Research Article

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

Volume: 30 Number: 1 April 24, 2026
TR EN

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

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.

Keywords

References

  1. [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. [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. [3] Gormez, Y. 2024. Customized deep learning based Turkish automatic speech recognition system supported by language model. PeerJ Computer Science, 10, e1981.
  4. [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. [5] Kang, O., Pickering, L. 2024. Acoustic and temporal analysis for assessing speaking. In The Concise Companion to Language Assessment, 383.
  6. [6] Abdul, Z. K., Al-Talabani, A. K. 2022. Mel frequency cepstral coefficient and its applications: A review. IEEE Access, 10, 122136–122158.
  7. [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. [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.

Details

Primary Language

English

Subjects

Speech Recognition

Journal Section

Research Article

Publication Date

April 24, 2026

Submission Date

July 29, 2025

Acceptance Date

December 22, 2025

Published in Issue

Year 2026 Volume: 30 Number: 1

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.