SerbNumAO 1.0: Design, Development, and Applications of a Serbian Speech Database of Numbers and Arithmetic Operators

11th International Scientific Conference Technics, Informatics and Education – TIE 2026, (pp. 210-215)

АУТОР(И) / AUTHOR(S): Branko Marković , Đorđe Damnjanović , Milan Vesković  and Dimitrije Rozgić

  

Download Full Pdf  

DOI: https://doi.org/10.46793/TIE26.210M

САЖЕТАК /ABSTRACT:

This paper presents the design and development of a Serbian speech database, primarily consisting of spoken numbers and arithmetic operators. The vocabulary comprises 54 Serbian words. The database includes recordings from 50 speakers, each of whom uttered the complete vocabulary twice using a normal speaking style. The primary objective of this database is to support human–machine communication applications. To verify its applicability for speech recognition tasks, a subset of the SerbNumAO 1.0 database was used in an automatic speech recognition experiment. Mel-Frequency Cepstral Coefficients (MFCCs) were employed as front-end of ASR (Automatic Speech Recognition) system, while a Convolutional Neural Network (CNN) served as the back-end classifier. The proposed method achieved an average Word Recognition Rate (WRR) of up to 95%.

КЉУЧНЕ РЕЧИ / KEYWORDS: 

speech database; Serbian numbers; arithmetic operators; MFCC; CNN

 ПРОЈЕКАТ / ACKNOWLEDGEMENT:

ЛИТЕРАТУРА / REFERENCES:

  • Cole, R. A., Noel, M., Lander, T., & Durham, T. (1995). New Telephone Speech Corpora at CSLU. Proceedings of Eurospeech 1995, Madrid, Spain, pp. 821–824.
  • Martín-Doñas, J. M., López-Espejo, I., González-Lao, C. R., Gallardo-Jiménez, D., Gómez, A. M., Pérez-Córdoba, J. L., Sánchez, V., Morales-Cordovilla, J. A., & Peinado, A. M. (2016). SecuVoice: A Spanish Speech Corpus for Secure Applications with Smartphones. Proceedings of IberSPEECH 2016, Lisbon, Portugal.
  • Zhang, B., Lv, H., Guo, P., Shao, Q., Yang, C., Xie, L., Xu, X., Bu, H., Chen, X., Zeng, C., Wu, D., & Peng, Z. (2021). WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition. arXiv:2110.03370. https://doi.org/10.48550/arXiv.2110.03370
  • Jovicic, S. T., (2004). Serbian emotional speech database: Design, processing and evaluation, in Proc. 9th Conference on Speech and Computer (SPECOM), 77–81.
  • Marković, B., Jovičić, S. T., Galić, J., & Grozdić, Đ. (2013). Whispered speech database: Design, processing and application. In Text, Speech, and Dialogue (LNAI, Vol. 8082, pp. 591–598). Springer.
  • Marković, B., Milićević, V., Petrović, D., Nešković, D., & Marković, G., (2016). Serbian language speech database „Phonemes_1.0‟: Design and application , TIO 2016, May 28-29, Čačak, Serbia, Faculty of Technical Sciences, Proceedings TIO 2016, 6th International Conference, 232-236, (UDK: 004.6:811.163.41’ 342.4). ISBN: 978-86-7776-192-9
  • Jurafsky, D. & Martin, J. H., (2025). Speech and Language Processing, 3rd ed. (draft), Pearson.
  • Rabiner, L. R. & Juang, B.-H., (1993). Fundamentals of Speech Recognition. Prentice Hall.
  • Alsobhani, A., Al Abboodi, H. M. A., & Mahdi, H., (2021), Speech recognition using convolution deep neural networks, Journal of Physics: Conference Series, 1973(1), 0121166.
    DOI: 10.1088/1742-6596/1973/1/012166
  • Vujičić, D., Damnjanović, Đ., Marković, D., & Stamenković, Z. (2025). Deep Learning System for Speech Command Recognition. Electronics, 14(19), 3793. https://doi.org/10.3390/electronics14193793
  • Marković, B. R., Lončarević, V., & Galić, J., (2025). Application of 1D-Convolutional Neural Networks for Whispered Speech Recognition. 33rd Telecommunications Forum (TELFOR). IEEE, pp. 1–4, Nov. 25.
    DOI: 10.1109/telfor67910.2025.11314414.
  • De Veth, J. & Boves, L., (1998). Channel Normalization Techniques for Automatic Speech Recognition over the Telephone. Speech Communication, 25, 149-164.
  • Grozdić, Đ. T., Jovičić, S. T., Šumarac Pavlović, D., Galić, J., & Marković, B., (2017). Comparison of cepstral normalization techniques in whispered speech recognition. Advances in Electrical and Computer Engineering, 17(1), 21-27.
    DOI: 10.4316/AECE.2017.01004.
  • Nasr-Esfahani, A., Bekrani, M., & Rajabi, R., (2024). Robust Persian digit recognition in noisy environments using hybrid CNN-BiGRU model, arXiv:2412.10857.
  • Peter, D., Roth, W., & Pernkopf, F., (2021). End-to-end keyword spotting using neural architecture search and quantization, arXiv:2104.06666.
Post Views: 19