The development of data-driven heart sound classification models has been an active area of research in recent years. To develop such data-driven models in the first place, heart sound signals need to be captured using a signal acquisition device. However, it is almost impossible to capture noise-free heart sound signals due to the presence of internal and external noises in most situations. Such noises and degradations in heart sound signals can potentially reduce the accuracy of data-driven classification models. Although different techniques have been proposed in the literature to address the noise issue, how and to what extent different noise and degradations in heart sound signals impact the accuracy of data-driven classification models remains unexplored. To answer this question, we produced a synthetic heart sound dataset including normal and abnormal heart sounds contaminated with a large variety of noise and degradations. We used this dataset to investigate the impact of noise and degradation in heart sound recordings on the performance of different classification models. The results show different noises and degradations affect the performance of heart sound classification models to a different extent; some are more problematic for classification models, and others are less destructive. Comparing the findings of this study with the results of a survey we previously carried out with a group of clinicians shows noise and degradations that are more detrimental to classification models are also more disruptive to accurate auscultation. The findings of this study can be leveraged to develop targeted heart sound quality enhancement approaches - which adapt the type and aggressiveness of quality enhancement based on the characteristics of noise and degradation in heart sound signals.
Recently, massive architectures based on Convolutional Neural Network (CNN) and self-attention mechanisms have become necessary for audio classification. While these techniques are state-of-the-art, these works' effectiveness can only be guaranteed with huge computational costs and parameters, large amounts of data augmentation, transfer from large datasets and some other tricks. By utilizing the lightweight nature of audio, we propose an efficient network structure called Paired Inverse Pyramid Structure (PIP) and a network called Paired Inverse Pyramid Structure MLP Network (PIPMN). The PIPMN reaches 96\% of Environmental Sound Classification (ESC) accuracy on the UrbanSound8K dataset and 93.2\% of Music Genre Classification (MGC) on the GTAZN dataset, with only 1 million parameters. Both of the results are achieved without data augmentation or model transfer. Public code is available at: https://github.com/JNAIC/PIPMN
Methods based on supervised learning using annotations in an end-to-end fashion have been the state-of-the-art for classification problems. However, they may be limited in their generalization capability, especially in the low data regime. In this study, we address this issue using supervised contrastive learning combined with available metadata to solve multiple pretext tasks that learn a good representation of data. We apply our approach on respiratory sound classification. This task is suited for this setting as demographic information such as sex and age are correlated with presence of lung diseases, and learning a system that implicitly encode this information may better detect anomalies. Supervised contrastive learning is a paradigm that learns similar representations to samples sharing the same class labels and dissimilar representations to samples with different class labels. The feature extractor learned using this paradigm extract useful features from the data, and we show that it outperforms cross-entropy in classifying respiratory anomalies in two different datasets. We also show that learning representations using only metadata, without class labels, obtains similar performance as using cross entropy with those labels only. In addition, when combining class labels with metadata using multiple supervised contrastive learning, an extension of supervised contrastive learning solving an additional task of grouping patients within the same sex and age group, more informative features are learned. This work suggests the potential of using multiple metadata sources in supervised contrastive settings, in particular in settings with class imbalance and few data. Our code is released at https://github.com/ilyassmoummad/scl_icbhi2017
Recently, deep learning-based methods have drawn huge attention due to their simple yet high performance without domain knowledge in sound classification and localization tasks. However, a lack of gun sounds in existing datasets has been a major obstacle to implementing a support system to spot criminals from their gunshots by leveraging deep learning models. Since the occurrence of gunshot is rare and unpredictable, it is impractical to collect gun sounds in the real world. As an alternative, gun sounds can be obtained from an FPS game that is designed to mimic real-world warfare. The recent FPS game offers a realistic environment where we can safely collect gunshot data while simulating even dangerous situations. By exploiting the advantage of the game environment, we construct a gunshot dataset, namely BGG, for the firearm classification and gunshot localization tasks. The BGG dataset consists of 37 different types of firearms, distances, and directions between the sound source and a receiver. We carefully verify that the in-game gunshot data has sufficient information to identify the location and type of gunshots by training several sound classification and localization baselines on the BGG dataset. Afterward, we demonstrate that the accuracy of real-world firearm classification and localization tasks can be enhanced by utilizing the BGG dataset.
