Enhancing Sound Texture in CNN-based Acoustic Scene Classification

In Acoustic Scene Classification (ASC) two major approaches have been followed. While one utilizes engineered features such as mel-frequency-cepstral-coefficients (MFCCs), the other uses learned features that are the outcome of an optimization algorithm. I-vectors are the result of a modeling technique that usually takes engineered features as input. It has been shown that standard MFCCs extracted from monaural audio signals lead to i-vectors that exhibit poor performance, especially on indoor acoustic scenes. At the same time, Convolutional Neural Networks (CNNs) are well known for their ability to learn features by optimizing their filters. They have been applied on ASC and have shown promising results. In this paper, we first propose a novel multi-channel i-vector extraction and scoring scheme for ASC, improving their performance on indoor and outdoor scenes. Second, we propose a CNN architecture that achieves promising ASC results. Further, we show that i-vectors and CNNs capture complementary information from acoustic scenes. Finally, we propose a hybrid system for ASC using multi-channel i-vectors and CNNs by utilizing a score fusion technique. Using our method, we participated in the ASC task of the DCASE-2016 challenge. Our hybrid approach achieved 1st rank among 49 submissions, substantially improving the previous state of the art.

Understanding the learning mechanism of convolutional neural networks in spectral analysis

Hierarchical classification for acoustic scenes using deep learning

Identification of crops is an important topic in the agricultural domain. Hyperspectral remote sensing data are very useful for crop feature extraction and classification. Remote sensing data is an unstructured data and Convolutional Neural Network (CNN) can work on unstructured data efficiently. This paper presents an evaluation of CNN for crop classification using the Indian Pines standard dataset obtained from the AVIRIS sensor and the study area dataset obtained from the EO-1hyperion sensor. Optimized CNN has been tuned by training the model on different parameters. It has been compared with two classification algorithms: Deep Neural Network (DNN) and Convolutional Autoencoder. According to the test results, the proposed optimized CNN model provided better results as compared to the other two methods. CNN has given 97 ± 0.58% overall accuracy for the Indian Pines standard dataset and 78 ± 2.43% for our study area dataset.

Covid-19 first occurred in Wuhan, China in December 2019. Subsequently, the virus spread throughout the world and as of June 2020 the total number of confirmed cases are above 4.7 million with over 315,000 deaths. Machine learning algorithms built on radiography images can be used as a decision support mechanism to aid radiologists to speed up the diagnostic process. The aim of this work is to conduct a critical analysis to investigate the applicability of convolutional neural networks (CNNs) for the purpose of COVID-19 detection in chest X-ray images and highlight the issues of using CNN directly on the whole image. To accomplish this task, we use 12-off-the-shelf CNN architectures in transfer learning mode on 3 publicly available chest X-ray databases together with proposing a shallow CNN architecture in which we train it from scratch. Chest X-ray images are fed into CNN models without any preprocessing to replicate researches used chest X-rays in this manner. Then a qualitative investigation performed to inspect the decisions made by CNNs using a technique known as class activation maps (CAM). Using CAMs, one can map the activations contributed to the decision of CNNs back to the original image to visualize the most discriminating region(s) on the input image. We conclude that CNN decisions should not be taken into consideration, despite their high classification accuracy, until clinicians can visually inspect and approve the region(s) of the input image used by CNNs that lead to its prediction.

Acoustic scene classification and related tasks have been dominated by Convolutional Neural Networks (CNNs). Top-performing CNNs use mainly audio spectograms as input and borrow their architectural design primarily from computer vision. A recent study has shown that restricting the receptive field (RF) of CNNs in appropriate ways is crucial for their performance, robustness and generalization in audio tasks. One side effect of restricting the RF of CNNs is that more frequency information is lost. In this paper, we perform a systematic investigation of different RF configuration for various CNN architectures on the DCASE 2019 Task 1.A dataset. Second, we introduce Frequency Aware CNNs to compensate for the lack of frequency information caused by the restricted RF, and experimentally determine if and in what RF ranges they yield additional improvement. The result of these investigations are several well-performing submissions to different tasks in the DCASE 2019 Challenge.

