Research Article
BibTex RIS Cite

Türkçe Sesli Komut Sınıflandırması için Melez Spektral ve İstatistiksel Özellik Modellemesi: Çapraz Korelasyon ve Topluluk Öğrenmesi Yaklaşımı

Year 2026, Volume: 30 Issue: 1 , 67 - 82 , 24.04.2026
https://doi.org/10.19113/sdufenbed.1753641
https://izlik.org/JA93NA43GK

Abstract

Öz: Türkçe sesli komutların doğru bir şekilde sınıflandırılması, sesle kontrol edilen teknolojilerin gelişimi ve ana dil bağlamında insan-bilgisayar etkileşiminin sorunsuz bir şekilde gerçekleşmesi açısından kritik öneme sahiptir. Bu çalışmada, konuşma sinyallerinin zamansal, spektral ve zaman-frekans temelli özelliklerini yakalayarak tanıma doğruluğunu artırmayı amaçlayan çeşitli özellik çıkarım modelleri sistematik olarak değerlendirilmiştir. Altı farklı özellik vektörü modeli geliştirilmiş; son modelde ise Bilgi Kazancı tabanlı özellik seçimi ile Doğrusal Öngörümleme Kodlama kullanılarak elde edilen formant frekansları entegre edilerek kapsamlı ve ayrıştırıcı bir temsil elde edilmiştir. Sınıflandırma süreci, yaygın olarak kullanılan altı algoritma ile gerçekleştirilmiştir: Rastgele Orman, k-En Yakın Komşu, Çok Katmanlı Algılayıcı, Lojistik Model Ağacı, Destek Vektör Makineleri ve Rastgele Orman, Çok Katmanlı Algılayıcı ve Lojistik Model Ağacı yöntemlerini birleştiren bir topluluk oylama yöntemi. Topluluk oylama sınıflandırıcısı, %93,94 doğruluk oranı ile en yüksek performansı sergileyerek bireysel sınıflayıcıları ve temel modelleri anlamlı şekilde geride bırakmıştır. Bu çalışma, Türkçe sesli komut tanıma uygulamalarına yönelik sağlam, açıklanabilir ve yüksek performanslı bir özellik çerçevesi sunarak literatüre önemli bir katkı sağlamaktadır. Spektral, zamansal ve artikülatuvar özelliklerin entegrasyonu, sesli komutların daha başarılı bir şekilde ayrıştırılmasını mümkün kılmakta ve Türkçe dilindeki sesli kontrol sistemlerinin gelecekteki uygulamaları için değerli çıkarımlar sunmaktadır.

References

  • [1] Jakob, D. 2022. Voice controlled devices and older adults – a systematic literature review. In Proc. International Conference on Human-Computer Interaction, Cham, Switzerland: Springer International Publishing, 175–200.
  • [2] Saritha, B., Laskar, M. A., Laskar, R. H. 2022. A comprehensive review on speaker recognition. In Advances in Speech and Music Technology: Computational Aspects and Applications, 3–23.
  • [3] Gormez, Y. 2024. Customized deep learning based Turkish automatic speech recognition system supported by language model. PeerJ Computer Science, 10, e1981.
  • [4] Çelik, Y. 2024. Application of deep learning for voice command classification in Turkish language. Bitlis Eren University Journal of Science and Technology, 13(3), 701–708.
  • [5] Kang, O., Pickering, L. 2024. Acoustic and temporal analysis for assessing speaking. In The Concise Companion to Language Assessment, 383.
  • [6] Abdul, Z. K., Al-Talabani, A. K. 2022. Mel frequency cepstral coefficient and its applications: A review. IEEE Access, 10, 122136–122158.
  • [7] Badhe, S. S., Shirbahadurkar, S. D., Gulhane, S. R. 2022. Renyi entropy and deep learning-based approach for accent classification. Multimedia Tools and Applications, 81(1), 1467–1499.
  • [8] Singh, V. K., Sharma, K., Sur, S. N. 2025. Acoustic scene classification using dynamic time warping technique based on short time Fourier transform and discrete wavelet transforms. Circuits, Systems, and Signal Processing, 44(3), 1887–1913.
  • [9] İkizler, N. 1995. Doğrusal Öngörümleme Kodlama ve Yapay Sinir Ağı Yöntemlerinin Ses Tanımada Kullanılması. Karadeniz Teknik Üniversitesi, Fen Bilimleri Enstitüsü Yüksek Lisans Tezi, 83s, Trabzon.
  • [10] Malik, M., Malik, M. K., Mehmood, K., Makhdoom, I. 2021. Automatic speech recognition: a survey. Multimedia Tools and Applications, 80(6), 9411–9457.
  • [11] Debnath, S., Roy, P. 2021. Appearance and shape-based hybrid visual feature extraction: toward audio–visual automatic speech recognition. Signal, Image, and Video Processing, 15(1), 25–32.
  • [12] Vashisht, V., Pandey, A. K., Yadav, S. P. 2021. Speech recognition using machine learning. IEIE Transactions on Smart Processing and Computation, 10(3), 233–239.
  • [13] Madhu, G., Bukka, A. 2023. Ensemble learning model for gender recognition using the human voice. In Proc. 2023 1st International Conference on Advanced Electronics, Electronics, Computer Intelligence (ICAEECI), October 2023, 1–5.
  • [14] Alsobhani, A., ALabboodi, H. M., Mahdi, H. 2021. Speech recognition using convolution deep neural networks. Journal of Physics: Conference Series, 1973(1), 012166, August 2021.
  • [15] Alharbi, S. et al. 2021. Automatic speech recognition: systematic literature review. IEEE Access, 9, 131858–131876.
  • [16] Bakır, H., Çayır, A. N., Navruz, T. S. 2024. A comprehensive experimental study for analyzing the effects of data augmentation techniques on voice classification. Multimedia Tools and Applications, 83(6), 17601–17628.
  • [17] Kurtkaya, M. 2020. Turkish speech command dataset. https://www.kaggle.com/murat-kurtkaya/turkish-speech-command-dataset (Accessed: 15.07.2025).
  • [18] İkizler, N. 2002. Türkçe’de Konuşmacıdan Bağımsız Hece Tanıma Sistemi, Karadeniz Teknik Üniversitesi, Fen Bilimleri Enstitüsü, Doktora Tezi, 143s, Trabzon.
  • [19] İkizler, N., Çavdar, İ. H., Ekim, G. 2005. Türkçe’de konuşmacıdan bağımsız ayrık hece tanıma sistemi. In Proc. IEEE Signal Processing and Communications Applications Conference (SIU), vol. 1, Kayseri, Türkiye, May, 55–59.
  • [20] Ekim, G., İkizler, N., Atasoy, A., Çavdar, İ. H. 2008. A speaker recognition system using cross correlation. In Proc. IEEE 16th Signal Processing and Communications Applications Conference (SIU), Aydın, Türkiye, April, 18–21.
  • [21] Liu, D., Xu, J., Zhang, P., Yan, Y. 2021. A unified system for multilingual speech recognition and language identification. Speech Communication, 127, 17–28.
  • [22] Iqbal, Y., Zhang, T., Gunawan, T. S., Pratondo, A., Zhao, X., Geng, Y., et al. 2025. A hybrid speech enhancement technique based on discrete wavelet transform and spectral subtraction. IEEE Access.
  • [23] Andriyanov, N. 2023. The use of correlation features in the problem of speech recognition. Algorithms, 16(2), 90.
  • [24] Ikizler, N., Ekim, G. 2025. Investigating the effects of Gaussian noise on epileptic seizure detection: The role of spectral flatness, bandwidth, and entropy. Engineering Science and Technology, International Journal, 64, 102005.
  • [25] Mohine, S., Gupta, P., Bansod, B. S., Bhalla, R., Basra, A. 2022. Evaluation of acoustic modality features for moving vehicle identification. Multidimensional Systems and Signal Processing, 33(4), 1349–1365.
  • [26] Nawas, K. K., Barik, M. K., Khan, A. N. 2021. Speaker recognition using random forest. In Proc. ITM Web Conference, vol. 37, 01022.
  • [27] Singh, M. K. 2024. Feature extraction and classification efficiency analysis using machine learning approach for speech signal. Multimedia Tools and Applications, 83(16), 47069–47084.
  • [28] Goh, M., Yann, X. L. 2021. A novel sentiments analysis model using perceptron classifier. International Journal of Electronics Engineering Applications, 9(4), 1–10.
  • [29] Ferrer, L. 2022. Analysis and comparison of classification metrics. arXiv preprint, arXiv:2209.05355.
  • [30] Omuya, E.O., Okeyo, G. O., Kimwele, M. W. 2021. Feature selection for classification using principal component analysis and information gain. Expert Systems with Applications, 174, 114765.
  • [31] Unluturk, A. 2023. Speech Command Based Intelligent Control of Multiple Home Devices for Physically Handicapped. In Proc. 2023 5th Global Power, Energy and Communication Conference (GPECOM), June, 560–564, IEEE.
  • [32] Karakaş, B. 2025. Türkçe Sesli Komut Verilerinin Evrişimsel Sinir Ağı ile Sınıflandırılması. Mühendislik Bilimleri ve Araştırmaları Dergisi, 7(1), 51–59.
  • [33] Uslu, İ. B., Tora, H., Sümer, E., Türker, M. 2020. Yalıtık Sözcüklü bir Türkçe Konuşma Tanıma Sisteminin Yapay Veri Artırımı ile Tasarımı ve Gerçekleştirilimi. Afyon Kocatepe University Journal of Science and Engineering, 20(6), 1147–1155.
  • [34] Işık, G. 2019. Türkçe Ağızların Tanınmasında Derin Öğrenme Tekniğinin Kullanılması. Hacettepe Üniversitesi Fen Bilimleri Enstitüsü, Doktora Tezi, 100s, Ankara.

