Journal Articles:

  1. A. L. Dobre, R. Tapu, A.-E. Sultana, and B. Mocanu, “A comprehensive survey of audio-visual speech recognition: Current trends, challenges and future directions,” Neurocomputing, Art. no. 135349, 2026, doi: 10.1016/j.neucom.2026.135349. FI (JCR 2025): 6,7; Q1 (Computer Science, Artificial Intelligence).

  2. B. Mocanu and R. Tapu, “Audio-guided articulatory distillation for multilingual visual speech recognition with large language model decoding,” Multimedia Tools and Applications, vol. 85, Art. no. 694, Aug. 2026, doi: 10.1007/s11042-026-21853-y. IF (JCR 2023): 3,0; Q2.

  3. M. Modrogan, R. Tapu, and B. Mocanu, “AI-Based semantic video indexing: a unified survey from segmentation to retrieval,” Knowledge-Based Systems, vol. 351, Part B, Art. no. 116714, Oct. 2026, doi: 10.1016/j.knosys.2026.116714. IF (JCR 2025): 8,0; Q1 (Computer Science, Artificial Intelligence).

  4. R. Tapu and B. Mocanu, “EARS4SEE: A multimodal audio description system dedicated to blind and visually impaired users,” Computer Vision and Image Understanding, vol. 268, Art. no. 104772, May 2026, doi: 10.1016/j.cviu.2026.104772. IF (JCR 2025): 3,6; Q2 (Computer Science, Artificial Intelligence; Engineering, Electrical & Electronic).

  5. M.-M. Grosu (Marinescu), O. Datcu, R. Tapu, and B. Mocanu, “A Comparative Study of Emotion Recognition Systems: From Classical Approaches to Multimodal Large Language Models,” Applied Sciences, vol. 16, no. 3, Art. no. 1289, Jan. 2026, doi: 10.3390/app16031289. IF (JCR 2025): 2,9; Q2 (Engineering, Multidisciplinary).

  6. R. Tapu, B. Mocanu, and I.-C. Chiva, “Multimodal Visual Speech Recognition for Under-Resource Languages via Cross-Modal Learning and Large Language Models,” Romanian Journal of Information Science and Technology, vol. 29, no. 1, pp. 53–64, 2026, doi: 10.59277/ROMJIST.2026.1.05. IF (JCR 2025): 4,6; Q1 (Computer Science, Theory & Methods).

International Conference Papers:

  1. L. Gruia and R. Tapu, “Readability Improvement with Open-Source LLMs: A Comparative Evaluation on Romanian Language,” in Proc. 2026 16th International Conference on Communications (COMM), Bucharest, Romania, May 2026, pp. 299–303, IEEE, doi: 10.1109/COMM70054.2026.11591289

  2. B. Mocanu and R. Tapu, “Learning Selective Vision-Language Inference for Vehicle Make and Model Recognition,” in Proc. 2026 16th International Conference on Communications (COMM), Bucharest, Romania, May 2026, pp. 368–372, IEEE, doi: 10.1109/COMM70054.2026.11591314

  3. R. Tapu and B. Mocanu, “Decoupling Articulation from Language: Phonetic Interfaces for Romanian Visual Speech Recognition,” in Proc. 2026 16th International Conference on Communications (COMM), Bucharest, Romania, May 2026, pp. 304–308, IEEE, doi: 10.1109/COMM70054.2026.11591421

  4. O. Constantin, R. Tapu, B. Mocanu, and M. Grosu, “Food Image Recognition: From CNNs to Transformers and Multimodal Learning,” in Advances in Digital Health and Medical Bioengineering II, vol. 3, IFMBE Proceedings, Springer, 2026, pp. 290–297, doi: 10.1007/978-3-032-23952-5_32

  5. Minulescu, D.-E., & Toma, Ș.-A. (2025). Whisper Based Speech Recognition for Emergency Services. In 2025 17th International Conference on Electronics, Computers and Artificial Intelligence (ECAI) (pp. 1–6). https://doi.org/10.1109/ecai65401.2025.11095458

  6. V. Dragoș-Mitruț, Ș. Ștefănescu, and Ș.-A. Toma, “Transcription and Identification of Compound and Special Numeral Entities Using Artificial Intelligence and Rule-Based Methods,” in Proc. 2025 13th International Conference on Speech Technology and Human-Computer Dialogue (SpeD), Cluj-Napoca, Romania, Oct. 2025, pp. 40–45, IEEE, doi: 10.1109/SpeD67700.2025.11252470.

  7. B. Ionescu, H. Müller, D.-C. Stanciu, A. Radzhabov, A. García Seco de Herrera, A.-G. Andrei, et al., “ImageCLEF 2026: Multimodal Challenges in Medicine, Science, Agritech, and Security,” in Advances in Information Retrieval – 48th European Conference on Information Retrieval (ECIR 2026), Part IV, Lecture Notes in Computer Science, vol. 16486, Springer, 2026, pp. 336–344, doi: 10.1007/978-3-032-21321-1_44

  8. B. Mocanu and R. Tapu, “A Lightweight Audio-Visual Speaker Detection System for Assistive Video Captioning,” in Proc. 2025 13th European Workshop on Visual Information Processing (EUVIP), Valletta, Malta, Oct. 2025, pp. 1–6, IEEE, doi: 10.1109/EUVIP66349.2025.11238860

  9. B. Mocanu and R. Tapu, “Seeing Through Words: A Zero-Shot Multimodal Audio Description System with Foundation Models,” in Advances in Visual Computing – 20th International Symposium (ISVC 2025), Lecture Notes in Computer Science, vol. 16397, Springer, 2026, pp. 85–97, doi: 10.1007/978-3-032-14495-9_7

  10. M. Grosu, B. Mocanu, R. Tapu, and O. Datcu, “Evaluating Speech Emotion Recognition Systems: From Traditional Low-Level Features to Transformer-Based Models,” in Advances in Digital Health and Medical Bioengineering II (EHB 2025), IFMBE Proceedings, vol. 143, Springer, 2026, pp. 81–88, doi: 10.1007/978-3-032-24045-3_9

  11. R. Tapu and B. Mocanu, “Lip Reading Across Languages: A Cross-Modal Framework Leveraging Foundation Models,” in Proc. 2025 International Conference on Content-Based Multimedia Indexing (CBMI), Dublin, Ireland, Oct. 2025, pp. 1–7, IEEE, doi: 10.1109/CBMI66578.2025.11339323

  12. R. Tapu and B. Mocanu, “Automatic Audio Description: A Training-Free Approach Using Foundation Models,” in Computer Analysis of Images and Patterns (CAIP 2025), Lecture Notes in Computer Science, vol. 15622, Springer, 2026, pp. 173–183, doi: 10.1007/978-3-032-05060-1_15.

  13. B. Mocanu and R. Tapu, “Teacher-Student Visual Speech Recognition with Reliability-Aware Fusion and Uncertainty-Aware LLM Adaptation”, 22nd International Conference on Advanced Visual and Signal-Based Systems, 31 Aug - 3 Sept. 2026, Lecce, Italy.

Patent Application:

  1. R. Tapu and B. Mocanu, “Sistem distribuit pentru recunoașterea vorbirii vizuale prin analiza fluxului video orofacial,” cerere de brevet de invenție nr. A/00034, OSIM, România, depusă la 30 ianuarie 2026.