This paper works on the idea of integrating the acoustic scene classification technique in active noise control (ANC), whereby the major difficulty lies in the limited dataset available from an ANC system in use. A large-scale acoustic scene dataset recorded by a different acoustic device has to be considered. This leads to the research problem of acoustic scene classification by mismatched devices. Hence, an ensemble of the convolutional neural networks (CNNs) is demonstrated with a novel data augmentation method. Monaural samples are processed by the head-related transfer functions (HRTFs) of 24 azimuths to add in the artificial spatial information. Every two symmetrical azimuths are then paired together to provide a tempo-spectral feature consisting of 4 channels. 12 CNNs are trained with respective features. Finally, different ensemble strategies are carried out and their classification accuracies are compared. When the random forest is used as the meta-learner, the ensemble of CNNs achieves the best classification accuracy of 65.1% over 10 acoustic scenes.

Acoustic scene classification (ASC) is a problem related to the field of machine listening whose objective is to classify/tag an audio clip in a predefined label describing a scene location (e. g. park, airport, etc.). Many state-of-the-art solutions to ASC incorporate data augmentation techniques and model ensembles. However, considerable improvements can also be achieved only by modifying the architecture of convolutional neural networks (CNNs). In this work we propose two novel squeeze-excitation blocks to improve the accuracy of a CNN-based ASC framework based on residual learning. The main idea of squeeze-excitation blocks is to learn spatial and channel-wise feature maps independently instead of jointly as standard CNNs do. This is usually achieved by some global grouping operators, linear operators and a final calibration between the input of the block and its obtained relationships. The behavior of the block that implements such operators and, therefore, the entire neural network, can be modified depending on the input to the block, the established residual configurations and the selected non-linear activations. The analysis has been carried out using the TAU Urban Acoustic Scenes 2019 dataset (https://zenodo.org/record/2589280) presented in the 2019 edition of the DCASE challenge. All configurations discussed in this document exceed the performance of the baseline proposed by the DCASE organization by 13\% percentage points. In turn, the novel configurations proposed in this paper outperform the residual configurations proposed in previous works.

Frequency-based CNN and attention module for acoustic scene classification

Late fusion framework for Acoustic Scene Classification using LPCC, SCMC, and log-Mel band energies with Deep Neural Networks

The goal of acoustic scene classification (ASC) is to automatically classify the environment based on an audio recording of the situation. It has become a significant but difficult issue in audio processing, allowing for a vast variety of successive applications such as security, social care, and context-aware facilities. Recently, Convolutional Neural Networks (CNNs) have been broadly applied to speech audio classification, yielding promising results. In this paper, we have extracted four types of acoustic features i.e., Mel-Frequency Cepstral Coefficients (MFCCs), Linear Predictive Coding (LPC), Zero-crossing-rate (ZCR) and root mean square value (RMSV) value from audio signals for automatic scene classification. We have used Litis Rouen Dataset for CNN model training and testing. Experimental results show that the proposed method has achieved a significant accuracy of 84.15% on the Litis Rouen Dataset. Moreover, we have also compared the performance of the proposed method with other ASC techniques used in the literature.

Visual attention mechanism has been widely used in computer vision and plays a vital role in the research of human action recognition. In this paper, we explore a novel moving target detection mechanism for human action recognition and propose a new 3D CNN (3D Convolutional Neural Network) model, dubbed LaM-2SRN (Local Features Enhanced and Moving target detected 2Stream-ResNet) for extracting and learning attention-enhanced spatiotemporal features. The contributions of this paper are as follow: First, the traditional CAM (Class Activation Map) based visual attention algorithm is used to obtain the optical flow information of the human region, thus eliminating the influence of irrelevant optical flow information (such as background clutter). Second, the ViBe algorithm is used to identify the moving target in the continuous frame, retain the optical flow information of the moving target, and make it complement with the optical flow information of the human region, to obtain a complete motion descriptor. After the motion information is marked in the video frame, we put the marked video frames and the original video frames into the 3D CNN and 2D CNN models respectively, to acquired mixed descriptor, which serves as the basis for video classification. Different from most of the previous target detection algorithms, this paper not only detects the human target, but also detects the moving foreground targets in the video, so that the pre-trained CNN model can obtain more complete motion information from videos. We use RGB-only video data for evaluation on two benchmarks: UCF101 and HMDB51, the experimental results demonstrate that our LaM-2SRN is comparable to the previous state-of-the-art algorithms.

