BZBagashar Zhumazhanov

Bagashar Zhumazhanov

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Bagashar Zhumazhanov has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Comparing Multi-Scale and Pipeline Models for Speaker Change Detection

    by Alymzhan Toleu, Gulmira Tolegen, Bagashar Zhumazhanov

    Speaker change detection (SCD) in long, multi-party meetings is essential for diarization, Automatic speech recognition (ASR), and summarization, and is now often performed in the space of pre-trained speech embeddings. However, unsupervised approaches remain dominant when timely labeled audio is scarce, and their behavior under a unified modeling setup is still not well understood. In this paper, we systematically compare two representative unsupervised approaches on the multi-talker audio meeting corpus: (i) a clustering-based pipeline that segments and clusters embeddings/features and scores boundaries via cluster changes and jump magnitude, and (ii) a multi-scale jump-based detector that measures embedding discontinuities at several window lengths and fuses them via temporal clustering and voting. Using a shared front-end and protocol, we vary the underlying features (ECAPA, WavLM, wav2vec 2.0, MFCC, and log-Mel) and test the model’s robustness under additive noise. The results show that embedding choice is crucial and that the two methods offer complementary trade-offs: the pipeline yields low false alarm rates but higher misses, while the multi-scale detector achieves relatively high recall at the cost of many false alarms.

  • Open Access

    Comparing Multi-Scale and Pipeline Models for Speaker Changes

    by Alymzhan Toleu, Gulmira Tolegen, Bagashar Zhumazhanov

    Speaker change detection (SCD) in long, multi-party meetings is essential for diarization, ASR, and summarization, and is now often performed in the space of pre-trained speech embeddings. However, unsupervised back-ends remain dominant when timely labeled audio is scarce, and their behavior under a unified modeling setup is still not well understood. In this paper, we systematically compare two representative unsupervised approaches on the multi-talker audio meeting corpus: (i) a clustering-based single-scale pipeline that segments and clusters embeddings/features and scores boundaries via cluster changes and jump magnitude, and (ii) a multi-scale jump-based detector that measures embedding discontinuities at several window lengths and fuses them by temporal clustering and voting. Using a shared front-end and protocol, we vary the underlying features (ECAPA, WavLM, wav2vec 2.0, MFCC, log-Mel) and test robustness under additive noise. Results show that embedding choice is crucial and that the two methods offer complementary trade-offs: the pipeline yields low false alarm rates but higher misses, while the multi-scale detector achieves relatively high recall at the cost of many false alarms.

  • Open Access

    End-to-End Multi-Modal Speaker Change Detection with Pre-Trained Models

    by Alymzhan Toleu, Gulmira Tolegen, Alexandr Pak, Jaxylykova Assel, Bagashar Zhumazhanov

    In this work, we propose a multi-modal speaker change detection (SCD) approach with focal loss, which integrates both audio and text features to enhance detection performance. The proposed approach utilizes pre-trained large-scale models for feature extraction and incorporates a self-attention mechanism to optimize useful features related to speaker change. The extracted features are fused and processed through a fully connected classification network, with layer normalization and dropout for stability and generalization. To address class imbalance, we apply focal loss, which reduces errors for the difficult samples, leading to better balanced performance. Extensive experiments on a multi-talker meeting dataset demonstrate that the proposed multi-modal approach consistently outperforms single-modal models, proving the complementary nature of audio and text for SCD. Fine-tuning pre-trained models (Wav2Vec2 and Bert) for audio and text significantly boosts accuracy, achieving a 21% improvement over frozen models. The self-attention mechanism further improves performance by 2%, highlighting its ability to capture speaker transition cues effectively. Additionally, focal loss enhances the model’s performance, making it more robust to imbalanced data.


  • Open Access

    End-to-End Multi-Modal Speaker Change Detection with Pre-trained Models

    by Alymzhan Toleu, Gulmira Tolegen, Alexandr Pak, Assel Jaxylykova, Bagashar Zhumazhanov

    In this work, we propose a multi-modal Speaker Change Detection (SCD) approach with focal loss that integrates both audio and text features to enhance detection performance. % The proposed approach utilizes pre-trained large-scale models for feature extraction and incorporates a self-attention mechanism to optimize the useful features related to speaker change. % The extracted features are fused and processed through a fully connected classification network, with layer normalization and dropout for stability and generalization. % To address class imbalance, we apply focal loss, which reduces errors for the difficult samples, leading to better balanced performance. Extensive experiments on a multi-talker meeting dataset demonstrate that the proposed multi-modal approach consistently outperforms single-modal models, proving the complementary nature of audio and text for SCD. % Fine-tuning pre-trained models (Wav2Vec2 and Bert) for audio and text significantly boosts accuracy, achieving a 21\% improvement over frozen models. % The self-attention mechanism further improves performance by 2\%, highlighting its ability to capture speaker transition cues effectively. % Additionally, focal loss enhances model's performance, making it more robust to imbalanced data.


