PARALLEL IMPLEMENTATION OF VOICE SIGNAL PROCESSING METHODS ON MULTICORE CPU AND GPU
DOI:
https://doi.org/10.26906/SUNZ.2025.4.039Keywords:
voice identification, signal processing, feature extraction, normalisation, MFCC, spectral subtraction and wavelet filtering, CPU, GPU, iGPUAbstract
Relevance. Systems such as voice assistants and speaker identification tools, which operate based on voice signal processing, have become increasingly widespread. The performance of such systems depends on the volume of data and operating conditions. Processing large collections of voice signals or ensuring real-time operation requires high-performance computing. Such performance can be achieved with massively parallel systems, including multiprocessor clusters or discrete GPUs. Object of research is the organisation of parallel computing processes in voice signal processing tasks using the capabilities of modern processor architectures. Purpose of the article is to develop a parallel voice signal processing system with adapted algorithms for a multi-core CPU and an integrated and discrete GPU. Research results. Comparative analysis revealed that for small loads (such as voice assistants and personal applications), CPU usage is sufficient to ensure efficient computation with low latency. However, when processing large datasets and performing streaming analytics, the proposed parallel approach, implemented on both the CPU and GPU, reduces execution time by 25-30% compared to a sequential implementation on the CPU. Conclusions. Research has shown that parallelism on the CPU is suitable for stages of voice signal processing that require a small amount of computation. At the same time, discrete GPUs can be utilised in stages with intensive computational tasks such as MFCC calculation, spectral subtraction, and wavelet filtering.Downloads
References
1. A. Kumar, S. Jain and M. Kumar, "Deep Learning based Fusion for a Multi-Biometric Identification Using LSTM", 2024 1st International Conference on Advanced Computing and Emerging Technologies (ACET), Ghaziabad, India, 2024, pp. 1-6. https://doi.org/10.1109/ACET61898.2024.10730213. DOI: https://doi.org/10.1109/ACET61898.2024.10730213
2. Mykhailichenko I., Ivashchenko H., Barkovska O., Liashenko O., “Application of Deep Neural Network for Real-Time Voice Command Recognition”, IEEE 3rd KhPI Week on Advanced Technology (KhPIWeek), Kharkiv, Ukraine, pp. 1-4. https://doi.org/10.1109/KhPIWeek57572.2022.9916473. DOI: https://doi.org/10.1109/KhPIWeek57572.2022.9916473
3. Бондаренко М. Е., Іващенко Г. С. Використання послідовності методів попередньої обробки в системах голосової ідентифікації. Системи управління, навігації та зв’язку. Полтава: ПНТУ, 2025. Т. 2 (80). С. 90-96. https://doi.org/10.26906/SUNZ.2025.2.090. DOI: https://doi.org/10.26906/SUNZ.2025.2.090
4. B. Gawrych and P. Czarnul, "Performance Assessment of OpenMP Constructs and Benchmarks Using Modern Compilers and Multi-Core CPUs", 2023 18th Conference on Computer Science and Intelligence Systems (FedCSIS), Warsaw, Poland, 2023, pp. 973-978. https://doi.org/10.15439/2023F7822. DOI: https://doi.org/10.15439/2023F7822
5. I. Vasileska, P. Tomšič, L. Kos and L. Bogdanović, "Unveiling Performance Insights and Portability Achievements Between CUDA and SYCL for Particle-in-Cell Codes on Different GPU Architectures", 2024 47th MIPRO ICT and Electronics Convention (MIPRO), Opatija, Croatia, 2024, pp. 1115-1120, DOI: https://doi.org/10.1109/MIPRO60963.2024.10569866. DOI: https://doi.org/10.1109/MIPRO60963.2024.10569866
6. F. Lumpp, H. D. Patel and N. Bombieri, "A Framework for Optimizing CPU-iGPU Communication on Embedded Platforms", 2021 58th ACM/IEEE Design Automation Conference (DAC), San Francisco, CA, USA, 2021, pp. 685-690. https://doi.org/10.1109/DAC18074.2021.9586304. DOI: https://doi.org/10.1109/DAC18074.2021.9586304
7. H. Li, J. K. Ng and T. Abdelzaher, "Enabling Real-time AI Inference on Mobile Devices via GPU-CPU Collaborative Execution", 2022 IEEE 28th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA), Taipei, Taiwan, 2022, pp. 195-204. https://doi.org/10.1109/RTCSA55878.2022.00027. DOI: https://doi.org/10.1109/RTCSA55878.2022.00027
8. R. M. Fazliddinovich and B. U. Abdumurodovich, "Parallel processing capabilities in the process of speech recognition", 2017 International Conference on Information Science and Communications Technologies (ICISCT), Tashkent, Uzbekistan, 2017, pp. 1-3. https://doi.org/10.1109/ICISCT.2017.8188585. DOI: https://doi.org/10.1109/ICISCT.2017.8188585
9. L. Yu, Y. Ukidave and D. Kaeli, "GPU-Accelerated HMM for Speech Recognition", 2014 43rd International Conference on Parallel Processing Workshops, Minneapolis, MN, USA, 2014, pp. 395-402. https://doi.org/10.1109/ICPPW.2014.59. DOI: https://doi.org/10.1109/ICPPW.2014.59
10. S. M. Hussain, B. Saritha, B. S. Reddy, C. Srikar, B. Suchitra and G. Purnachandrarao, "DeepVoice: An End-to-End Speaker Recognition System Leveraging Convolutional and Recurrent Neural Networks for Robust Voice Identification", 2025 International Conference on Electronics, AI and Computing (EAIC), Jalandhar, India, 2025, pp. 1-5. https://doi.org/10.1109/EAIC66483.2025.11101389. DOI: https://doi.org/10.1109/EAIC66483.2025.11101389
11. M. Dyvak and O. Kindzerskyi, "Implementation of Parallel Computation for Identification of Interval Models based on Multi-core Parallelism and CUDA Technology", 2024 14th International Conference on Advanced Computer Information Technologies (ACIT), Ceske Budejovice, Czech Republic, 2024, pp. 72-76. https://doi.org/10.1109/ACIT62333.2024.10712545. DOI: https://doi.org/10.1109/ACIT62333.2024.10712545
12. R. Kouatly and T. A. Khan, "Performance of Text-Independent Automatic Speaker Recognition on a Multicore System", in Tsinghua Science and Technology, vol. 29, no. 2, pp. 447-456, April 2024. https://doi.org/10.26599/TST.2023.9010018. DOI: https://doi.org/10.26599/TST.2023.9010018
13. P. Foster, S. Sigtia, S. Krstulovic, J. Barker, M. D. Plumbley. "CHiME-Home: A Dataset for Sound Source Recognition in a Domestic Environment", in Proceedings of the 11th Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2015, pp. 1-5. https://doi.org/10.1109/WASPAA.2015.7336899. DOI: https://doi.org/10.1109/WASPAA.2015.7336899
14. A. Moondra and P. Chahal, "Voice Feature Extraction Method Analysis for Speaker Recognition with Degraded Human Voice", 2023 5th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), Greater Noida, India, 2023, pp. 385-388. https://doi.org/10.1109/ICAC3N60023.2023.10541716. DOI: https://doi.org/10.1109/ICAC3N60023.2023.10541716
15. Y. A. Wubet and K. -Y. Lian, "Speaker Anonymization for Voice Biometrics Protection Using Voice Conversion and MultiTarget Speaker Voice Fusion", in IEEE Transactions on Information Forensics and Security, vol. 20, pp. 6046-6057, 2025. https://doi.org/10.1109/TIFS.2025.3577023. DOI: https://doi.org/10.1109/TIFS.2025.3577023
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Maksym Bondarenko, Heorhii Ivashchenko
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
