About
My expertise covers machine learning, deep learning, speech processing, natural language processing (NLP), computer vision, and applied AI research. I have hands-on experience developing, training, fine-tuning, and evaluating neural network models using Python, PyTorch, Hugging Face Transformers, and Scikit-learn. My primary research focuses on automated detection and classification of speech sound disorders in Kazakh-speaking children. I have worked with datasets containing more than 5,000 audio recordings and developed classification pipelines using WavLM, CNN, BiLSTM, GCN, and traditional machine learning algorithms. I also have research experience in speech intent recognition, audio anomaly detection, facial recognition, violence detection, and AI-powered educational technologies. My technical strengths include: Machine Learning: SVM, Random Forest, Logistic Regression, ensemble methods, feature engineering, model evaluation. Deep Learning: CNN, RNN, LSTM, BiLSTM, GCN, transfer learning, fine-tuning, attention mechanisms. Speech AI: WavLM, Wav2Vec2, HuBERT, MFCC, Mel-spectrograms, speech classification, audio feature extraction. Computer Vision: Image classification, facial recognition, video analysis, transfer learning. AI Development: Python, PyTorch, Scikit-learn, Hugging Face, NumPy, Pandas, CUDA, GPU-accelerated training. Research: Dataset preparation, experimental design, cross-validation, statistical evaluation, reproducible experiments, scientific writing. I am also involved in a funded research project on AI-powered personalized learning environments and teach Machine Learning and Neural Networks at university level. I am interested in remote research collaborations, AI/ML engineering opportunities, international scientific projects, and the development of practical AI solutions.
