摘要
为实现汽车在高速行驶过程中的车外应急车辆警笛声检测,提出一种基于频谱—时域特征融合的车载检测方法。对输入声音信号执行快速Fourier变换并计算对数Mel谱图以获得频域特征;采用卷积神经网络在时域中建模声音波形,得到其时域表示。利用坐标注意力网络对频域与时域特征进行融合与增强,并将融合结果输入分类器以实现检测。在公开和实采数据集上进行了实验。结果表明:在LSAD-EVSRN数据集上,受试者工作特征曲线下面积(AUC)得分为98.92%,较单独采用时域特征方法提升14.88%,较单独采用频域特征方法提升2.52%。因而,验证了该融合策略在提升检测性能方面的有效性,尤其在噪声环境下具有高稳定性。
An in-vehicle detection method was proposed based on the fusion of spectral and temporal features to detect the external emergency vehicle sirens during high-speed driving.The input audio signal was transformed using the fast Fourier transform,and its log-Mel spectrogram was computed to extract spectral features.A convolutional neural network was used to model the raw waveform in the time domain,yielding temporal features.A coordinate attention mechanism was used to fuse and enhance the spectral and the temporal representations.The fused features were subsequently fed into a classifier for final detection.The experiments were conducted on both public and real-recorded datasets.The results show that on the LSADEVSRN dataset,the proposed method achieves an AUC(area under the receiver operating characteristic curve)score of 98.92%,with representing an improvement of 14.88% compared to using temporal features alone,and 2.52% compared to using spectral features alone.These results confirm the effectiveness of the fusion strategy,with a high robustness particularly under noisy conditions.
作者
李昊
周浩
LI Hao;ZHOU Hao(Z-one Technology co.,Ltd.,Shanghai 201804,China;School of Communications and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 40065,China)
出处
《汽车安全与节能学报》
北大核心
2025年第4期529-538,共10页
Journal of Automotive Safety and Energy
基金
国家重点研发计划专项课题(2024QY2630)。
关键词
汽车安全
警笛声检测
应急车辆
声音事件检测
特征融合
automotive safety
siren detection
emergency vehicles
sound event detection
feature fusion
