EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Speaker Identification and Verification Using Convolutional Neural Network CNN

Azhar S. Abdulaziz, Akram Dawood, Amar Daood

Tikrit Journal of Engineering Sciences · 31.05.2025 · 32 (2) · 1-13

DOI: 10.25130/tjes.32.2.19 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Tikrit Journal of Engineering Sciences, online erschienen am 31.05.2025. Verfasst von Azhar S. Abdulaziz und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Speaker identification and verification are important fields contributing to smart IoT, phone banking, remote login services, E-learning, and other applications. In this work, the speaker identification and verification processes have been experimentally proven to have mutual enhancement effects if they are merged together in a proper manner. Speaker identification and verification work cooperatively so that the verifier will enhance the identifier model. The first step is to identify the speaker using context – independent speech signal, and the identifier model (ID) is trained using a classification model. The model’s outputs are then used to control the verification process as a next step. When the verification result is positive, the first process outcome is approved with high confidence. Otherwise, the negative verification will force the ID process to re-configure itself. The loop continues until both verification and ID agree on the speaker. A multiple Gaussian mixture GMM was used to efficiently model each person’s speech features (MFCC) for using expectation maximization (EM). On the other hand, the conducted experiments showed that the one-dimensional convolutional neural network (1D-CNN) proved its superiority over other models for speaker identification. A novel approach was proposed, proving that little data can be expanded with split-add-noise and train-on-the-fly procedures. In many speaker identification approaches, the specific context was used as a keyword or a password to simplify the processing, requiring big data to achieve high accuracy. It is noteworthy that a small amount of data was enough to efficiently train the proposed model, with a verification error of around 3%, i.e., an accuracy of 97%. Meanwhile, 95% and 96% identification accuracy was achieved using two different datasets. Additionally, the suggested algorithm did not imply using any keyword or password because it is a context-independent approach.

Zitieren

APA

Abdulaziz, A. S., Dawood, A., & Daood, A. (2025). Speaker Identification and Verification Using Convolutional Neural Network CNN. Tikrit Journal of Engineering Sciences, 32(2), 1-13. https://doi.org/10.25130/tjes.32.2.19

Vancouver

Abdulaziz AS, Dawood A, Daood A. Speaker Identification and Verification Using Convolutional Neural Network CNN. Tikrit Journal of Engineering Sciences. 2025;32(2):1-13. doi:10.25130/tjes.32.2.19

BibTeX
@article{Abdulaziz2025,
  author = {Abdulaziz, Azhar S. and Dawood, Akram and Daood, Amar},
  title = {Speaker Identification and Verification Using Convolutional Neural Network CNN},
  journal = {Tikrit Journal of Engineering Sciences},
  year = {2025},
  volume = {32},
  number = {2},
  pages = {1--13},
  doi = {10.25130/tjes.32.2.19}
}
Kostenlos starten →