@techreport{Arabnezhad2019,
    Author = "Arabnezhad, Fateme and Nasersharif, Babak",
    title = "Urban Acoustic Scene Classification Using Binaural Wavelet Scattering and Random Subspace Discrimination Method",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This report describe our contribution to Detection and Classification of Urban Acoustic Scenes on DCASE 2019 challenge (Task1 –Subtask A). We propose to use wavelet scatterings spectrum as a good representation and feature where we extracted from both average of 2 audio recorded(mono) and also difference of 2 audio recorded channels (side). The concatenation of these two set of wavelet scattering spectrum are used as a feature vector which is fed into a classifier based on random subspace method. In this work, Regularized Linear Discriminant Analysis (RLDA) is used as a base learner and a classification approach for Random Subspace Method. The experimental results shows that the proposed structure learn acoustic characteristics from audio segments. This structure achieved 87.98\% accuracy on whole development set (without cross-validation) and 78.83\% on leaderboard dataset."
}

@techreport{Bilot2019,
    Author = "Bilot, Valentin and Duong, Quang Khanh Ngoc",
    title = "Acoustic Scene Classification with Multiple Instance Learning and Fusion",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "Audio classification has been an emerging topic in the last few years, especially with the benchmark dataset and evaluation from DCASE. This paper present our deep learning models to address the acoustic scene classification (ASC) task of the DCASE 2019. The models exploit multiple instance learning (MIL) method as a way of guiding the network attention to different temporal segments of a recording. We then propose a simple late fusion of results obtained by the three investigated MIL-based models. Such fusion system uses multi-layer perceptron (MLP) to predict the final classes from the initial class probability predictions and obtains a better result on the development and the leaderboard dataset."
}

@techreport{Chen2019,
    Author = "Chen, Hangting and Liu, Zuozhen and Liu, Zongming and Zhang, Pengyuan and Yan, Yonghong",
    title = "Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This technical report describes the IOA team’s submission for TASK1A of DCASE2019 challenge. Our acoustic scene classification (ASC) system adopts a data augmentation scheme employing generative adversary networks. Two major classifiers, 1D deep convolutional neural network integrated with scalogram features and 2D fully convolutional neural network integrated with Mel filter bank features, are deployed in the scheme. Other approaches, such as adversary city adaptation, temporal module based on discrete cosine transform and hybrid architectures, have been developed for further fusion. The results of our experiments indicates that the final fusion systems A-D could achieve the accuracy above 85\% on the officially provided fold 1 evaluation dataset."
}

@techreport{Ding2019,
    Author = "Ding, Biyun and Liu, Ganjun and Liang, Jinhua",
    title = "Acoustic Scene Classification Based on Ensemble System",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This technical report is for the Task 1A Acoustic scene classification of the IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE). In this task, the features of audio will affect the performance. To improve the performance, we implement Acoustic scene classification task using multiple features and applying ensemble system which composed of CNN and GMM. According to the experiments which were performed with the DCASE 2019 challenge development dataset, the class average accuracy of GMM with 103 features is 64.3\%, which is an improvement of 4.2\% compared to Baseline CNN. Besides, the class average accuracy of the ensemble system is 66.3\% , which is an improvement of 7.4\% compared to Baseline CNN"
}

@techreport{Eghbal-zadeh2019,
    Author = "Eghbal-zadeh, Hamid and Koutini, Khaled and Widmer, Gerhard",
    title = "Acoustic Scene Classification and Audio Tagging with Receptive-Field-Regularized {CNNs}",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this report, we detail the CP-JKU submissions to the DCASE-2019 challenge Task 1 (acoustic scene classification) and Task 2 (audio tagging with noisy labels and minimal supervision). In all of our submissions, we use fully convolutional deep neural networks architectures that are regularized with Receptive Field (RF) adjustments. We adjust the RF of variants of Resnet and Densenet architectures to best fit the various audio processing tasks that use the spectrogram features as input. Additionally, we propose novel CNN layers such as Frequency-Aware CNNs, and new noise compensation techniques such as Adaptive Weighting for Learning from Noisy Labels to cope with the complexities of each task. We prepared all of our submissions without the use of any external data. Our focus in this year’s submissions is to provide the best-performing single-model submission, using our proposed approaches."
}

@techreport{FangLi2019,
    Author = "FangLi, Ning and Shuang, Duan",
    title = "Acoustic Scene Classification Based on the Dataset with Deep Convolutional Generated Against Network",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "As is known to us all, Convolutional Neural Networks have been the most excellent solution for image classification challenges. From the results of DCASE 2018 [1], the Convolutional Neural Network has also achieved excellent results in the classification of acoustic scenes. Therefore, our team also adopted Convolutional Neural Network for DCASE 2019 Task 1a. In order to make the audio features are exposed more, our team used multiple Mel-spectrograms to characterize the audio, trained multiple classifiers, and finally weighted the prediction results of each classifier to make results ensemble. The performance of classifier is largely limited by the quality and quantity of the data. From the results of the technical report [2], the use of GAN to augment the data set can play a vital role in the final performance, and our team also introduced Deep Convolution GANs (DCGAN) [3] to our solution to Task 1a Challenge, Our model ultimately achieved an accuracy of 0.846 on the development set and an accuracy of 0.671 on the leaderboard dataset."
}