  • Open Access

    Comparative Analysis of Audio Features for Unsupervised Speaker Change Detection

    by Alymzhan Toleu, Gulmira Tolegen, Rustam Mussabayev, Alexander Krassovitskiy, Bagashar Zhumazhanov

    This study examines how ten different audio features, including MFCC, mel-spectrogram, chroma, and spectral contrast etc., influence speaker change detection (SCD) performance. The analysis is conducted using two unsupervised methods: Bayesian information criterion with Gaussian mixture model (BIC-GMM), a model-based approach, and Kullback-Leibler divergence with Gaussian Mixture Model (KL-GMM), a metric-based approach. Evaluation involved statistical analysis of feature changes in relation to speaker changes (vice versa), supported by comprehensive experimental validation. Experimental results show MFCC as the most effective feature, demonstrating consistently good performance across both methods. Features such as zero crossing rate, chroma, and spectral contrast also showed notable effectiveness within the BIC-GMM framework, while mel-spectrogram consistently ranked as the least influential feature in both approaches. Further analysis revealed that BIC-GMM exhibits greater stability in managing variations in feature performance, whereas KL-GMM is more sensitive to threshold optimization. Nevertheless, KL-GMM achieved competitive results when paired with specific features, such as MFCC and zero crossing rate. These findings offer valuable insights into the impact of feature selection on unsupervised SCD, providing guidance for the development of more robust and accurate algorithms for practical applications.


  • Open Access

    Comparative Analysis of Audio Features for Unsupervised Speaker Change Detection

    by Alymzhan Toleu, Gulmira Tolegen, Rustam Mussabayev, Alexander Krassovitskiy, Bagashar Zhumazhanov

    This study analyzes how various audio features influence speaker change detection in different unsupervised approaches. Ten different audio features, including MFCC, mel-spectrogram, spectral centroid, and pitch, etc. were chosen for analysis. Two distinct unsupervised methods were selected for comparing the effectiveness of these feature: the Bayesian information criterion with Gaussian mixture model (BIC-GMM), a model-based approach, and the Kullback-Leibler divergence with Gaussian (KL-GMM), a metric-based approach. In order to gain a prior insight into which features have a significant impact on the SCD problem, we calculate statistic for two probabilities: the probability of speaker change given there is a feature change, and vice versa. To experimentally check the prior insights, a set of experiments carried out to analyze the influence of various audio feature for SCD. The results showed that in both methods, MFCC demonstrates a robust performance, and ranks at the top. Zero crossing rate, chroma and spectral contrast gives a higher performance in BIC-GMM. Mel-spectrogram consistently ranks at the bottom, suggesting it has the least impact on performance across both methods.


  • Open Access

    A USAGE OF THE IMPEDANCE METHOD FOR DETECTING CIRCULATORY DISORDERS TO DETERMINE THE DEGREE OF LIMB ISCHEMIA

    by Valerіi Kryvonosov, Oleg Avrunin, Serhii Sander, Volodymyr Pavlov, Liliia Martyniuk, Bagashar Zhumazhanov

    New engineering technologies allow the creation of diagnostic devices for predicting the development of acute tissue ischemia of the extremities and determining the residual time until the removal of the tourniquet, and solving these tasks is particularly relevant during military actions. Acute limb ischemia is a sudden critical decrease in perfusion that threatens the viability of the limb. The incidence of this condition is 1.5 cases per 10 000 people per year. Acute ischemia occurs due to the blockage of blood flow in major arteries (embolism, thrombosis, trauma), leading to the cessation of adequate blood supply to metabolically active tissues of the limb, including the skin, muscles, and nerve endings. To address these issues, the article analyzes the changes in the impedance of biological tissue. The introduction and use of the coefficient of relative electrical conductivity, denoted as k, as a diagnostic criterion parameter, are justified. Experimental studies of changes in the coefficient of relative electrical conductivity k were conducted, confirming that the transition from exponential to linear dependencies of the coefficient establishes the degree of viability of the biological cell (tissue) and the moment of occurrence of reperfusion syndrome. It has been established that a deviation of the value of k by 10–15% from its unit value diagnoses the initial process of blood perfusion impairment and the development of ischemic tissue disease. The rate of change of k serves as a criterion for predicting the progression of the disease and as a corrective factor for therapeutic treatment.

  • Automatic Speech Recognition Improvement for Kazakh Language with Enhanced Language Model

    by Akbayan Bekarystankyzy, Orken Mamyrbayev, Mateus Mendes, Dina Oralbekova, Bagashar Zhumazhanov, Anar Fazylzhanova


  • Open Access

    FINITE ELEMENT MODEL FOR ANALYSIS OF CHARACTERISTICS OF SHROUDED ROTOR BLADE VIBRATIONS

    by Anatoliy Zinkovskii, Kyrylo Savchenko, Yevheniia Onyshchenko, Leonid Polishchuk, Abilkaiyr Nazerke, Bagashar Zhumazhanov

    The paper presents the approaches to FE modelling of blade airfoil, contact between the shrouds and operational damage. The regularities are established concerning the influence of the finite element type, finite element mesh and model of contact interaction on the spectrum of natural frequencies of blade assemblies. The use of the developed computational models is substantiated to determine the forced vibration characteristics of the selected objects of investigation. Based on the performed numerical experiments it was substantiated of finite element model selection for analysis of characteristics of shrouded rotor blade vibrations.


  • Development of CRF and CTC Based End-To-End Kazakh Speech Recognition System

    by Dina Oralbekova, Orken Mamyrbayev, Mohamed Othman, Keylan Alimhan, Bagashar Zhumazhanov, Bulbul Nuranbayeva