Speech and Multimodal Interfaces Laboratory

All employees

Axyonov Alexander Alexandrovich

Position

Senior researcher

Qualification

PhD

Contacts

a.aksenov95@mail.ru +7-(812)-328-04-21 +7-(812)-328-70-81

Publications

2025

Ryumina Elena, Ryumin Dmitry, Axyonov Alexandr, Ivanko Denis, Karpov Alexey. Multi-Corpus Emotion Recognition Method based on Cross-Modal Gated Attention Fusion // Pattern Recognition Letters. 2025. vol. 190. pp. 192–200.

Ryumina Elena, Axyonov Alexandr, Abdulkadirov Timur, Koryakovskaya Darya, Ryumin Dmitry. Cross-Lingual Bimodal Emotion Recognition with LLM-Based Label Smoothing // Big Data and Cognitive Computing. 2025. vol. 9, 285.

Axyonov A.A., Ryumina E.V., Ryumin D.A. A method for generating digital avatar animation with speech and non-verbal synchronization based on bimodal data // Scientific and Technical Journal of Information Technologies, Mechanics and Optics. 2025. Vol. 25, No. 4. pp. 651–662.

Axyonov Alexandr, Dolgushin Mikhail, Ryumin Dmitry. NeRF-LipSync: A Diffusion Model for Speech-Driven and View-Consistent Lip Synchronization in Digital Avatars // The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences / Proc. 6th International Workshop PSBB 2025. Moscow, 2025. vol. XLVIII-2/W9-2025. pp. 25–31.

Ryumina Elena, Markitantov Maxim, Axyonov Alexandr, Ryumin Dmitry, Dolgushin Mikhail, Karpov Alexey. Zero-Shot Multimodal Compound Expression Recognition Approach using Off-the-Shelf Large Visual-Language Models // Proc. IEEE/CVF International Conference on Computer Vision (ICCV 2025) Workshops, 9th ABAW Workshop, USA, 2025. pp. 71–79.

Axyonov A.A. Multimodal Generation of Speech, Facial Expressions, and Gestures in Digital Avatars: Current Methods and Future Prospects // Proceedings of Voronezh State University. Series: Systems Analysis and Information Technologies. 2025. No. 4. pp. 155–182.

2024

Ryumin D., Axyonov A., Ryumina E., Ivanko D., Kashevnik A., Karpov A. Audio–visual speech recognition based on regulated transformer and spatio–temporal fusion strategy for driver assistive systems // Expert Systems with Applications. 2024. vol. 252. ID 124159.