@techreport{Fraile2019,
    Author = "Fraile, Ruben and Reina, Juan Carlos and Gutierrez-Arriola, Juana and Blanco, Elena",
    title = "Classification of Acoustic Scenes Based on Modulation Spectra and Position-Pitch Maps",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "A system for the automatic classification of acoustic scenes is proposed that uses the stereophonic signal captured by a binaural microphone. This system uses one channel for calculating the spectral distribution of energy across auditory-relevant frequency bands. It further obtains some descriptors of the envelope modulation spectrum (EMS) by applying the discrete cosine transform to the logarithm of the EMS. The availability of the two-channel binaural recordings is used for representing the spatial distribution of acoustic sources by means of position-pitch maps. These maps are further parametrized using the two-dimensional Fourier transform. These three types of features (energy spectrum, EMS and positionpitch maps) are used as inputs for a standard Gaussian Mixture Model with 64 components."
}

@techreport{Gao2019,
    Author = "Gao, Wei and McDonnell, Mark",
    title = "Acoustic Scene Classification Using Deep Residual Networks with Late Fusion of Separated High and Low Frequency Paths",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This technical report describes our approach to Tasks 1a, 1b and 1c in the 2019 DCASE acoustic scene classification challenge. Our focus was on developing strong single models, without use of any supplementary data. We investigated the use of a deep residual network applied to log-mel spectrograms complemented by log-mel deltas and delta-deltas. We designed the network to take into account that the temporal and frequency axes in spectrograms represent fundamentally different information. In particular, we used two pathways in the residual network: one for high frequencies and one for low frequencies, that were fused just two convolutional layers prior to the network output."
}

@techreport{Haocong2019,
    Author = "Haocong, Yang and Chuang, Shi and Huiyong, Li",
    title = "Acoustic Scene Classification Using {CNN} Ensembles and Primary Ambient Extraction",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This report describes our submission for Task 1a (acoustic scene classification) of the DCASE 2019 challenge. The results of the DCASE 2018 challenge demonstrate that the convolution neural networks (CNNs) and their ensembles can achieve excellent clas-sification accuracies. Inspired by the previous works, our method continues to work on the ensembles of CNNs, whereas the prima-ry ambient extraction is newly introduced to decompose a binaural audio sample into four channels by using the spatial information. The feature extraction is still carried out with mel spectrograms. 6 CNN models are trained by using the 4-fold cross validation. Ensemble is applied to further improve the performance. Finally, our method has achieved classification accuracies of 0.84 on the public leaderboard."
}

@techreport{Huang2019,
    Author = "Huang, Jonathan and Lopez Meyer, Paulo and Lu, Hong and Cordourier Maruri, Hector and Del Hoyo, Juan",
    title = "Acoustic Scene Classification Using Deep Learning-Based Ensemble Averaging",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In our submission to the DCASE 2019 Task 1a, we have explored the use of four different deep learning based neural networks architectures: Vgg12, ResNet50, AclNet, and AclSincNet. In order to improve performance, these four network architectures were pretrained with Audioset data, and then fine-tuned over the development set for the task. The outputs produced by these networks, due to the diversity of feature front-end and of architecture differences, proved to be complementary when fused together. The ensemble of these models’ outputs improved from best single model accuracy of 77.9\% to 83.0\% on the validation set, trained with the challenge default’s development split."
}

@techreport{Huang2019a,
    Author = "Huang, Zhenyi and Jiang, Dacan",
    title = "Acoustic Scene Classification Based on Deep Convolutional Neuralnetwork with Spatial-Temporal Attention Pooling",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "Acoustic scene classification is a challenging task in machine learn-ing with limited data sets. In this report, several different spectro-grams are applied to classify the acoustic scenes using deep convo-lutional neural network with spatial-temporal attention pooling. Inaddition, mixup augmentation is performed to further improve theclassification performance. Finally, majority voting is performed onsix different models and an accuracy of 73.86\% is achieved which is11.36 percentage points higher than the one of the baseline system."
}

