, Novi Sad, Serbia, Nov 18-21 2015. [RG]
  14. Melov A., B. Gerazov, and Z. Ivanovski , “Towards Extracting the Global Component from the Syllable Duration Contour for Emphatic Word Detection,” 3rd International Acoustics and Audio Engineering Conference TAKTONS, Novi Sad, Serbia, Nov 18-21 2015. [RG]
  15. Gerazov B. and Z. Ivanovski, “Gaussian power flow orientation coefficients for noise-robust speech recognition,” EUSIPCO, Lisbon, Portugal, Sep 1 – 5, 2014. [RG]
  16. Gerazov B., Z. Ivanovski, “Influence of the Filter Bank on Automatic Speech Recognition System Performance in Noise”, ETAI 2013, Ohrid, Macedonia, Sep 26 – 28, 2013. [RG]
  17. Hadzieva E., Gerazov B., “Fractal Analysis of Macedonian Folk Instruments”, ETAI 2013, Ohrid, Macedonia, Sep 26 – 28, 2013. [RG]
  18. Gerazov B., Z. Ivanovski, “Evaluation of Noise Robust ASR Features on a Subset of TIDigits Database”, Conference on Acoustics AIA-DAGA 2013, Merano, Italy, 18-21 Mar 2013. [RG]
  19. Gerazov B., Z. Kokolanski, G. Arsov, V. Dimcev, “Tracking of Electrical Network Frequency for the Purpose of Forensic Audio Authentication”, 13th International Conference on Optimization of Electrical and Electronic Equipment OPTIM 2012, Brasov, Romania, May 24-26, 2012. [RG]
  20. Gerazov B., Z. Ivanovski, “Analysis of Extracted Pitch Contours Across Speakers for Intonation Modelling in TTS Synthesis”, 5th International Symposium on Communications, Control, and Signal Processing ISCCSP 2012, Rome, Italy, May 2-4, 2012. [RG]
  21. Gerazov B., V. Labroska, Z. Ivanovski, “Modeling of Macedonian intonation structure at the level of intonation phrases”, SLAVIFON 2012, Ljubljana, Slovenia, Feb 16 – 17, 2012. (in Macedonian) [RG]
  22. Gerazov B., V. Labroska, Z. Ivanovski, “Modeling of Macedonian intonation structure at the level of intonation phrases”, in Slavistična revija, Miran Hladnik Ed., Slavistično društvo Slovenije, Ljubljana, 2012, vol. 60, Nr. 4, pp. 639 – 658. (in Macedonian) [RG]
  23. Gerazov B., Z. Ivanovski, “Prosody Modification Module for the Speech Synthesis System “Speak Macedonian””, ETAI 2011, Ohrid, Macedonia, Sep 16 – 20, 2011. (in Macedonian) [RG] [RG]
  24. Gerazov B., Z. Ivanovski, “Generation of Pitch Curves for Macedonian Text-to-Speech Synthesis”, 6th Forum Acusticum, Aalborg, Denmark, Jun 26 – Jul 01, 2011. [RG]
  25. Gerazov B., Z. Ivanovski, “Prosody Generation Module for Macedonian Text-to-Speech Synthesis”, AES 130th Convention, London, UK, May 13 – 16, 2011. [RG]
  26. Gerazov B., Z. Ivanovski, “Analysis of Intonation Dynamics in Macedonian for the Purpose of Text to Speech Synthesis”, 18th Telecommunications Forum TELFOR 2010, Belgrade, Serbia, Nov 23 – 25, 2010. [RG]
  27. Gerazov B., Z. Ivanovski, “Analysis of Intonation in the Macedonian Language for the Purpose of Text-to-Speech Synthesis”, EAA EUROREGIO 2010, Ljubljana, Slovenia, Sep 15 – 18, 2010. [RG]
  28. Gerazov B., S. Bogdanova, Z. Ivanovski, “Linear predictive based voice transformation module for Macedonian TTS“, 17th Telecommunications Forum TELFOR 2009, Belgrade, Serbia, Nov 24 – 26, 2009. [RG]
  29. Gerazov B., V. Kafedziski, G. Shutinoski, “A Tool for Teaching Linear Predictive Coding”, ELECTRONICS – ET2008, Sozopol, Bulgaria, Sep 24-26, 2008. [RG]
  30. Gerazov B., G. Shutinoski, G. Arsov, “A Novel Quasi-Diphone Inventory Approach to Text-To-Speech Synthesis“, MELECON, Ajaccio, France, May 2008 [RG]
  31. Gerazov B. and Z. Ivanovski, “Modeling the language of prosody,” Conference on Digital speech and image processing, DOGS 2014, Novi Sad, Serbia, Oct 5 – 9, 2014. [RG]
  32. Gerazov B., R. Velichkovska, I. Gerazova, “Rural Singing Parallels: Comparison of Formant Shift in Macedonian and Bulgarian Rural Singing”, Third Symposium of the ICTM Study Group For Music And Dance In Southeastern Europe, Berovo, Macedonia, Apr 17-22, 2012. [RG]
  33. Gerazov B., Z. Ivanovski, R. Bilibajkić, “Modeling Macedonian Intonation for Text-to-Speech Synthesis”, DOGS 2010, Iriski Venac, Serbia, Dec 16 – 18, 2010. [RG]
  34. Gerazov B., Z. Ivanovski, “Building a Basis for Automatic Melody Extraction from Macedonian Rural Folk Music”, ETRAN, Donji Milanovac, Serbia, 7 – 10 Jun 2010. [RG]
  35. Gerazov B., M. Bogdanov, Z. Ivanovski, “Segmentation of Speech Based on the Undecimated Wavelet Transformation“, ETAI, Ohrid, Macedonia, Sep 26 – 29, 2009. (in Macedonian) [RG]
  36. Gerazov B., G. Shutinovski, “One Approach to Text-to-Speech Synthesis in Macedonian”, ETAI, Ohrid, Macedonia, Sep 19 – 21, 2007. [RG]
  37. Gerazov B., Z. Ivanovski, “Speech Synthesis System in Macedonian Based on Quasi-Diphones”. In Makedonski Jazik LXIII, Institut za makedonski jazik “Krste Misirkov”, Skopje 2012, pp. 234-241. (in Macedonian)
  38. Gerazov B., Z. Ivanovski, “Analysis of Intonation at the Level of Intonation Phrases in the Macedonian Language”, XXXVIII Scientific Conference, XLIV International Seminar for Macedonian Language, Literature and Culture, Ohrid, Macedonia, Jul 14 – 15 2011. (in Macedonian) [RG]

