期刊
出版社
IEEE
DOI: 10.1109/IJCNN52387.2021.9533654
关键词
audio; classification; ESC; Fourier transform; fbsp-wavelet
类别
资金
- TU Kaiserslautern CS PhD scholarship program
- BMBF project ExplAINN [01IS19074]
Environmental Sound Classification (ESC) is a rapidly evolving field that has shown benefits in applying visual domain techniques to audio tasks. The proposed fbsp-layer, combined with a high-performance audio classification model, outperforms previous methods, achieving high accuracy on standard datasets. The study also evaluates different pre-training strategies and the model's robustness against signal perturbations.
Environmental Sound Classification (ESC) is a rapidly evolving field that recently demonstrated the advantages of application of visual domain techniques to the audio-related tasks. Previous studies indicate that the domain-specific modification of cross-domain approaches show a promise in pushing the whole area of ESC forward. In this paper, we present a new time-frequency transformation layer that is based on complex frequency B-spline (fbsp) wavelets. Being used with a high-performance audio classification model, the proposed fbsp-layer provides an accuracy improvement over the previously used Short-Time Fourier Transform (STFT) on standard datasets. We also investigate the influence of different pre-training strategies, including the joint use of two large-scale datasets for weight initialization: ImageNet and AudioSet. Our proposed model out-performs other approaches by achieving accuracies of 95.20% on the ESC-50 and 89.14% on the UrbanSound8K datasets. Additionally, we assess the increase of model robustness against additive white Gaussian noise and reduction of an effective sample rate introduced by the proposed layer and demonstrate that the fbsp-layer improves the model's ability to withstand signal perturbations, in comparison to STFT-based training. For the sake of reproducibility, our code is made available.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据