@techreport{Hyeji2019,
    Author = "Hyeji, Seo and Jihwan, Park",
    title = "Acoustic Scene Classification Using Various Pre-Processed Features and Convolutional Neural Networks",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this technical report, we describe our acoustic scene classification algorithm submitted in DCASE 2019 Task 1a. We focus on various pre-processed features to categorize the class of acoustic scenes using only stereo microphone input signal. In the frontend system, the pre-processed and spatial information are extracted from the stereo microphone input. Residual network, subspectral network, and conventional convolutional neural network (CNN) are used for back-end systems. Finally, we ensemble all of the models to take advantage of each algorithm. By using proposed systems, we achieved a classification accuracy of 80.4\%, which is 17.9\% over than the baseline system."
}

@techreport{Jiang2019,
    Author = "Jiang, Shengwang and Shi, Chuang",
    title = "Acoustic Scene Classification Using Ensembles of Convolutional Neural Networks and Spectrogram Decompositions",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This technical report proposes ensembles of convolutional neural networks (CNNs) for the task 1 / subtask B of the DCASE 2019 challenge, with emphasis on using different spectrogram decompositions. The harmonic percussive source separation (HPSS), nearest neighbor filter (NNF), and vocal separation are applied to the monaural samples. Head-related transfer function (HRTF) is also proposed to transform monaural samples to binaural ones with augmented spatial information. Finally, 16 neural networks are trained and put together. The classification accuracy of the proposed system achieves 0.70166 on the public leaderboard."
}

@techreport{Jung2019,
    Author = "Jung, Jee-weon and Heo, Hee-Soo and Shim, Hye-jin and Yu, Ha-Jin",
    title = "Knowledge Distillation with Specialist Models in Acoustic Scene Classification",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this technical report, we describe our submission for the Detection and Classification of Acoustic Scenes and Events 2019 task1-a competition which exploits knowledge distillation with specialist models. Different acoustic scenes that share common properties are one of the main obstacles that hinder successful acoustic scene classification. We found that confusion between scenes, sharing the common properties, causes most of the errors in the acoustic scene classification. For example, the confusing scene pairs such as airport-shopping mall and metro-tram have caused the most errors in various systems. We applied knowledge distillation based on the specialist models to address the errors from the most confusing scene pairs. Specialist models where each model concentrates on discriminating a pair two similar scenes are exploited to provide soft-labels. We expected that knowledge distillation from multiple specialist models and a pre-trained generalist model to a single model could train an ensemble of models that gives more emphasis on discriminating specific acoustic scene pairs. Through knowledge distillation from well trained model and specialist models to single model, we report improved accuracy on the validation set."
}

@techreport{KK2019,
    Author = "KK, Teh and HW, Sun and Huy Dat, Tran",
    title = "The I2r Submission to {DCASE} 2019 Challenge",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This paper proposes Convolutional Neural Network (CNN) ensembles for acoustic scene classification of tasks1A of the DCASE 2019 challenge. In this approach various preprocessing features method: mel-filterbank and delta feature vectors, harmonic-percussive and subband power distribution are used to train CNN model. We also used score-fusion of the features to find an optimum feature configuration. On the official leaderboard data set of the task1A challenge, an accuracy of 79.67\% is achieved."
}

@techreport{Komider2019,
    Author = "Kośmider, Michał",
    title = "Calibrating Neural Networks for Secondary Recording Devices",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This report describes the solution to Task 1B of the DCASE 2019 challenge proposed by Samsung R\&D Institute Poland. Primary focus of the system for task 1B was a novel technique designed to address issues with learning from microphones with different frequency responses in settings with limited examples for the targeted secondary devices. This technique is independent from the architecture of the predictive model and requires just a few examples to become effective."
}

@techreport{Kong2019,
    Author = "Kong, Qiuqiang and Cao, Yin and Iqbal, Turab and Wang, Wenwu and Plumbley, Mark D.",
    title = "Cross-Task Learning for Audio Tagging, Sound Event Detection and Spatial Localization: {DCASE} 2019 Baseline Systems",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "The Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 challenge focuses on audio tagging, sound event detection and spatial localisation. DCASE 2019 consists of five tasks: 1) acoustic scene classification, 2) audio tagging with noisy labels and minimal supervision, 3) sound event localisation and detection, 4) sound event detection in domestic environments, and 5) urban sound tagging. In this paper, we propose generic cross-task baseline systems based on convolutional neural networks (CNNs). The motivation is to investigate the performance of a variety of models across several audio recognition tasks without exploiting the specific characteristics of the tasks. We looked at CNNs with 5, 9, and 13 layers, and found that the optimal architecture is task-dependent. For the systems we considered, we found that the 9-layer CNN with average pooling after convolutional layers is a good model for a majority of the DCASE 2019 tasks."
}