Recently, deep learning-based methods have drawn huge attention due to their simple yet high performance without domain knowledge in sound classification and localization tasks. However, a lack of gun sounds in existing datasets has been a major obstacle to implementing a support system to spot criminals from their gunshots by leveraging deep learning models. Since the occurrence of gunshot is rare and unpredictable, it is impractical to collect gun sounds in the real world. As an alternative, gun sounds can be obtained from an FPS game that is designed to mimic real-world warfare. The recent FPS game offers a realistic environment where we can safely collect gunshot data while simulating even dangerous situations. By exploiting the advantage of the game environment, we construct a gunshot dataset, namely BGG, for the firearm classification and gunshot localization tasks. The BGG dataset consists of 37 different types of firearms, distances, and directions between the sound source and a receiver. We carefully verify that the in-game gunshot data has sufficient information to identify the location and type of gunshots by training several sound classification and localization baselines on the BGG dataset. Afterward, we demonstrate that the accuracy of real-world firearm classification and localization tasks can be enhanced by utilizing the BGG dataset.
Automatic identification of adventitious respiratory sound has still been a challenging problem in recent years. To address this challenge, we propose an adventitious respiratory sound classification network (ARSC-Net), which combines residual block with channel-spatial attention for accurate classification. Specifically, we extract two types of features from adventitious respiratory sound, including Mel-Frequency Cepstral Coefficients (MFCCs) and Mel-spectrogram. The two types of features are entered into the parallel encoders paths with residual attention for extracting feature representation, and then fused into a channel-spatial attention module to adaptively focus on the important features between channel and spatial part for the classification task. Moreover, the channel-spatial attention can enhance the feature representation, in which the channel attention explores the inter-channel relationship of the spectrums, and then the inter-spatial correlation mapping is generated by the spatial attention introduced serially. We evaluate our proposed method on ICBHI 2017 database. Experimental results show that our proposed method achieves encouraging predictive performance with an accuracy of 80.0% for identifying abnormal sounds from normal sounds, and with an accuracy of 92.4% for distinguishing crackles from wheezes. In addition, our method also achieves a score of 56.76% for the four-class sound classification of adventitious sounds and outperforms several state-of-the-art methods.
Cough audio signal classification is a potentially useful tool in screening for respiratory disorders, such as COVID-19. Since it is dangerous to collect data from patients with such contagious diseases, many research teams have turned to crowdsourcing to quickly gather cough sound data, as it was done to generate the COUGHVID dataset. The COUGHVID dataset enlisted expert physicians to diagnose the underlying diseases present in a limited number of uploaded recordings. However, this approach suffers from potential mislabeling of the coughs, as well as notable disagreement between experts. In this work, we use a semi-supervised learning (SSL) approach to improve the labeling consistency of the COUGHVID dataset and the robustness of COVID-19 versus healthy cough sound classification. First, we leverage existing SSL expert knowledge aggregation techniques to overcome the labeling inconsistencies and sparsity in the dataset. Next, our SSL approach is used to identify a subsample of re-labeled COUGHVID audio samples that can be used to train or augment future cough classification models. The consistency of the re-labeled data is demonstrated in that it exhibits a high degree of class separability, 3x higher than that of the user-labeled data, despite the expert label inconsistency present in the original dataset. Furthermore, the spectral differences in the user-labeled audio segments are amplified in the re-labeled data, resulting in significantly different power spectral densities between healthy and COVID-19 coughs, which demonstrates both the increased consistency of the new dataset and its explainability from an acoustic perspective. Finally, we demonstrate how the re-labeled dataset can be used to train a cough classifier. This SSL approach can be used to combine the medical knowledge of several experts to improve the database consistency for any diagnostic classification task.
Recognizing patterns in lung sounds is crucial to detecting and monitoring respiratory diseases. Current techniques for analyzing respiratory sounds demand domain experts and are subject to interpretation. Hence an accurate and automatic respiratory sound classification system is desired. In this work, we took a data-driven approach to classify abnormal lung sounds. We compared the performance using three different feature extraction techniques, which are short-time Fourier transformation (STFT), Mel spectrograms, and Wav2vec, as well as three different classifiers, including pre-trained ResNet18, LightCNN, and Audio Spectrogram Transformer. Our key contributions include the bench-marking of different audio feature extractors and neural network based classifiers, and the implementation of a complete pipeline using STFT and a fine-tuned ResNet18 network. The proposed method achieved Harmonic Scores of 0.89, 0.80, 0.71, 0.36 for tasks 1-1, 1-2, 2-1 and 2-2, respectively on the testing sets in the IEEE BioCAS 2022 Grand Challenge on Respiratory Sound Classification.
Standard machine learning models for tagging and classifying acoustic signals cannot handle classes that were not seen during training. Zero-Shot (ZS) learning overcomes this restriction by predicting classes based on adaptable class descriptions. This study sets out to investigate the effectiveness of self-attention-based audio embedding architectures for ZS learning. To this end, we compare the very recent patchout spectrogram transformer with two classic convolutional architectures. We evaluate these three architectures on three tasks and on three different benchmark datasets: general-purpose tagging on AudioSet, environmental sound classification on ESC-50, and instrument tagging on OpenMIC. Our results show that the self-attention-based embedding methods outperform both compared convolutional architectures in all of these settings. By designing training and test data accordingly, we observe that prediction performance suffers significantly when the `semantic distance' between training and new test classes is large, an effect that will deserve more detailed investigations.
