Speech translation systems have become indispensable in facilitating seamless communication across language barriers. This paper presents a cascade speech translation system tailored specifically for translating speech from the Kazakh language to Russian. The system aims to enable effective cross-lingual communication between Kazakh and Russian speakers, addressing the unique challenges posed by these languages. To develop the cascade speech translation system, we first created a dedicated speech translation dataset ST-kk-ru based on the ISSAI Corpus. The ST-kk-ru dataset comprises a large collection of Kazakh speech recordings along with their corresponding Russian translations. The automatic speech recognition (ASR) module of the system utilizes deep learning techniques to convert spoken Kazakh input into text. The machine translation (MT) module employs state-of-the-art neural machine translation methods, leveraging the parallel Kazakh-Russian translations available in the dataset to generate accurate translations. By conducting extensive experiments and evaluations, we have thoroughly assessed the performance of the cascade speech translation system on the ST-kk-ru dataset. The outcomes of our evaluation highlight the effectiveness of incorporating additional datasets for both the ASR and MT modules. This augmentation leads to a significant improvement in the performance of the cascade speech translation system, increasing the BLEU score by approximately 2 points when translating from Kazakh to Russian. These findings underscore the importance of leveraging supplementary data to enhance the capabilities of speech translation systems.
This paper presents a systematic framework that combines federated learning, self-supervised learning, and few-shot learning paradigms for privacy-preserving face recognition. We use the large-scale CASIA-WebFace dataset for self-supervised pre-training using SimCLR in a federated setting, followed by federated few-shot fine-tuning on the LFW dataset using prototypical networks. Through comprehensive evaluation across six state-of-the-art architectures (ResNet, DenseNet, MobileViT, ViT-Small, CvT, and CoAtNet), we demonstrate that while our federated approach successfully preserves data privacy, it comes with significant performance trade-offs. Our results show 12–30% accuracy degradation compared to centralized methods, representing the substantial cost of privacy preservation. We find that traditional CNNs show superior robustness to federated constraints compared to transformer-based architectures, and that five-shot configurations provide an optimal balance between data efficiency and performance. This work provides important empirical insights and establishes benchmarks for federated few-shot face recognition, quantifying the privacy–utility trade-offs that practitioners must consider when deploying such systems in real-world applications.
25 December 2024 in Eastern-European Journal of Enterprise Technologies
This research addresses the critical challenge of recognizing mutual actions involving multiple individuals, an important task for applications such as video surveillance, human-computer interaction, autonomous systems, and behavioral analysis. Identifying these actions from 3D skeleton motion sequences poses significant challenges due to the necessity of accurately capturing intricate spatial and temporal patterns in diverse, dynamic, and often unpredictable environments. To tackle this, a robust neural network framework was developed that combines Convolutional Neural Networks (CNNs) for efficient spatial feature extraction with Long Short-Term Memory (LSTM) networks to model temporal dependencies over extended sequences. A distinguishing feature of this study is the creation of a hybrid dataset that which combines real-world skeleton motion data with synthetically generated samples, produced using Generative Adversarial Networks (GANs). This dataset enriches variability, enhances generalization, and mitigates data scarcity challenges. Experimental findings across three different network architectures demonstrate that our method significantly enhances recognition accuracy, mainly due to the integration of CNNs and LSTMs alongside the broadened dataset. Our approach successfully identifies complex interactions and ensures consistent performance across different perspectives and environmental conditions. The improved reliability in recognition indicates that this framework can be effectively utilized in practical applications such as security systems, crowd monitoring, and other areas where precise detection of mutual actions is critical, particularly in real-time and dynamic environments
23 March 2025 in Herald of the Kazakh-British technical university
The technology of intelligent detection of military vehicle objects has already become the foundation for tasks related to intelligence and tracking of weapons and equipment, which is essential for situational awareness in modern intelligent warfare. Over the past two decades, numerous datasets of military vehicle images have been collected, primarily focusing on the classification of various categories of military vehicles. However, almost all these datasets are not publicly available, and the publicly available ones suffer from annotation quality issues. To address the lack of datasets and the quality of existing public datasets, we propose a specialized dataset based on our own collection of images, as well as publicly available ones. To develop methods for automatic detection of various categories of military vehicles and distinguishing them from civilian vehicles, we created a new dataset for military vehicle detection and classification (DMVDC). It consists of 5,899 images of military vehicles collected using three different methods: automated scraping, manual selection of image search results, and data augmentation techniques. To the best of our knowledge, our DMVDC [1] dataset is the only publicly available dataset of military vehicles that consider hidden and partially visible objects. This dataset will contribute to the development of computer vision models for detecting military vehicles.