@techreport{Koutini2019,
    Author = "Koutini, Khaled and Eghbal-zadeh, Hamid and Widmer, Gerhard",
    title = "Acoustic Scene Classification and Audio Tagging with Receptive-Field-Regularized {CNNs}",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this report, we detail the CP-JKU submissions to the DCASE-2019 challenge Task 1 (acoustic scene classification) and Task 2 (audio tagging with noisy labels and minimal supervision). In all of our submissions, we use fully convolutional deep neural networks architectures that are regularized with Receptive Field (RF) adjustments. We adjust the RF of variants of Resnet and Densenet architectures to best fit the various audio processing tasks that use the spectrogram features as input. Additionally, we propose novel CNN layers such as Frequency-Aware CNNs, and new noise compensation techniques such as Adaptive Weighting for Learning from Noisy Labels to cope with the complexities of each task. We prepared all of our submissions without the use of any external data. Our focus in this year’s submissions is to provide the best-performing single-model submission, using our proposed approaches."
}

@techreport{Lehner2019,
    Author = "Lehner, Bernhard and Koutini, Khaled",
    title = "Acoustic Scene Classification with Reject Option Based on Resnets",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This technical report describes the submissions from the SAL/CP JKU team for Task 1 - Subtask C (classification on data that includes classes not encountered in the training data) of the DCASE-2019 challenge. Our method uses a ResNet variant specifically adapted to be used along with spectrograms in the context of Acoustic Scene Classification (ASC). The reject option is based on the logit values of the same networks. We do not use any of the provided external data sets, and perform data augmentation only with the mixup technique [1]. The result of our experiments is a system that achieves classification accuracies of up to around 60\% on the public Kaggle-Leaderboard. This is an improvement of around 14 percentage points compared to the official DCASE 2019 baseline."
}

@techreport{Lei2019,
    Author = "Lei, Chongqin and Wang, Zixu",
    title = "Multi-Scale Recalibrated Features Fusion for Acoustic Scene Classification",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "We investigate the effectiveness of multi-scale recalibrated features fusion for acoustic scene classification as contribution to the subtask of the IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE 2019). A general problem in acoustic scene classification task is audio signal segment contains less effective information. In order to further utilize features with less effective information to improve classification accuracy, we introduce the Squeeze-and-Excitation unit to embed the backbone structure of Xception to recalibrate the channel weights of feature maps in each block. In addition, the recalibrated features of multiscale are fused and finally fed into the full connection layer to get more useful information. Furthermore, we introduce Mixup method to augment the data in training stage to reduce the degree of over-fitting of network. The proposed method attains a recognition accuracy of 77.5\%, which is 13\% higher compared to the baseline system of the DCASE 2019 Acoustic Scenes Classification task."
}

@techreport{Liang2019,
    Author = "Liang, Han and Ma, Yaxiong",
    title = "Acoustic Scene Classification Using Attention-Based Convolutional Neural Network",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This technical report describes the Task 1 - Subtask A (Acoustic Scene Classification, ASC) of the DCASE 2019 challenge whose goal is to classify a test audio recording into one of the predefined classes that characterizes the environment. We detemine to use mel-spectrogram as audio feature and deep convolutional neural networks (CNNs) as classifier to classify acoustic scenes. In our method, spectrogram of every audio clip is divided in two ways. In addition, we introduce attention mechanism to further improve the performance. Experimental results illustrate that our best model can achieve classification accuracy of around 70.7\% for Development dataset, which is superior to the baseline system with the accuracy of 62.5\%."
}

@techreport{Ma2019,
    Author = "Ma, Xinixn and Gu, Mingliang",
    title = "Jsnu\_wdxy Submission for {DCASE}-2019: Acoustic Scene Classification with Convolution Neural Networks",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "Acoustic Scene Classification (ASC) is the task of identifying the scene from which the audio signal is recorded. It is one of the core research problems in the field of Computational Sound Scene Analysis. Most of current best performing Acoustic Scene Classification systems utilize Mel scale spectrograms with Convolutional Neural Networks (CNNs). In this paper, we demonstrate how we applied convolutional neural network for DCASE 2019 task1, acoustic scene classification. First, we applied Mel scale spectrogram to extract acoustic features. Mel scale is a common way to suit frequency warping of human ears, with strict decreasing frequency resolution on low to high frequency range. Second, we generate Mel spectrogram from binaural audio, adaptively learn 5 Convolutional Neural Networks. The best classification result of the proposed system was 71.1\% for Development dataset and 73.16\% for Leaderboard dataset."
}

@techreport{Ma2019a,
    Author = "Ma, Sifan and Liu, Wei",
    title = "Acoustic Scene Classification Based on Binaural Deep Scattering Spectra with Neural Network",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This technical report presents our approach for the acoustic scene classification of DCASE2019 task1a. Compared to traditional audio features such as Mel-frequency Cepstral Coefficients (MFCC) and Constant-Q Transform (CQT), we choose Deep Scattering Spectra (DSS) features which are more suitable for characterizing acoustic scenes. DSS is a good way to preserve high frequency information. Based on DSS features, we choose a network model of Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) to classify acoustic scenes. The experimental results show that our approach increase the classification accuracy from 62.5\% (DCASE2019 baseline) to 85\%."
}