###Objective: Over the last few decades, there has been significant interest in the automatic analysis of respiratory sounds. However, currently there are no publicly available large databases with which new algorithms can be evaluated and compared. Further developments in the field are dependent on the creation of such databases. ###Approach: This paper describes a public respiratory sound database, which was compiled for an international competition, the first scientific challenge of the IFMBE's International Conference on Biomedical and Health Informatics. The database includes 920 recordings acquired from 126 participants and two sets of annotations. One set contains 6898 annotated respiratory cycles, some including crackles, wheezes, or a combination of both, and some with no adventitious respiratory sounds. In the other set, precise locations of 10 775 events of crackles and wheezes were annotated. ###Main results: The best system that participated in the challenge achieved an average score of 52.5% with the respiratory cycle annotations and an average score of 91.2% with the event annotations. ###Significance: The creation and public release of this database will be useful to the research community and could bring attention to the respiratory sound classification problem.
Improving access to health care services for the medically under-served population is vital to ensure that critical illness can be addressed immediately. In the scenarios where there is a severely lacking of skilled medical staff, a basic lung sound classification through a digital stethoscope can be used to provide an immediate diagnostic for respiratory-related diseases such as chronic obstructive pulmonary. In this work, we have developed an improved bi-ResNet deep learning architecture, LungBRN, which uses STFT and wavelet feature extraction techniques to mprove the accuracy compared to the state-of-the-art works. To ensure a fair evaluation, we have adopted the official benchmark standards and the “train-and-test” dataset splitting method stated in the ICBHI 2017 challenge. As a result, we are able to achieve a performance of 50.16%, which is the best result in terms of accuracy compared to all participating teams from ICBHI 2017.
Time-Frequency Distributions (TFDs) support the heart sound characterisation and classification in early cardiac screening. However, despite the frequent use of TFDs in signal analysis, no study comprehensively compared their performances on deep learning for automatic diagnosis. Furthermore, the combination of signal processing methods as inputs for Convolutional Neural Networks (CNNs) has been proved as a practical approach to increasing signal classification performance. Therefore, this study aimed to investigate the optimal use of TFD/ combined TFDs as input for CNNs. The presented results revealed that: 1) The transformation of the heart sound signal into the TF domain achieves higher classification performance than using of raw signals. Among the TFDs, the difference in the performance was slight for all the CNN models (within $1.3\%$ in average accuracy). However, Continuous wavelet transform (CWT) and Chirplet transform (CT) outperformed the rest. 2) The appropriate increase of the CNN capacity and architecture optimisation can improve the performance, while the network architecture should not be overly complicated. Based on the ResNet or SEResNet family results, the increase in the number of parameters and the depth of the structure do not improve the performance apparently. 3) Combining TFDs as CNN inputs did not significantly improve the classification results. The findings of this study provided the knowledge for selecting TFDs as CNN input and designing CNN architecture for heart sound classification.
Machine sound classification has been one of the fundamental tasks of music technology. A major branch of sound classification is the classification of music genres. However, though covering most genres of music, existing music genre datasets often do not contain fine-grained labels that indicate the detailed sub-genres of music. In consideration of the consistency of genres of songs in a mixtape or in a DJ (live) set, we have collected and annotated a dataset of house music that provide 4 sub-genre labels, namely future house, bass house, progressive house and melodic house. Experiments show that our annotations well exhibit the characteristics of different categories. Also, we have built baseline models that classify the sub-genre based on the mel-spectrograms of a track, achieving strongly competitive results. Besides, we have put forward a few application scenarios of our dataset and baseline model, with a simulated sci-fi tunnel as a short demo built and rendered in a 3D modeling software, with the colors of the lights automated by the output of our model.
Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device environmental sound classification given the restrictions on computation resources (e.g., model size, running memory). To address this issue, we propose a simple and efficient continual learning method. Our method selects the historical data for the training by measuring the per-sample classification uncertainty. Specifically, we measure the uncertainty by observing how the classification probability of data fluctuates against the parallel perturbations added to the classifier embedding. In this way, the computation cost can be significantly reduced compared with adding perturbation to the raw data. Experimental results on the DCASE 2019 Task 1 and ESC-50 dataset show that our proposed method outperforms baseline continual learning methods on classification accuracy and computational efficiency, indicating our method can efficiently and incrementally learn new classes without the catastrophic forgetting problem for on-device environmental sound classification.
