Enhancing Driving Control via Speech Recognition Utilizing Influential Parameters in Deep Learning Techniques
Yükleniyor...
Tarih
2025
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Multidisciplinary Digital Publishing Institute (MDPI)
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
This study investigates the enhancement of automated driving and command control through speech recognition using a Deep Neural Network (DNN). The method depends on some sequential stages such as noise removal, feature extraction from the audio file, and their classification using a neural network. In the proposed approach, the variables that affect the results in the hidden layers were extracted and stored in a vector to classify them and issue the most influential ones for feedback to the hidden layers in the neural network to increase the accuracy of the result. The result was 93% in terms of accuracy and with a very good response time of 0.75 s, with PSNR 78 dB. The proposed method is considered promising and is highly satisfactory to users. The results encouraged the use of more commands, more data processing, more future exploration, and the addition of sensors to increase the efficiency of the system and obtain more efficient and safe driving, which is the main goal of this research.
Açıklama
Article number; 496.
Anahtar Kelimeler
deep neural network, driving control, feature extraction, noise reduction, speech recognition
Kaynak
Electronics (Switzerland)
WoS Q Değeri
Q2
Scopus Q Değeri
Cilt
14
Sayı
3
Künye
Hussein, H. H., Karan, O., & Kurnaz, S. (2025). Enhancing Driving Control via Speech Recognition Utilizing Influential Parameters in Deep Learning Techniques. Electronics, 14(3), 496.