@techreport{Mars2019,
    Author = "Mars, Rohith and Pratik, Pranay and Nagisetty, Srikanth and Lim, Chong Soon",
    title = "Acoustic Scene Classification From Binaural Signals Using Convolutional Neural Networks",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this report, we present the technical details of our proposed framework and solution for the DCASE 2019 Task 1A - Acoustic Scene Classification challenge. We describe the audio pre-processing, feature extraction steps and the time-frequency (TF) representations used for acoustic scene classification using binaural audio recordings. We employ two distinct architectures of convolutional neural networks (CNNs) for processing the extracted audio features for classification and compare their relative performance in terms of both accuracy and model complexity. Using an ensemble of the predictions from multiple models based on the above CNNs, we achieved an average classification accuracy of 79.35\% on the test split of the development dataset for this task and a system score of 82.33\% in the Kaggle public leaderboard, which is an improvement of ≈ 18\% over the baseline system."
}

@techreport{Mingle2019,
    Author = "Mingle, Liu and Yanxiong, Li",
    title = "The System for Acoustic Scene Classification Using Resnet",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this report, we present our works concerning task 1a of DCASE 2019, i.e. acoustic scene classification (ASC) with mismatched recording devices. We propose a strategy of classifiers voting for ASC. Specifically, an audio feature, such as logarithmic filter-bank (LFB), is first extracted from audio recordings. Then a series of convolutional neural network (CNN) is built for obtaining classifiers ensemble. Finally, classification result for each test sample is based on the voting of all classifiers."
}

@techreport{Naranjo-Alcazar2019,
    Author = "Naranjo-Alcazar, Javier and Perez-Castanos, Sergi and Zuccarello, Pedro and Cobos, Maximo",
    title = "{DCASE} 2019: {CNN} Depth Analysis with Different Channel Inputs for Acoustic Scene Classification",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "The objective of this technical report is to describe the framework used in Task 1, Acoustic scene classification (ASC), of the DCASE 2019 challenge. The presented approach is based on Log-Mel spectrogram representations and VGG-based Convolutional Neural Networks (CNNs). Three different CNNs, with very similar architectures, have been implemented. The main difference is the number of filters in their convolutional blocks. Experiments show that the depth of the network is not the most relevant factor for improving the accuracy of the results. The performance seems to be more sensitive to the input audio representation. This conclusion is important for the implementation of real-time audio recognition and classification system on edge devices. In the presented experiments the best audio representation is the Log-Mel spectrogram of the harmonic and percussive sources plus the Log-Mel spectrogram of the difference between left and right stereo-channels (L − R). Also, in order to improve accuracy, ensemble methods combining different model predictions with different inputs are explored. Besides geometric and arithmetic means, ensembles aggregated with the Orness Weighted Averaged (OWA) operator have shown interesting and novel results. The proposed framework outperforms the baseline system by 14.34 percentage points. For Task 1a, the obtained development accuracy is 76.84\%, being 62.5\% the baseline, whereas the accuracy obtained in public leaderboard is 77.33\%, being 64.33\% the baseline."
}

@techreport{Paseddula2019,
    Author = "Paseddula, Chandrasekhar and V.Gangashetty, Suryakanth",
    title = "{DCASE} 2019 Task 1a: Acoustic Scene Classification by Sffcc and {DNN}",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this study, we dealt with the acoustic scene classification (ASC) task in the Detection and Classification of Acoustic Scenes and Events (DCASE)-2019 challenge Task 1A. Single frequency filtering cepstral coefficients (SFFCC) features and Deep Neural networks (DNN) model is proposed for ASC. We have adopted a late fusion mechanism to further improve the performance and finally, to validate the performance of the model and compare it to the baseline system. We used the TAU Urban Acoustic Scenes 2019 development dataset for training and cross-validation, resulting in a 7.9\% improvement when compared to the baseline system."
}

@techreport{Pham2019,
    Author = "Pham, Lam and Doan, Tan and Thanh Ngo, Dat and Nguyen, Hung and Hoang Kha, Ha",
    title = "Cdnn-{CRNN} Joined Model for Acoustic Scene Classification",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This work proposes a deep learning framework applied for Acoustic Scene Classification (ASC), targeting DCASE2019 task 1A. In general, the front-end process shows a combination of three types of spectrograms: Gammatone (GAM), log-Mel and Constant Q Transform (CQT). The back-end classification presents a joined learning model between CDNN and CRNN. Our experiments over the development dataset of DCASE2019 challenge task 1A show a significant improvement, increasing 11.2\% compared to DCASE2019 baseline of 62.5\%. The Kaggle reports the classification accuracy of 74.6\% when we train all development dataset."
}

