?
Audio-Visual Speech Recognition In-The-Wild: Multi-Angle Vehicle Cabin Corpus and Attention-Based Method
P. 8195–8199.
Audio-visual speech recognition (AVSR) gains increasing attention as an important part of human-machine interaction. However, the publicly available corpora are limited, particularly in driving conditions with prevalent background noise. Research so far has been collected in constrained environments, and thus cannot reflect the true performance of AVSR systems in real-world scenarios. Moreover, data for languages other than English is often unavailable. To meet the request for research on AVSR in unconstrained driving conditions, this paper presents a corpus collected ‘in-the-wild’. We propose a cross-modal attention method enhancing multi-angle AVSR for vehicles, leveraging visual context to improve accuracy and noise robustness. Our proposed model achieves state-of-the-art (SOTA) results with 98.65% accuracy in recognizing driver voice commands. For more details, visit our project page.
Springer, 2026.
This book 16934 - 16935 constitutes the refereed proceedings of the 28th International Conference on Speech and Computer SPECOM 2026 held in Ohrid, North Macedonia,, during September 17–18, 2026.
The total of 65 papers included in the proceedings was carefully reviewed and selected from 99 submissions. They were organized in topical sections as follows:
Part 1 : ...
Added: September 20, 2026
Springer, 2026.
This two-volume set LNAI16934 - 16935 constitutes the refereed proceedings of the 28th International Conference on Speech and Computer SPECOM 2026, held in Ohrid, North Macedonia, during September 17–18, 2026.
The 65 full papers included in these volumes were carefully reviewed and selected from 99 submissions. They were organized in topical sections as follows:
Part I: Automatic ...
Added: September 20, 2026
Seralan V., S L. L., Kunchala S. B. et al., European Physical Journal: Special Topics 2025 Vol. 234 P. 1073–1091
In this work, a network of Morris–Lecar neurons with electromagnetic induction is imposed with nonlinear magnetic flux diffusion. We study wave propagation in a network of Morris–Lecar (ML) neurons with magnetic flux diffusion, connected to the local nodes of the nearest neighbors in a 100x100 lattice of neurons with periodic boundary conditions. First, we explore ...
Added: October 15, 2025
Dogonasheva O., Doelling K., Zakharov D. et al., Nature Computational Science 2025 Vol. 5 P. 915–926
Unraveling how humans understand speech despite distortions has long intrigued researchers. A prominent hypothesis highlights the role of multiple endogenous brain rhythms in forming the computational context to predict speech structure and content. Yet, how neural processes may implement rhythm-based context formation remains unclear. Here, we propose the Brain-Rhythm-Based Inference model (BRyBI) as a possible neural implementation of speech processing ...
Added: September 2, 2025
International Society for Computers and Their Applications (ISCA), 2024.
Added: March 6, 2025
IEEE, 2024.
Added: March 6, 2025
Elena Ryumina, Markitantov M., Dmitry Ryumin et al., Expert Systems with Applications 2024 Vol. 239 P. 0
Psychological and neurological studies earlier suggested that a personality type can be determined by the whole face as well as by its sides. This article discusses novel research using deep neural networks that address the features of both sides of the face (hemifaces) to assess the human’s Big Five personality traits (PT). For this, we have developed a real time approach called EmoFormer ...
Added: March 6, 2025
Dmitry Ryumin, Alexandr Axyonov, Elena Ryumina et al., Expert Systems with Applications 2024 Vol. 252 Article 124159
This article presents a research methodology for audio–visual speech recognition (AVSR) in driver assistive systems. These systems necessitate ongoing interaction with drivers while driving through voice control for safety reasons. The article introduces a novel audio–visual speech command recognition transformer (AVCRFormer) specifically designed for robust AVSR. We propose (i) a multimodal fusion strategy based on ...
Added: March 6, 2025
An P. P., V. V. Kovalyuk, Y. G. Gladush et al., Applied Physics Letters 2024 Vol. 125 No. 20 Article 201101
The rapid development of photonic integrated circuits (PICs) and their applications in various fields of science and technology requires the creation of easy-to-manufacture high-speed integrated detectors. In this work, we fabricated and studied planar waveguide-integrated bolometers based on a thin film of single-walled carbon nanotubes (SWCNTs) on the silicon nitride platform. This bolometer showed good ...
Added: November 11, 2024
Turin: Institute of Electrical and Electronics Engineers, 2024.
AICT2024 will offer oral, keynote speeches, tutorials and professional meetings. Submitted papers are expected to cover state-of-the-art technologies, theoretical concepts, standards, products implementation, ongoing research projects as well as applications of ICT. The previous AICT joined hundreds of participants from several countries including Australia, Azerbaijan, Brasilia, China, Finland, Georgia, Germany, India, Iran, Italy, Japan, Kazakhstan, ...
Added: November 7, 2024
Shirnin A., Andreev N., Potapova S. et al., IEEE/ACM Transactions on Speech and Language Processing 2024 Vol. 32 P. 2751–2763
We present an approach to evaluate the robustness of pre-trained vision and language (V&L) models to noise in input data. Given a source image/text, we perturb it using standard computer vision (CV) / natural language processing (NLP) techniques and feed it to a V&L model. To track performance changes, we explore the problem of visual ...
Added: July 19, 2024
IEEE, 2023.
The IEEE Russia North West Section and Saint Petersburg Electrotechnical University “LETI” (ETU “LETI”) are pleased to present the Proceedings of the Seminar on Signal Processing. The Seminar took place on November 22, 2023 in Saint Petersburg Electrotechnical University “LETI”.
The event provided ample opportunities to present new scientific results, exchange experience and establish professional contacts to researchers in the ...
Added: February 10, 2024
Cham: Springer, 2023.
Added: November 29, 2023
IEEE, 2023.
Added: November 5, 2023
International Speech Communication Association, 2023.
Added: November 5, 2023
Baku: IEEE, 2023.
The AICT2023 is co-organized by ADA University, George Washington University, Politecnico di Torino and IEEE Azerbaijan Joint Chapter and technically sponsored by the Institute of Electrical and Electronics Engineers (IEEE). The AICT2023 will offer keynotes, tutorials and research presentations. Submitted papers are expected to cover state-of-the-art technologies, theoretical concepts, standards, products implementation, ongoing research projects ...
Added: November 4, 2023
Washington: IEEE, 2022.
2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT) Copyright © 2022 by the Institute of Electrical and Electronics Engineers, Inc.
All rights reserved.
Copyright and Reprint Permission Abstracting is permitted with credit to the source.
Libraries are permitted to photocopy beyond the limit of U.S. copyright law, for private use of patrons, ...
Added: October 29, 2022
Makarov I., Bakhanova M., Nikolenko S. et al., PeerJ Computer Science 2022 Vol. 8 Article e865
Depth estimation has been an essential task for many computer vision applications, especially in autonomous driving, where safety is paramount. Depth can be estimated not only with traditional supervised learning but also via a self-supervised approach that relies on camera motion and does not require ground truth depth maps. Recently, major improvements have been introduced ...
Added: February 1, 2022