Open AccessReal-Time Recognition Algorithm of Vehicle External Specific Sounds Based on Spectrum Characteristics
Author(s) -
Hongbin Lei,
Botao Wang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1631/1/012076
Subject(s) - robustness (evolution) , computer science , interference (communication) , speech recognition , noise (video) , computer vision , artificial intelligence , frequency spectrum , algorithm , pattern recognition (psychology) , image (mathematics) , spectral density , telecommunications , channel (broadcasting) , biochemistry , chemistry , gene
As the development of vehicle sound insulation technology, drivers ignore some external sound information regularly. It is particularly important for the recognition of external sounds when the vehicle is driving. The real-time detection of the fundamental frequency of the external sound is not accurate due to the complexity of the external environment and the noise interference. In this paper, a recognition algorithm of vehicle external specific sounds is presented. The spectrum information of the external sound is converted into an image form, and the analysis result is obtained after processing the spectrum image. We choose five different types of sounds and the total number of 1000 samples for testing. The experiment data shows that the overall accuracy of the algorithm’s processing data can reach more than 90%, and the recognition rate can reach more than 90%. This algorithm has the characteristics of high accuracy and strong robustness, and it can easily be realized in real time.