Robust Persian Speaker Identification Using a Lightweight Attention‐Based CNN With Spectral Augmentation
IET Biometrics · 2026-01 · 2026 (1)
DOI: 10.1049/bme2/5420687 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Biometrics, online erschienen am 25.06.2026. Verfasst von Atefe Pakzad und 2 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Accurate speaker identification is critical for forensic investigations and biometric authentication. This study introduces Lightweight squeeze‐and‐excitation network (LSE‐Net), a compact, robust deep learning architecture specifically tailored for speaker identification in challenging, noisy environments. Our approach integrates four core design principles: RMS‐energy‐based voice activity detection (VAD) for signal refinement, standardized Log‐Mel spectrogram extraction, noise‐aware regularization with spectral data augmentation to enhance generalization, and channel‐wise squeeze‐excitation (SE) blocks that dynamically recalibrate feature maps to emphasize speaker‐discriminative information. Finally, an utterance‐level probability aggregation strategy ensures robust classification of entire audio recordings. We evaluated LSE‐Net on two datasets: the newly constructed PERSID33 (933 formal Persian news‐style utterances from 33 speakers) and the benchmark TIMIT dataset (6300 utterances from 630 speakers). Experiments were conducted across diverse conditions, including clean audio and various real‐world and synthetic noise scenarios at multiple signal‐to‐noise ratios. LSE‐Net achieved 100% accuracy on PERSID33 and 95.07% on TIMIT under noise‐free conditions, consistently outperforming baseline methods. In noisy settings, LSE‐Net maintained near‐perfect accuracy on the PERSID33 dataset and demonstrated superior robustness on the larger TIMIT dataset compared to state‐of‐the‐art (SOTA) approaches. Ablation studies confirmed that spectral augmentation and SE attention are pivotal in preserving identification accuracy under acoustic stress. These results demonstrate that LSE‐Net is a highly efficient, forensic‐grade solution for speaker identification, particularly suitable for constrained or noisy investigative contexts.
Zitieren
APA
Pakzad, A., Hourali, S., & Kiani, V. (2026). Robust Persian Speaker Identification Using a Lightweight Attention‐Based CNN With Spectral Augmentation. IET Biometrics, 2026(1). https://doi.org/10.1049/bme2/5420687
Vancouver
Pakzad A, Hourali S, Kiani V. Robust Persian Speaker Identification Using a Lightweight Attention‐Based CNN With Spectral Augmentation. IET Biometrics. 2026;2026(1). doi:10.1049/bme2/5420687
BibTeX
@article{Pakzad2026,
author = {Pakzad, Atefe and Hourali, Samira and Kiani, Vahid},
title = {Robust Persian Speaker Identification Using a Lightweight Attention‐Based CNN With Spectral Augmentation},
journal = {IET Biometrics},
year = {2026},
volume = {2026},
number = {1},
doi = {10.1049/bme2/5420687}
}
EUVIMED