@techreport{Abbasi2020,
    Author = "Abbasi, Reyhaneh and Balazs, Peter",
    title = "Acoustic Scene Classification by the Snapshot Ensemble of {CNNs} with {XGBoost}",
    institution = "DCASE2020 Challenge",
    year = "2020",
    month = "June",
    abstract = "This is the report for the DCASE challenge task 1A. The aim is to implement acoustic scene classification of audio recordings into 10 predefined classes including Airport, shopping mall, metro station, street pedestrian, public square, street traffic, tram, bus, metro, and park. Two main drawbacks of this task are that recordings are provided by five devices with different quality and that some of these classes are very close in terms of acoustic information. To bias correct all instruments against the reference (here the instrument A), we have used XGboost algorithm fed by standaridiezd Mel spectrogram. Our classifier consists of a CNN, mix-up augmentation, and snapshot ensemble (to decrease the total number of parameters and, consequently, the variance of model prediction). Our model has yielded an accuracy of 62.1\% and cross-entropy loss of 1.06. Whereas the baseline model has yielded the accuracy and cross-entropy loss of 54.1\% and 1.36, respectively."
}

@techreport{Aryal2020,
    Author = "Aryal, Nisan and Lee, Sang Woong",
    title = "Attention-Based Resnet-18 Model for Acoustic Scene Classification",
    institution = "DCASE2020 Challenge",
    year = "2020",
    month = "June",
    abstract = "This technical report describes our approach to solve Detection and Classification of Acoustic Scenes and Events (DCASE) 2020 challenge task1a. Resnet-18 with attention model and Openl3 embedding are used to solve the acoustic scene classification problem. The model shows 59.6\% accuracy in the training and validation split of the development set, which is 5.5\% higher than that of the baseline network."
}

@techreport{Changmin2020,
    Author = "Changmin, Kim and Soonshin, Seo and Ji-Hwan, Kim",
    title = "Multi-Channel Feature Using Inter-Class and Inter-Device Standard Deviations for Acoustic Scene Classification",
    institution = "DCASE2020 Challenge",
    year = "2020",
    month = "June",
    abstract = "In this technical report, we describe our acoustic scene classification methods submitted to detection and classification of acoustic scenes and events challenge 2020 task 1a. Our proposed methods aim to maximize the differences between acoustic scene classes and minimize the differences between various devices. We obtained the inter-class and inter-device standard deviations of the training data and applied them to the log-mel spectrogram features. These features are added to the channel of the original log-mel spectrogram. In addition, we applied class-wise random masking for the frequency domain with small standard deviations. Then, masked features are divided into quarters on the frequency axis. They are trained using four-pathway residual convolutional neural networks. Our proposed methods achieved an overall accuracy of 72.7\% for the official development dataset, which was an improvement by 18.6\% over the official baseline."
}