Hybrid Spectral and Statistical Feature Modelling with Cross-Correlation and Ensemble Learning for Robust Turkish Voice Command Classification

Year 2026, Volume: 30 Issue: 1 , 67 - 82 , 24.04.2026
https://doi.org/10.19113/sdufenbed.1753641
https://izlik.org/JA93NA43GK

Abstract

Accurate classification of Turkish voice commands is essential for advancing voice-controlled technologies and enabling seamless human-computer interaction in native language contexts. This study systematically evaluates multiple feature extraction models capturing temporal, spectral, and time-frequency characteristics of speech signals to enhance recognition accuracy. Six feature vector models were developed, with the final model integrating Information Gain-based feature selection and Linear Predictive Coding-derived formant frequencies to create a comprehensive and discriminative representation. Classification was performed using six widely adopted algorithms: Random Forest, k-Nearest Neighbors, Multilayer Perceptron, Logistic Model Tree, Support Vector Machine, and an Ensemble voting method combining Random Forest, Multilayer Perceptron, and Logistic Model Tree. The Ensemble voting classifier demonstrated superior performance, achieving an accuracy of 93.94%, significantly outperforming individual classifiers and baseline models. This study contributes to the literature by presenting a robust, explainable, and high-performing feature framework tailored for Turkish voice command recognition. The integration of spectral, temporal, and articulatory features enables improved discrimination of speech commands, offering valuable insights for future voice-activated applications in Turkish language environments.