While efficient architectures and a plethora of augmentations for end-to-end image classification tasks have been suggested and heavily investigated, state-of-the-art techniques for audio classifications still rely on numerous representations of the audio signal together with large architectures, fine-tuned from large datasets. By utilizing the inherited lightweight nature of audio and novel audio augmentations, we were able to present an efficient end-to-end network with strong generalization ability. Experiments on a variety of sound classification sets demonstrate the effectiveness and robustness of our approach, by achieving state-of-the-art results in various settings. Public code is available at: \href{https://github.com/Alibaba-MIIL/AudioClassfication}{this http url}
Heart sound diagnosis and classification play an essential role in detecting cardiovascular disorders, especially when the remote diagnosis becomes standard clinical practice. Most of the current work is designed for single category based heard sound classification tasks. To further extend the landscape of the automatic heart sound diagnosis landscape, this work proposes a deep multilabel learning model that can automatically annotate heart sound recordings with labels from different label groups, including murmur's timing, pitch, grading, quality, and shape. Our experiment results show that the proposed method has achieved outstanding performance on the holdout data for the multi-labelling task with sensitivity=0.990, specificity=0.999, F1=0.990 at the segments level, and an overall accuracy=0.969 at the patient's recording level.
Respiratory sound classification is an important tool for remote screening of respiratory-related diseases such as pneumonia, asthma, and COVID-19. To facilitate the interpretability of classification results, especially ones based on deep learning, many explanation methods have been proposed using prototypes. However, existing explanation techniques often assume that the data is non-biased and the prediction results can be explained by a set of prototypical examples. In this work, we develop a unified example-based explanation method for selecting both representative data (prototypes) and outliers (criticisms). In particular, we propose a novel application of adversarial attacks to generate an explanation spectrum of data instances via an iterative fast gradient sign method. Such unified explanation can avoid over-generalisation and bias by allowing human experts to assess the model mistakes case by case. We performed a wide range of quantitative and qualitative evaluations to show that our approach generates effective and understandable explanation and is robust with many deep learning models
Outsourced training and machine learning as a service have resulted in novel attack vectors like backdoor attacks. Such attacks embed a secret functionality in a neural network activated when the trigger is added to its input. In most works in the literature, the trigger is static, both in terms of location and pattern. The effectiveness of various detection mechanisms depends on this property. It was recently shown that countermeasures in image classification, like Neural Cleanse and ABS, could be bypassed with dynamic triggers that are effective regardless of their pattern and location. Still, such backdoors are demanding as they require a large percentage of poisoned training data. In this work, we are the first to show that dynamic backdoor attacks could happen due to a global average pooling layer without increasing the percentage of the poisoned training data. Nevertheless, our experiments in sound classification, text sentiment analysis, and image classification show this to be very difficult in practice.
Audio classification is an important task of mapping audio samples into their corresponding labels. Recently, the transformer model with self-attention mechanisms has been adopted in this field. However, existing audio transformers require large GPU memories and long training time, meanwhile relying on pretrained vision models to achieve high performance, which limits the model's scalability in audio tasks. To combat these problems, we introduce HTS-AT: an audio transformer with a hierarchical structure to reduce the model size and training time. It is further combined with a token-semantic module to map final outputs into class featuremaps, thus enabling the model for the audio event detection (i.e. localization in time). We evaluate HTS-AT on three datasets of audio classification where it achieves new state-of-the-art (SOTA) results on AudioSet and ESC-50, and equals the SOTA on Speech Command V2. It also achieves better performance in event localization than the previous CNN-based models. Moreover, HTS-AT requires only 35% model parameters and 15% training time of the previous audio transformer. These results demonstrate the high performance and high efficiency of HTS-AT.
The issue in respiratory sound classification has attained good attention from the clinical scientists and medical researcher's group in the last year to diagnosing COVID-19 disease. To date, various models of Artificial Intelligence (AI) entered into the real-world to detect the COVID-19 disease from human-generated sounds such as voice/speech, cough, and breath. The Convolutional Neural Network (CNN) model is implemented for solving a lot of real-world problems on machines based on Artificial Intelligence (AI). In this context, one dimension (1D) CNN is suggested and implemented to diagnose respiratory diseases of COVID-19 from human respiratory sounds such as a voice, cough, and breath. An augmentation-based mechanism is applied to improve the preprocessing performance of the COVID-19 sounds dataset and to automate COVID-19 disease diagnosis using the 1D convolutional network. Furthermore, a DDAE (Data De-noising Auto Encoder) technique is used to generate deep sound features such as the input function to the 1D CNN instead of adopting the standard input of MFCC (Mel-frequency cepstral coefficient), and it is performed better accuracy and performance than previous models.