@techreport{Pham2019a,
    Author = "Pham, Lam and McLoughlin, Ian and Phan, Huy and Palaniappan, Ramaswamy",
    title = "A Multi-Spectrogram Deep Neural Network for Acoustic Scene Classification",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This work targets the task 1A and 1B of DCASE2019 challenge that are Acoustic Scene Classification (ASC) over ten different classes recorded by a same device (task 1A) and mismatched devices (task 1B). For the front-end feature extraction, this work proposes a combination of three types of spectrograms: Gammatone (GAM), log- Mel and Constant Q Transform (CQT). The back-end classification shows two training processes, namely pre-trained CNN and post- trained DNN, and the result of post-trained DNN is reported. Our experiments over the development dataset of DCASE2019 1A and 1B show significant improvement, increasing 14\% and 17.4 \% compared to DCASE2019 baseline of 62.5\% and 41.4\%, respectively. The Kaggle report also confirms the classification accuracy of 79\% and 69.2\% for task 1A and 1B."
}

@techreport{Plata2019,
    Author = "Plata, Marcin",
    title = "Deep Neural Networks with Supported Clusters Preclassification Procedure for Acoustic Scene Recognition",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this technical report, we presented a system for acoustic scene classification focuses on deeper analysis of data. We made an impact analysis of various combinations of arguments for short time Fourier transform (STFT) and Mel filter bank. We also used the harmonic and percussive source separation (HPSS) algorithm as an additional features extractor. Finally, next to common spectrograms divided and non-overlap classification neural networks, we decided to present an out-of-the-box solution with one main neural network trained on clustered labels and a few supporting neural network to distinguish between most difficult scenes, e.g. street pedestrian and public square."
}

@techreport{Primus2019,
    Author = "Primus, Paul and Eitelsebner, David",
    title = "Acoustic Scene Classification with Mismatched Recording Devices",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This technical report describes CP-JKU Student team’s approach for Task 1 - Subtask B of the DCASE 2019 challenge. In this context, we propose two loss functions for domain adaptation to learn invariant representations given time-aligned recordings. We show that these methods improve the classification performance on our cross-validation, as well as performance on the Kaggle leader board, up to three percentage points compared to our baseline model. Our best scoring submission is an ensemble of eight classifiers."
}

@techreport{Rakowski2019_t1,
    Author = "Rakowski, Alexander and Kośmider, Michał",
    title = "Frequency-Aware {CNN} for Open Set Acoustic Scene Classification",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This report describes systems used for Task 1c of the DCASE 2019 Challenge - Open Set Acoustic Scene Classification. The main system consists of a 5-layer convolutional neural network which preserves the location of features on the frequency axis. This is in contrast to the standard approach where global pooling is applied along the frequency-related dimension. Additionally the main system is combined with an ensemble of calibrated neural networks in order to improve generalization."
}

@techreport{Salvati2019,
    Author = "Salvati, Daniele and Drioli, Carlo and Foresti, Gian Luca",
    title = "Urban Acoustic Scene Classification Using Raw Waveform Convolutional Neural Networks",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "We present the signal processing framework and the results obtained with the development dataset (task 1, subtask A) for the detection and classification of acoustic scenes and events (DCASE 2019) challenge. The framework for the classification of urban acoustic scenes consists of a raw waveform (RW) end-to-end computational scheme based on convolutional neural networks (CNNs). The RW-CNN operates on a time-domain signal segment of 0.5 s and consists of 5 one-dimensional convolutional layers and 3 fully connected layers. The overall classification accuracy with the development dataset of the proposed RW-CNN is 69.7 \%."
}

@techreport{Sangwon2019,
    Author = "Sangwon, Suh and Youngho, Jeong and Wootaek, Lim and Sooyoung, Park",
    title = "Acoustic Scene Classification Using Specaugment and Convolutional Neural Network with Inception Modules",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This paper describes the system submitted to the Task 1a (Acoustic Scene Classification, ASC). By analyzing the major systems submitted in 2017 and 2018, we have selected a two-dimensional convolutional neural network (CNN) as the most suitable model for this task. The proposed model is composed of four convolution blocks; two of them are conventional CNN structures but the following two blocks consist of Inception modules. We have constructed a meta-learning problem with this model in order to train the super learner. For each base model training, we have applied different validation split methods to take advantage in generalized result with the ensemble method. In addition, we have applied data augmentation in real time with SpecAugment, which was performed for each base model. With our final system with all of the above techniques have applied, we have achieved an accuracy of 76.1\% with the development dataset and 81.3\% with the leader board set."
}