References

  • [1] Jakob, D. 2022. Voice controlled devices and older adults – a systematic literature review. In Proc. International Conference on Human-Computer Interaction, Cham, Switzerland: Springer International Publishing, 175–200.
  • [2] Saritha, B., Laskar, M. A., Laskar, R. H. 2022. A comprehensive review on speaker recognition. In Advances in Speech and Music Technology: Computational Aspects and Applications, 3–23.
  • [3] Gormez, Y. 2024. Customized deep learning based Turkish automatic speech recognition system supported by language model. PeerJ Computer Science, 10, e1981.
  • [4] Çelik, Y. 2024. Application of deep learning for voice command classification in Turkish language. Bitlis Eren University Journal of Science and Technology, 13(3), 701–708.
  • [5] Kang, O., Pickering, L. 2024. Acoustic and temporal analysis for assessing speaking. In The Concise Companion to Language Assessment, 383.
  • [6] Abdul, Z. K., Al-Talabani, A. K. 2022. Mel frequency cepstral coefficient and its applications: A review. IEEE Access, 10, 122136–122158.
  • [7] Badhe, S. S., Shirbahadurkar, S. D., Gulhane, S. R. 2022. Renyi entropy and deep learning-based approach for accent classification. Multimedia Tools and Applications, 81(1), 1467–1499.
  • [8] Singh, V. K., Sharma, K., Sur, S. N. 2025. Acoustic scene classification using dynamic time warping technique based on short time Fourier transform and discrete wavelet transforms. Circuits, Systems, and Signal Processing, 44(3), 1887–1913.
  • [9] İkizler, N. 1995. Doğrusal Öngörümleme Kodlama ve Yapay Sinir Ağı Yöntemlerinin Ses Tanımada Kullanılması. Karadeniz Teknik Üniversitesi, Fen Bilimleri Enstitüsü Yüksek Lisans Tezi, 83s, Trabzon.
  • [10] Malik, M., Malik, M. K., Mehmood, K., Makhdoom, I. 2021. Automatic speech recognition: a survey. Multimedia Tools and Applications, 80(6), 9411–9457.
  • [11] Debnath, S., Roy, P. 2021. Appearance and shape-based hybrid visual feature extraction: toward audio–visual automatic speech recognition. Signal, Image, and Video Processing, 15(1), 25–32.
  • [12] Vashisht, V., Pandey, A. K., Yadav, S. P. 2021. Speech recognition using machine learning. IEIE Transactions on Smart Processing and Computation, 10(3), 233–239.
  • [13] Madhu, G., Bukka, A. 2023. Ensemble learning model for gender recognition using the human voice. In Proc. 2023 1st International Conference on Advanced Electronics, Electronics, Computer Intelligence (ICAEECI), October 2023, 1–5.
  • [14] Alsobhani, A., ALabboodi, H. M., Mahdi, H. 2021. Speech recognition using convolution deep neural networks. Journal of Physics: Conference Series, 1973(1), 012166, August 2021.
  • [15] Alharbi, S. et al. 2021. Automatic speech recognition: systematic literature review. IEEE Access, 9, 131858–131876.
  • [16] Bakır, H., Çayır, A. N., Navruz, T. S. 2024. A comprehensive experimental study for analyzing the effects of data augmentation techniques on voice classification. Multimedia Tools and Applications, 83(6), 17601–17628.
  • [17] Kurtkaya, M. 2020. Turkish speech command dataset. https://www.kaggle.com/murat-kurtkaya/turkish-speech-command-dataset (Accessed: 15.07.2025).
  • [18] İkizler, N. 2002. Türkçe’de Konuşmacıdan Bağımsız Hece Tanıma Sistemi, Karadeniz Teknik Üniversitesi, Fen Bilimleri Enstitüsü, Doktora Tezi, 143s, Trabzon.
  • [19] İkizler, N., Çavdar, İ. H., Ekim, G. 2005. Türkçe’de konuşmacıdan bağımsız ayrık hece tanıma sistemi. In Proc. IEEE Signal Processing and Communications Applications Conference (SIU), vol. 1, Kayseri, Türkiye, May, 55–59.
  • [20] Ekim, G., İkizler, N., Atasoy, A., Çavdar, İ. H. 2008. A speaker recognition system using cross correlation. In Proc. IEEE 16th Signal Processing and Communications Applications Conference (SIU), Aydın, Türkiye, April, 18–21.
  • [21] Liu, D., Xu, J., Zhang, P., Yan, Y. 2021. A unified system for multilingual speech recognition and language identification. Speech Communication, 127, 17–28.
  • [22] Iqbal, Y., Zhang, T., Gunawan, T. S., Pratondo, A., Zhao, X., Geng, Y., et al. 2025. A hybrid speech enhancement technique based on discrete wavelet transform and spectral subtraction. IEEE Access.
  • [23] Andriyanov, N. 2023. The use of correlation features in the problem of speech recognition. Algorithms, 16(2), 90.
  • [24] Ikizler, N., Ekim, G. 2025. Investigating the effects of Gaussian noise on epileptic seizure detection: The role of spectral flatness, bandwidth, and entropy. Engineering Science and Technology, International Journal, 64, 102005.
  • [25] Mohine, S., Gupta, P., Bansod, B. S., Bhalla, R., Basra, A. 2022. Evaluation of acoustic modality features for moving vehicle identification. Multidimensional Systems and Signal Processing, 33(4), 1349–1365.
  • [26] Nawas, K. K., Barik, M. K., Khan, A. N. 2021. Speaker recognition using random forest. In Proc. ITM Web Conference, vol. 37, 01022.
  • [27] Singh, M. K. 2024. Feature extraction and classification efficiency analysis using machine learning approach for speech signal. Multimedia Tools and Applications, 83(16), 47069–47084.
  • [28] Goh, M., Yann, X. L. 2021. A novel sentiments analysis model using perceptron classifier. International Journal of Electronics Engineering Applications, 9(4), 1–10.
  • [29] Ferrer, L. 2022. Analysis and comparison of classification metrics. arXiv preprint, arXiv:2209.05355.
  • [30] Omuya, E.O., Okeyo, G. O., Kimwele, M. W. 2021. Feature selection for classification using principal component analysis and information gain. Expert Systems with Applications, 174, 114765.
  • [31] Unluturk, A. 2023. Speech Command Based Intelligent Control of Multiple Home Devices for Physically Handicapped. In Proc. 2023 5th Global Power, Energy and Communication Conference (GPECOM), June, 560–564, IEEE.
  • [32] Karakaş, B. 2025. Türkçe Sesli Komut Verilerinin Evrişimsel Sinir Ağı ile Sınıflandırılması. Mühendislik Bilimleri ve Araştırmaları Dergisi, 7(1), 51–59.
  • [33] Uslu, İ. B., Tora, H., Sümer, E., Türker, M. 2020. Yalıtık Sözcüklü bir Türkçe Konuşma Tanıma Sisteminin Yapay Veri Artırımı ile Tasarımı ve Gerçekleştirilimi. Afyon Kocatepe University Journal of Science and Engineering, 20(6), 1147–1155.
  • [34] Işık, G. 2019. Türkçe Ağızların Tanınmasında Derin Öğrenme Tekniğinin Kullanılması. Hacettepe Üniversitesi Fen Bilimleri Enstitüsü, Doktora Tezi, 100s, Ankara.
There are 34 citations in total.