Natural Language Processing

  1. Gerazov B., Z. Ivanovski, “Text Normalization and Phonetic Analysis Modules for Macedonian TTS Synthesis”, 19th Telecommunications Forum TELFOR 2011, Belgrade, Serbia, Nov 22–24, 2011. [RG]
  2. Gerazov B., Z. Ivanovski, “The Construction of a Mixed Unit Inventory for Macedonian Text-to-Speech Synthesis”, International Scientific – Professional Symposium INFOTEH, Jahorina, Bosnia and Herzegovina, Mar 16 – 18, 2011. [RG]
  3. Gerazov B., Z. Ivanovski, “Diphone Analysis of the Macedonian Language for the Purpose of Text-to-Speech Synthesis”, ICEST 2009, Veliko Tarnovo, Bulgaria, Jun 25 – 27, 2009. [RG]

Other Speech Related

  1. Grozdanovska M., V. Mladenovikj, Gj. Smilevski, S. Janev, M. Velinovska-Velkovska, M. Trajchova, B. Gerazov, “Towards a free software-based communication tool for children with disabilities,” 28th Telecommunications forum TELFOR 2020, Serbia, Belgrade, Nov 24 – 25, 2020. RG

  2. Secujski M., B. Gerazov, T. G. Csapo, V. Delic, P. N. Garner, A. Gjoreski, D. Guennec, Z. Ivanovski, A. Melov, G. Nemeth, A. Stojkovic , and G. Szaszak, “Design of a Speech Corpus for Research on Cross-Lingual Prosody Transfer,” International Conference on Speech and Computer SPECOM, Budapest, Hungary, 23-27 Aug, 2016. [RG]

  3. Labroska V. and B. Gerazov, “Analysis of the models of adaptation of the phoneme /v/ in modern spoken Macedonian,” Rocznik slavistyczny, LXVI, Polska akademia nauk, Warszawa 2017, pp. 15-25 . (in Macedonian). [RG]

  4. Gerazov B., Z. Ivanovski, I. Gerazova, “International Norms and Recommendations for Digitalization of Archive Materials”. In Makedonski Folklor XXXVII, No. 70, Skopje 2015, pp. 249-254. (in Macedonian) [RG]

  5. Szaszák G., T.G. Csapó, P.N. Garner, B. Gerazov, Z. Ivanovski, G. Németh, B. Tóth, M. Sečujski, and V. Delić, “The SP2 SCOPES project on speech prosody,” DOGS 2014, Novi Sad, Serbia, Oct 5 – 9, 2014. [RG]

  6. Gerazov B., Z. Ivanovski, “International norms and recommendations for the digitization of archive material”, 1st International Conference of Cultural Heritage, Media and Tourism, - Ohrid, Macedonia 18-19 Jan 2013.

  7. Gerazov B., T. Janevski, Z. Ivanovski, “Web-based Application of the Text-to-Speech Synthesis System “Speak Macedonian””, ICEST 2010, Ohrid, Macedonia, Jun 23 – 26, 2010. [RG]

 Patents

  1. Levi A.R., M. Petkovikj, B. Gerazov, Y. J. M. Serra, R. Offer, R. Mizrahi, I. Simevski, “Method for slowing down a speech in an input media content,” Listen Up Technologies Ltd, European Patent Office EP3327723A1