@techreport{Song2019,
    Author = "Song, Hongwei and Yang, Hao",
    title = "Feature Enhancement for Robust Acoustic Scene Classification with Device Mismatch",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This technical report describes our system for DCASE2019 Task1 SubtaskB. We focus on analyzing how device distortions affect the classic log Mel feature, which is the most adopted feature for convolutional neural networks (CNN) based models. We demonstrate mathematically that for log Mel feature, the influence of device distortion shows as an additive constant vector over the log Mel spectrogram. Based on this analysis, we propose to use feature enhancement methods such as spectrogram-wise mean subtraction and median filtering, to remove the additive term of channel distortions. Information loss introduced by the enhancement methods is discussed. We also motivate to use mixup technique to generate virtual samples with various device distortions. Combining the proposed techniques, we rank the second on the public kaggle leaderboard."
}

@techreport{Waldekar2019,
    Author = "Waldekar, Shefali and Saha, Goutam",
    title = "Wavelet Based Mel-Scaled Features for {DCASE} 2019 Task 1a and Task 1b",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This report describes a submission for IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 for Task 1 (acoustic scene classification (ASC)), sub-task A (basic ASC) and sub-task B (ASC with mismatched recording devices). The system exploits time-frequency representation of audio to obtain the scene labels. It follows a simple pattern classification framework employing wavelet transform based mel-scaled features along with support vector machine as classifier. The proposed system relatively outperforms the deep-learning based baseline system by almost 8\% for sub-task A and 26\% for sub-task B on the development dataset provided for the respective sub-tasks."
}

@techreport{Wang2019,
    Author = "Wang, Zhuhe and Ma, Jingkai and Li, Chunyang",
    title = "Acoustic Scene Classification Based on {CNN} System",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this study, we present a solution for the acoustic scene classification task1A in the DCASE 2019 Challenge. Our model uses a convolutional neural network and makes some improvements on the basis of CNN. Then we extract the MFCC (Mel frequency cepstral coefficient) feature from the official audio file and recreate the data set. Use this as an input to the neural network. Finally, comparing our model to the performance of the baseline system, the results were 12\% more accurate than the baseline system."
}

@techreport{Wang2019a_t1,
    Author = "Wang, Mou and Wang, Rui",
    title = "Ciaic-{ASC} System for {DCASE} 2019 Challenge Task1",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this report, we present our systems for subtask A and subtask B of the DCASE 2019 Task1, i.e. acoustic scene classification. The subtask A is a problem of basic closed set classification with data from a single device. In our system, we firstly extracted several acoustic features such as mel-spectrogram, hybrid constant-Q transform, harmonic-percussive source separation and etc.. Convolution neural networks (CNN) with average pooling are used to classify acoustic scenes. We averaged the outputs of CNN fed by different features to ensemble those methods. The subtask B is a classification problem with mismatched devices. So, we introduce a Domain Adaptation Neural Network (DANN) to extract the feature, which is uncorrelated with domain. We further ensemble DANN with CNN methods to obtain a better performance. The accuracy of the our system for subtask A is 0.783 on validation dataset and 0.816 on leaderboard dataset. The accuracy of subtask B achieves 0:717 on leaderborad dataset, which shows that our method can solve such a cross-domain problem and outperforms baseline system."
}

@techreport{Wang2019b,
    Author = "Wang, Wucheng and Liu, Mingle",
    title = "The {SEIE-SCUT} Systems for Acoustic Scene Classification Using {CNN} Ensemble",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this report, we present our works concerning task 1b of DCASE 2019, i.e. acoustic scene classification (ASC) with mismatched recording devices. We propose a strategy of CNN ensemble for ASC. Specifically, an audio feature, such as Mel-frequency cepstral coefficients (MFCCs) and logarithmic filter-bank (LFB), is first extracted from audio recordings. Then a series of convolutional neural network (CNN) is built for obtaining CNN ensemble. Finally, classification result for each test sample is based on the voting of all CNNS contained in the CNN ensemble."
}

@techreport{Wilkinghoff2019,
    Author = "Wilkinghoff, Kevin and Kurth, Frank",
    title = "Open-Set Acoustic Scene Classification with Deep Convolutional Autoencoders",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "Acoustic scene classification is the task of determining the environment in which a given audio file has been recorded. If it is a priori not known whether all possible environments that may be encountered during test time are also known when training the system, the task is referred to as open-set classification. This paper contains a description of an open-set acoustic scene classification system submitted to Task 1C of the Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge 2019. Our system consists of a combination of convolutional neural networks for closed-set identification and deep convolutional autoencoders for outlier detection. In evaluations conducted on the leaderboard dataset of the challenge, the proposed system significantly outperforms the baseline systems and improves the score by 35.4\% from 0.46666 to 0.63166."
}

@techreport{Wu2019,
    Author = "Wu, Yuzhong and Lee, Tan",
    title = "Stratified Time-Frequency Features for {CNN}-Based Acoustic Scene Classification",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "Acoustic scene signal is a mixture of diverse sound events, which are frequently overlapped with each other. The CNN models for acoustic scene classification usually suffer from model overfitting because they might memorize the overlapped sounds as the representative patterns for acoustic scenes, and might fail to recognize the scene when only one of the sound is present. Based on a standard CNN setup with log-Mel feature as input, we propose to stratify the log-Mel image to several component images based on sound duration, and each component image should contain a specific type of time-frequency patterns. Then we emphasize the independent modeling of time-frequency patterns to better utilize the stratified features. The experiment results on TAU Urban Acoustic Scenes 2019 development dataset [1] show that the use of stratified feature can significantly improve the classification performance."
}

