Acoustic scene classification using deep CNN with fine-resolution feature
作者：
Highlights：
• A new model for acoustic scene classification is proposed.
• A relationship between time-frequency resolution and receptive field is modeled.
• A fine-resolution feature with semantic information is used for classification.
• The proposed method can customize feature representations in various resolutions.
• Compared to other deep CNNs, the proposed model reduces computational complexity.
摘要
•A new model for acoustic scene classification is proposed.•A relationship between time-frequency resolution and receptive field is modeled.•A fine-resolution feature with semantic information is used for classification.•The proposed method can customize feature representations in various resolutions.•Compared to other deep CNNs, the proposed model reduces computational complexity.
论文关键词：Acoustic scene classification,Convolutional neural network,Lateral construction,Depth-wise separable convolution,Fine-resolution convolutional neural network
论文评审过程：Received 4 August 2019, Revised 27 October 2019, Accepted 27 October 2019, Available online 31 October 2019, Version of Record 7 November 2019.
论文官网地址：https://doi.org/10.1016/j.eswa.2019.113067