Details

Primary Language English
Subjects Speech Recognition
Journal Section Research Article
Authors

Nuri İkizler 0000-0002-7632-1973

Submission Date July 29, 2025
Acceptance Date December 22, 2025
Publication Date April 24, 2026
DOI https://doi.org/10.19113/sdufenbed.1753641
IZ https://izlik.org/JA93NA43GK
Published in Issue Year 2026 Volume: 30 Issue: 1

Cite

APA İkizler, N. (2026). Hybrid Spectral and Statistical Feature Modelling with Cross-Correlation and Ensemble Learning for Robust Turkish Voice Command Classification. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 30(1), 67-82. https://doi.org/10.19113/sdufenbed.1753641
AMA 1.İkizler N. Hybrid Spectral and Statistical Feature Modelling with Cross-Correlation and Ensemble Learning for Robust Turkish Voice Command Classification. J. Nat. Appl. Sci. 2026;30(1):67-82. doi:10.19113/sdufenbed.1753641
Chicago İkizler, Nuri. 2026. “Hybrid Spectral and Statistical Feature Modelling With Cross-Correlation and Ensemble Learning for Robust Turkish Voice Command Classification”. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi 30 (1): 67-82. https://doi.org/10.19113/sdufenbed.1753641.
EndNote İkizler N (April 1, 2026) Hybrid Spectral and Statistical Feature Modelling with Cross-Correlation and Ensemble Learning for Robust Turkish Voice Command Classification. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi 30 1 67–82.
IEEE [1]N. İkizler, “Hybrid Spectral and Statistical Feature Modelling with Cross-Correlation and Ensemble Learning for Robust Turkish Voice Command Classification”, J. Nat. Appl. Sci., vol. 30, no. 1, pp. 67–82, Apr. 2026, doi: 10.19113/sdufenbed.1753641.
ISNAD İkizler, Nuri. “Hybrid Spectral and Statistical Feature Modelling With Cross-Correlation and Ensemble Learning for Robust Turkish Voice Command Classification”. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi 30/1 (April 1, 2026): 67-82. https://doi.org/10.19113/sdufenbed.1753641.
JAMA 1.İkizler N. Hybrid Spectral and Statistical Feature Modelling with Cross-Correlation and Ensemble Learning for Robust Turkish Voice Command Classification. J. Nat. Appl. Sci. 2026;30:67–82.
MLA İkizler, Nuri. “Hybrid Spectral and Statistical Feature Modelling With Cross-Correlation and Ensemble Learning for Robust Turkish Voice Command Classification”. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, vol. 30, no. 1, Apr. 2026, pp. 67-82, doi:10.19113/sdufenbed.1753641.
Vancouver 1.Nuri İkizler. Hybrid Spectral and Statistical Feature Modelling with Cross-Correlation and Ensemble Learning for Robust Turkish Voice Command Classification. J. Nat. Appl. Sci. 2026 Apr. 1;30(1):67-82. doi:10.19113/sdufenbed.1753641

e-ISSN :1308-6529
Linking ISSN (ISSN-L): 1300-7688

All published articles in the journal can be accessed free of charge and are open access under the Creative Commons CC BY-NC (Attribution-NonCommercial) license. All authors and other journal users are deemed to have accepted this situation. Click here to access detailed information about the CC BY-NC license.