@techreport{Zeinali2019,
    Author = "Zeinali, Hossein and Burget, Lukas and Cernocky, Honza",
    title = "Acoustic Scene Classification Using Fusion of Attentive Convolutional Neural Networks for Dcase2019 Challenge",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this report, the Brno University of Technology (BUT) team submissions for Task 1 (Acoustic Scene Classification, ASC) of the DCASE-2019 challenge are described. Also, the analysis of different methods is provided. The proposed approach is a fusion of three different Convolutional Neural Network (CNN) topologies. The first one is a VGG like two-dimensional CNNs. The second one is again a two-dimensional CNN network which uses MaxFeature-Map activation and called Light-CNN (LCNN). The third network is a one-dimensional CNN which mainly used for speaker verification and called x-vector topology. All proposed networks use self-attention mechanism for statistic pooling. As a feature, we use a 256-dimensional log Mel-spectrogram. Our submissions are a fusion of several networks trained on 4-folds generated evaluation setup using different fusion strategies."
}

@techreport{Zheng2019,
    Author = "Zheng, Xu and Yan, Jie",
    title = "Acoustic Scene Classification Combining Log-Mel {CNN} Model and End-To-End Model",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This technical report describes the Zheng-USTC team’s submissions for Task 1 - Subtask A (Acoustic Scene Classification, ASC) of the DCASE-2019 challenge. In this paper, two different models for Acoustic Scene Classification are provided.The first one is a common two-dimensional CNN model in which the log-mel energies spectrogram is treated as an image. The second one is an end-to-end model, in which the features of a speech are extracted by a 3-layer CNN model with 64 filters. The experimental results on the fold1 validation set of 4185 samples and the leaderboard showed that the class-wise accuracy of the two models are complementary in some way. Finally we fused the softmax ouput scores of the two different systems by using a simple non-weighted average."
}

@techreport{Zhou2019_t1,
    Author = "Zhou, Nai and Liu, Yanfang and Wei, Qingkai",
    title = "Audio Scene Calssification Based on Deeper {CNN} and Mixed Mono Channel Feature",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This technical report describes Kuaiyu team’s submissions for Task 1 - Subtask A (Acoustic Scene Classification, ASC) of the DCASE-2019 challenge. Refering the results of DCASE 2018, a convolution neural network and log-mel spectrogram generated from mono audio are used, log-mel specture is converted into multiple channels spectrogram and as a input to 8 convolutional layer neural networks. The result of our experiments is a classification system that achieves classification accuracies of around 75.5\% on the public Kaggle-Leaderboard."
}

@techreport{Zhu2019,
    Author = "Zhu, Houwei and Ren, Chunxia and Wang, Jun and Li, Shengchen and Wang, Lizhong and Yang, Lei",
    title = "{DCASE} 2019 Challenge Task1 Technical Report",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This report describe our methods for the DCASE 2019 task1a and task1c of Acoustic Scene Classification(ASC).Especially task1c for unknown scene, which not included in training data set, We use less training data and a threshold to classify the known and unknown scenes. In our method, we use Log MelSpectrogram with different divisions, as the input of multiple neural network , the ensemble learning output shows good accuracy. For task 1a we use VGG and xception as network and 3 different divisions ensemble, the accuracy is 0.807 for Leadboard dataset. For task 1c we use Convolutional Recurrent Neural Network (CRNN) and self-attention mechanism with 2 different features division ensemble, and 0.4 as threshold for unknown judgment, the Leadboard accuracy is 0.648."
}

@techreport{Zhu2019a,
    Author = "Zhu, Houwei and Ren, Chunxia and Wang, Jun and Li, Shengchen and Wang, Lizhong and Yang, Lei",
    title = "{DCASE} 2019 Challenge Task1 Technical Report",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This report describe our methods for the DCASE 2019 task1a and task1c of Acoustic Scene Classification(ASC).Especially task1c for unknown scene, which not included in training data set, We use less training data and a threshold to classify the known and unknown scenes. In our method, we use Log MelSpectrogram with different divisions, as the input of multiple neural network , the ensemble learning output shows good accuracy. For task 1a we use VGG and xception as network and 3 different divisions ensemble, the accuracy is 0.807 for Leadboard dataset. For task 1c we use Convolutional Recurrent Neural Network (CRNN) and self-attention mechanism with 2 different features division ensemble, and 0.4 as threshold for unknown judgment, the Leadboard accuracy is 0.648."
}