Deep convolutional neural networks (DCNNs) for diagnosis of disease on chest radiographs (CXR) have been shown to be biased against males or females if the datasets used to train them have unbalanced sex representation. Prior work has suggested that DCNNs can predict sex on CXR, which could aid forensic evaluations, but also be a source of bias. To (1) evaluate the performance of DCNNs for predicting sex across different datasets and architectures and (2) evaluate visual biomarkers used by DCNNs to predict sex on CXRs. Chest radiographs were obtained from the Stanford CheXPert and NIH Chest XRay14 datasets which comprised of 224,316 and 112,120 CXRs, respectively. To control for dataset size and class imbalance, random undersampling was used to reduce each dataset to 97,560 images that were balanced for sex. Each dataset was randomly split into training (70%), validation (10%), and test (20%) sets. Four DCNN architectures pre-trained on ImageNet were used for transfer learning. DCNNs were externally validated using a test set from the opposing dataset. Performance was evaluated using area under the receiver operating characteristic curve (AUC). Class activation mapping (CAM) was used to generate heatmaps visualizing the regions contributing to the DCNN's prediction. On the internal test set, DCNNs achieved AUROCs ranging from 0.98 to 0.99. On external validation, the models reached peak cross-dataset performance of 0.94 for the VGG19-Stanford model and 0.95 for the InceptionV3-NIH model. Heatmaps highlighted similar regions of attention between model architectures and datasets, localizing to the mediastinal and upper rib regions, as well as to the lower chest/diaphragmatic regions. DCNNs trained on two large CXR datasets accurately predicted sex on internal and external test data with similar heatmap localizations across DCNN architectures and datasets. These findings support the notion that DCNNs can leverage imaging biomarkers to predict sex and potentially confound the accurate prediction of disease on CXRs and contribute to biased models. On the other hand, these DCNNs can be beneficial to emergency radiologists for forensic evaluations and identifying patient sex for patients whose identities are unknown, such as in acute trauma.

Emotions expressed by humans can be identified from facial expressions, speech signals, or physiological signals. Among them, the use of physiological signals for emotion classification is a notable emerging area of research. In emotion recognition, a person’s electrocardiogram (ECG) and galvanic skin response (GSR) signals cannot be manipulated, unlike facial and voice signals. Moreover, wearables such as smartwatches and wristbands enable the detection of emotions in people’s naturalistic environment. During the COVID-19 pandemic, it was necessary to detect people’s emotions in order to ensure that appropriate actions were taken according to the prevailing situation and achieve societal balance. Experimentally, the duration of the emotion stimulus period and the social and non-social contexts of participants influence the emotion classification process. Hence, classification of emotions when participants are exposed to the elicitation process for a longer duration and taking into consideration the social context needs to be explored. This work explores the classification of emotions using five pretrained convolutional neural network (CNN) models: MobileNet, NASNetMobile, DenseNet 201, InceptionResnetV2, and EfficientNetB7. The continuous wavelet transform (CWT) coefficients were detected from ECG and GSR recordings from the AMIGOS database with suitable filtering. Scalograms of the sum of frequency coefficients versus time were obtained and converted into images. Emotions were classified using the pre-trained CNN models. The valence and arousal emotion classification accuracy obtained using ECG and GSR data were, respectively, 91.27% and 91.45% using the InceptionResnetV2 CNN classifier and 99.19% and 98.39% using the MobileNet CNN classifier. Other studies have not explored the use of scalograms to represent ECG and GSR CWT features for emotion classification using deep learning models. Additionally, this study provides a novel classification of emotions built on individual and group settings using ECG data. When the participants watched long-duration emotion elicitation videos individually and in groups, the accuracy was around 99.8%. MobileNet had the highest accuracy and shortest execution time. These subject-independent classification methods enable emotion classification independent of varying human behavior.

The mango leaf powdery mildew disease poses a serious threat to mango production society globally by significantly lowering yield and quality. For timely intervention and efficient management, early disease detection and classification are important. In this research and education area, a novel hybrid approach utilizes Convolutional Neural Networks (CNN) and Support Vector Machines to identify the mango leaf powdery mildew disease based on four severity levels (SVM). Three phases make up the proposed approach: data structure, CNN-selected attributes, and SVM classification. We collect and preprocess images of mango leaves during the data organization step, and in the CNN - attributes selection phase, we apply a CNN model for feature extraction and selection. For the mango leaf powdery mildew dataset, we improve the CNN model to find the most relevant features for the classification task. The SVM - classification step includes training an SVM model on the obtained features and refining the hyperparameters via k-fold cross-validation. The proposed CNN and SVM hybrid multi-classification model for mango leaf powdery mildew disease achieved an overall accuracy of 89.29%. A dataset of 2559 images with 4 severity levels was utilized. The model works well overall, as a macro-average F1-score of 90.10, the weighted average F1-score's minimal value of 53.85%. The model is less successful in predicting instances for classes with smaller support proportions, as shown by the micro-average F1-score, which is 89.29% and is lower overall than the macro-average F1-score.