Automatic evaluation method for vehicle audio warning system using MFCC-polynomial hybrid feature

Abstract

In the evaluation of vehicle audio warning system, there is no automatic method. Besides, due to the noise interference of in-vehicle environmental, the quantity limitation and only positive training samples, the accuracy of traditional template matching or identification methods for audio is low. To solve the above problems, an efficient, accurate, and automatic evaluation method is proposed for vehicle audio warning system. Firstly, logmmse-spectrum subtraction method is used to filter the dynamic noise and static noise of the evaluation audio acquired in the in-vehicle environment. Secondly, the end point detection based on short-time energy is used to obtain the effective audio segment after noise reduction, and the start time of the audio warning segment can be accurately obtained. Then, the Mel Frequency Cepstrum Coefficient (MFCC) feature and the polynomial fitting feature of each audio segment are extracted. The hybrid features are treated as the input of the Hidden Markov Model-Gaussian Mixture Model (GMM-HMM) based audio matching model. Finally, according to frame shift set by endpoint detection and the audio sampling frequency, the emitted time of matched audio warning can be calculated to support the evaluation of vehicle audio warning system. The experimental result shows that, with dynamic-static noise reduction and MFCC-polynomial hybrid feature, the average matching accuracy of the proposed method reaches 99.6% in the case of only five training samples.

Keywords

MFCC-polynomial hybrid feature audio noise filtering endpoint detection vehicle audio warning system evaluation

Get full access to this article

View all access options for this article.

References

Yang

Shladover

X-Y

, et al. A first investigation of truck drivers’ preferences and behaviors using a prototype cooperative adaptive cruise control system. Transp Res Rec 2018; 2672(34): 39–48.

Zhang

Zou

Shen

, et al. Design, implementation, and evaluation of a roadside cooperative perception system. Transp Res Rec 2022; 2676(11): 273–284.

Gao

Zhu

Gao

, et al. A self-learning lane change motion planning system considering the driver’s personality. Proc IMechE, Part D: J Automobile Engineering 2021; 235(14): 3322–3338.

Cano

Batlle

Kalker

, et al. A review of audio fingerprinting. J VLSI Signal Process Syst Signal Image Video Technol 2005; 41: 271–284.

Alvarez

Park

H-J

. End-to-end streaming keyword spotting. In: ICASSP 2019 - 2019 IEEE international conference on acoustics, speech and signal processing (ICASSP), Brighton, UK, 12–17 May 2019, pp.6336–6340. New York: IEEE.

Lin

Kilgour

Roblek

, et al. Training keyword spotters with limited and synthesized speech data. In: ICASSP 2020 - 2020 IEEE international conference on acoustics, speech and signal processing (ICASSP), Barcelona, Spain, 4–8 May 2020, pp.7474–7478. New York: IEEE.

Deng

. Automatic speech recognition. Berlin: Springer, 2016.

Zhao

Xie

. A new dynamic radius SVDD for fault detection of aircraft engine. Eng Appl Artif Intell 2021; 100: 104177.

Dong

Zhang

. SVDD-based network traffic anomaly detection method with high robustness. In: 2019 IEEE 5th international conference on computer and communications (ICCC), Chengdu, China, 6–9 December 2019, pp. 1522–1526. New York: IEEE.

10.

Khaledian

Pandy

Kundn

, et al. Real-time synchrophasor data anomaly detection and classification using Isolation Forest, KMeans, and LoOP. IEEE Trans Smart Grid 2021; 12(3): 2378–2388.

11.

Guo

Gao

, et al. Similarity-measured isolation forest: anomaly detection method for machine monitoring data. IEEE Trans Instrum Meas 2021; 70: 1–12.

12.

Zhang

Doughty

Shao

, et al. Audio-adaptive activity recognition across video domains. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp.13791–13800. Computer Vision Foundation.

13.

Besbes

Lachiri

. Classification of speech under stress based on cepstral features and one-class SVM. In: 2017 international conference on control, automation and diagnosis (ICCAD), Hammamet, Tunisia, 19–21 January 2017, pp.213–218. New York: IEEE.

14.

Droghini

Ferretti

Principi

, et al. A combined one-class SVM and template-matching approach for user-aided human fall detection by means of floor acoustic features. Comput Intell Neurosci 2017; 2017: 1512670.

15.

Liu

Lin

Xiao

, et al. Self-adversarial variational autoencoder with spectral residual for time series anomaly detection. Neurocomputing 2021; 458: 349–363.

16.

Thill

Konen

Wang

, et al. Temporal convolutional autoencoder for unsupervised anomaly detection in time series. Appl Soft Comput 2021; 112: 107751.

17.

Schoneveld

Othmani

Abdelkawy

. Leveraging recent advances in deep learning for audio-visual emotion recognition. Pattern Recognit Lett 2021; 146: 1–7.

18.

Luan

Huang

Zhao

, et al. A comprehensive lateral motion prediction method of surrounding vehicles integrating driver intention prediction and vehicle behavior recognition. Proc IMechE, Part D: J Automobile Engineering 2023; 237(1): 61–74.

19.

Iglesias-Martínez

Fernández

Córdoba

Antonino-Daviu

, et al. Detection of nonadjacent rotor faults in induction motors via spectral subtraction and autocorrelation of stray flux signals. IEEE Trans Ind Appl 2019; 55(5): 4585–4594.

20.

Shanmeng Hamdulla

Ablimit

. Summary of research methods of voice activity. In: 2021 international conference of social computing and digital economy (ICSCDE), Chongqing, China, 28–29 August 2021, pp.313–317. New York: IEEE.

21.

Labied

Belangour

Banane

, et al. An overview of automatic speech recognition preprocessing techniques. In: 2022 international conference on decision aid sciences and applications (DASA), Chiangrai, Thailand, 23–25 March 2022, pp.804–809. New York: IEEE.

22.

Soares

ASP

Parreira

Souza

, et al. Voice activity detection using generalized exponential kernels for time and frequency domains. IEEE Trans Circuits Syst I Regul Pap 2019; 66(6): 2116–2123.

23.

Wei

Zeng

. Single-channel speech enhancement based on subband spectral entropy. J Audio Eng Soc 2018; 66(3): 100–113.

24.

Andayani

Theng

Tsun

, et al. Hybrid LSTM-transformer model for emotion recognition from speech audio files. IEEE Access 2022; 10: 36018–36027.

25.

Liu

Hussain

, et al. I sense you by breath: speaker recognition via breath biometrics. IEEE Trans Dependable Secure Comput 2020; 17(2): 306–319.

26.

Shi

Ahmad

, et al. Hidden Markov model based drone sound recognition using MFCC technique in practical noisy environments. J Commun Netw 2018; 20(5): 509–518.