Deep Learning-Based Speech Enhancement for Robust Sound Classification in Security Systems
Guardado en:
| Publicado en: | Electronics vol. 14, no. 13 (2025), p. 2643-2668 |
|---|---|
| Autor principal: | |
| Otros Autores: | , , |
| Publicado: |
MDPI AG
|
| Materias: | |
| Acceso en línea: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3229142959 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2079-9292 | ||
| 024 | 7 | |a 10.3390/electronics14132643 |2 doi | |
| 035 | |a 3229142959 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 231458 |2 nlm | ||
| 100 | 1 | |a Mensah, Samuel Yaw |u School of Information Engineering, Tianjin University, 92 Weijin Road, Nankai District, Tianjin 300072, China | |
| 245 | 1 | |a Deep Learning-Based Speech Enhancement for Robust Sound Classification in Security Systems | |
| 260 | |b MDPI AG |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Deep learning has emerged as a powerful technique for speech enhancement, particularly in security systems where audio signals are often degraded by non-stationary noise. Traditional signal processing methods struggle in such conditions, making it difficult to detect critical sounds like gunshots, alarms, and unauthorized speech. This study investigates a hybrid deep learning framework that combines Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Generative Adversarial Networks (GANs) to enhance speech quality and improve sound classification accuracy in noisy security environments. The proposed model is trained and validated using real-world datasets containing diverse noise distortions, including VoxCeleb for benchmarking speech enhancement and UrbanSound8K and ESC-50 for sound classification. Performance is evaluated using industry-standard metrics such as Perceptual Evaluation of Speech Quality (PESQ), Short-Time Objective Intelligibility (STOI), and Signal-to-Noise Ratio (SNR). The architecture includes multi-layered neural networks, residual connections, and dropout regularization to ensure robustness and generalizability. Additionally, the paper addresses key challenges in deploying deep learning models for security applications, such as computational complexity, latency, and vulnerability to adversarial attacks. Experimental results demonstrate that the proposed DNN + GAN-based approach significantly improves speech intelligibility and classification performance in high-interference scenarios, offering a scalable solution for enhancing the reliability of audio-based security systems. | |
| 653 | |a Mean square errors | ||
| 653 | |a Accuracy | ||
| 653 | |a Datasets | ||
| 653 | |a Deep learning | ||
| 653 | |a Performance evaluation | ||
| 653 | |a Classification | ||
| 653 | |a Multilayers | ||
| 653 | |a Artificial neural networks | ||
| 653 | |a Real time | ||
| 653 | |a Signal processing | ||
| 653 | |a Generative adversarial networks | ||
| 653 | |a Speech processing | ||
| 653 | |a Audio recordings | ||
| 653 | |a Machine learning | ||
| 653 | |a Access control | ||
| 653 | |a Sound | ||
| 653 | |a Statistical analysis | ||
| 653 | |a Regularization | ||
| 653 | |a Artificial intelligence | ||
| 653 | |a Security systems | ||
| 653 | |a Fourier transforms | ||
| 653 | |a Signal to noise ratio | ||
| 653 | |a Intelligibility | ||
| 653 | |a Neural networks | ||
| 653 | |a Decision making | ||
| 653 | |a Network latency | ||
| 653 | |a Recurrent neural networks | ||
| 653 | |a Methods | ||
| 653 | |a Audio signals | ||
| 653 | |a Surveillance | ||
| 653 | |a Kalman filters | ||
| 653 | |a Speech | ||
| 700 | 1 | |a Zhang, Tao |u Digital Signal Processing Laboratory, Tianjin University, 92 Weijin Road, Nankai District, Tianjin 300072, China; zhangtao@tju.edu.cn (T.Z.); gregory@tju.edu.cn (Y.G.) | |
| 700 | 1 | |a Mahmud, Nahid AI |u School of Electrical & Information Engineering, Tianjin University, 92 Weijin Road, Nankai District, Tianjin 300072, China; nahidalmahmud@tju.edu.cn | |
| 700 | 1 | |a Geng Yanzhang |u Digital Signal Processing Laboratory, Tianjin University, 92 Weijin Road, Nankai District, Tianjin 300072, China; zhangtao@tju.edu.cn (T.Z.); gregory@tju.edu.cn (Y.G.) | |
| 773 | 0 | |t Electronics |g vol. 14, no. 13 (2025), p. 2643-2668 | |
| 786 | 0 | |d ProQuest |t Advanced Technologies & Aerospace Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3229142959/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3229142959/fulltextwithgraphics/embedded/6A8EOT78XXH2IG52?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3229142959/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch |