Sound Recognition Research Articles

Audio Recognition of the Percussion Sounds Generated by a 3D Auto-Drum Machine System via Machine Learning

Audio Recognition of the Percussion Sounds Generated by a 3D Auto-Drum Machine System via Machine Learning

Sound classification with time-frequency features in forest environment

The study of forest sound classification has drawn more attention recently due to its potential for illegal activities and natural disaster monitoring. Based on the forest sound classification dataset (FSC22), a dataset specific to possible sound existing in the forest, five classification methods are utilized to investigate the relationship between recognition accuracy and the number of sound acoustic features, as well as the number of target classes. The results confirmed that extreme random forest is the best method for forest sound classification, with an accuracy of around 70% when the target class number is above 20. Further, Mel-frequency cepstral coefficients are the critical feature for sound classification, while fuzzy labels in the dataset may reduce the success rate of recognition.

An open auscultation dataset for machine learning-based respiratory diagnosis studies.

Machine learning enabled auscultating diagnosis can provide promising solutions especially for prescreening purposes. The bottleneck for its potential success is that high-quality datasets for training are still scarce. An open auscultation dataset that consists of samples and annotations from patients and healthy individuals is established in this work for the respiratory diagnosis studies with machine learning, which is of both scientific importance and practical potential. A machine learning approach is examined to showcase the use of this new dataset for lung sound classifications with different diseases. The open dataset is available to the public online.

Incremental Fuzzy Clustering-Based Neural Networks Driven With the Aid of Dynamic Input Space Partition and Quasi-Fuzzy Local Models.

Fuzzy clustering-based neural networks (FCNNs) based on information granulation techniques have been shown to be effective Takagi-Sugeno (TS)-type fuzzy models. However, the existing FCNNs could not cope well with sequential learning tasks. In this study, we introduce incremental FCNNs (IFCNNs), which could dynamically update themselves whenever new learning data (e.g., single datum or block data) are incorporated into the dataset. Specifically, we employ dynamic (incremental) fuzzy C-means (FCMs) clustering algorithms to reveal a structure in data and divide the entire input space into several subregions. In the aforementioned partition, the dynamic FCM adaptively adjusts the position of its prototypes by using sequential data. Due to the time-sharing arrival of training data, compared with batch learning models, incremental learning methods may lose classification (prediction) accuracy. In order to tackle this challenge, we utilize quasi-fuzzy local models (QFLMs) based on modified Schmidt neural networks to replace the popular linear functions in TS-type fuzzy models to refine and enhance the ability to represent the behavior of fuzzy subspaces. Meanwhile, the recursive least square error (LSE) estimation is utilized to update the weights of QFLMs from one-by-one or block-by-block (fixed or varying block size) learning data. In addition, the L2 regularization is considered to ameliorate the deterioration of generalization abilities caused by potential overfitting when carrying out weight estimation. The proposed method leads to the construction of FCNNs in a new way, which can effectively deal with incremental data as well as deliver sound generalization capability. Extensive machine-learning datasets and a real-world application are employed to show the validity and performance of the presented methods. From the experimental results, we show that the proposal can maintain sound classification accuracy when effectively processing sequential data.

Exploring an Intelligent Classification Model for the Recognition of Automobile Sounds Based on EEG Physiological Signals

The advancement of an intelligent automobile sound switching system has the potential to elevate the market standing of automotive products, with the pivotal prerequisite being the selection of automobile sounds based on the driver’s subjective perception. The subjective responses of diverse individuals to sounds can be objectively manifested through EEG signals. Therefore, EEG signals are employed herein to attain the recognition of automobile sounds. A subjective evaluation and EEG signal acquisition experiment are designed involving the stimulation of three distinct types of automobile sounds, namely comfort, power, and technology sounds, and a comprehensive database of EEG signals corresponding to these three sound qualities is established. Then, a specific transfer learning model based on a convolutional neural network (STL-CNN) is formulated, where the method of training the upper layer parameters with the fixed bottom weights is proposed to adaptively extract the EEG features related to automobile sounds. These improvements contribute to improving the generalization ability of the model and realizing the recognition of automobile sounds fused with EEG signals. The results of the comparison with traditional support vector machine (SVM) and convolutional neural network (CNN) models demonstrate that the accuracy of the test set of the STL-CNN model reaches 91.5%. Moreover, its comprehensive performance, coupled with the ability to adapt to individual differences, surpasses that of both SVM and CNN models. The demonstrated method in the recognition of automobile sounds based on EEG signals is of significance for the future implementation of switching driving sound modes fused with EEG signals.

Lightweight network based features fusion for steel rolling ambient sound classification

With the intelligent development of industrial production, sound monitoring technology has been widely used to monitor the operation status of mechanical facilities, and this progress has gradually become a research hotspot in the steel manufacturing industry. However, the complex composition of sound sources and the high computational requirements of most models limit their applicability to industrial scenarios. This work presents a targeted approach for remote monitoring of rolling sound. They are using visual features of audio signals to design classification models on the self-harvested dataset for more efficient adaptation to complex production sites. An in-depth analysis of the actual sound reveals that it is characterized by high similarity, complexity, and partial synchronization. To optimize interclass and intraclass data engineering few-sample, multi-feature fusion, and data augmentation methods were combined to characterize the details fully. In addition, by leveraging the deep small convolutions of VGGNet and the randomness of stochastic pooling, local features are effectively extracted. Finally, global average pooling with final softmax layer stacking is used to classify the rolling signals to reduce the number of parameters, avoid overfitting, and perform a global analysis of the features. Experimental results on the rolling sound dataset show that the method proposed achieves an accuracy of 91.26%, with 92.66%, and 95.88% on the ESC10 and MIMII datasets, respectively. These results confirm that the method can be widely applied to sound classification for multi-category rolling processes, showing good performance and scalability.

Proposed CNN Model for Audio Recognition on Embedded Device

The audio detection system enables autonomous cars to recognize their surroundings based on the noise produced by moving vehicles. This paper proposes the utilization of a machine learning model based on convolutional neural networks (CNN) integrated into an embedded system supported by a microphone. The system includes a specialized microphone and a main processor. The microphone enables the transmission of an accurate analog signal to the main processor, which then analyzes the recorded signal and provides a prediction in return. While designing an adequate hardware system is a crucial task that directly impacts the predictive capability of the system, it is equally imperative to train a CNN model with high accuracy. To achieve this goal, a dataset containing over 3000 up-to-5-second WAV files for four classes was obtained from open-source research. The dataset is then divided into training, validation, and testing sets. The training data is converted into images using the spectrogram technique before training the CNN. Finally, the generated model is tested on the testing segment, resulting in a model accuracy of 77.54%.

Leveraging AI and Machine Learning to Develop and Evaluate a Contextualized User-Friendly Cough Audio Classifier for Detecting Respiratory Diseases: Protocol for a Diagnostic Study in Rural Tanzania.

Respiratory diseases, including active tuberculosis (TB), asthma, and chronic obstructive pulmonary disease (COPD), constitute substantial global health challenges, necessitating timely and accurate diagnosis for effective treatment and management. This research seeks to develop and evaluate a noninvasive user-friendly artificial intelligence (AI)-powered cough audio classifier for detecting these respiratory conditions in rural Tanzania. This is a nonexperimental cross-sectional research with the primary objective of collection and analysis of cough sounds from patients with active TB, asthma, and COPD in outpatient clinics to generate and evaluate a noninvasive cough audio classifier. Specialized cough sound recording devices, designed to be nonintrusive and user-friendly, will facilitate the collection of diverse cough sound samples from patients attending outpatient clinics in 20 health care facilities in the Shinyanga region. The collected cough sound data will undergo rigorous analysis, using advanced AI signal processing and machine learning techniques. By comparing acoustic features and patterns associated with TB, asthma, and COPD, a robust algorithm capable of automated disease discrimination will be generated facilitating the development of a smartphone-based cough sound classifier. The classifier will be evaluated against the calculated reference standards including clinical assessments, sputum smear, GeneXpert, chest x-ray, culture and sensitivity, spirometry and peak expiratory flow, and sensitivity and predictive values. This research represents a vital step toward enhancing the diagnostic capabilities available in outpatient clinics, with the potential to revolutionize the field of respiratory disease diagnosis. Findings from the 4 phases of the study will be presented as descriptions supported by relevant images, tables, and figures. The anticipated outcome of this research is the creation of a reliable, noninvasive diagnostic cough classifier that empowers health care professionals and patients themselves to identify and differentiate these respiratory diseases based on cough sound patterns. Cough sound classifiers use advanced technology for early detection and management of respiratory conditions, offering a less invasive and more efficient alternative to traditional diagnostics. This technology promises to ease public health burdens, improve patient outcomes, and enhance health care access in under-resourced areas, potentially transforming respiratory disease management globally. PRR1-10.2196/54388.

Broiler sound signal filtering method based on improved wavelet denoising and effective pulse extraction

There is little attention paid to signal filtering in existing broiler health monitoring or broiler sound signal classification research, and the only few studies still have issues such as lack of specific, in-depth, and specialized details. In response to these problems, the authors conducted a depth analysis of the signal characteristics of effective signal components and noises, and proposed a broiler sound signal filtering method based on improved wavelet denoising and effective pulse extraction. This method consists of two parts. The first part is wavelet denoising, which is used to remove the widely distributed noises in broiler sound signals. Specifically, a wavelet denoising algorithm based on continuous differentiable threshold function and scale threshold has been proposed. The disadvantages in existing hard threshold function, soft threshold function, and semi-soft threshold function have been effectively addressed, and the smoothness of broiler sound signals has been ensured. The second part is pulse extraction processing, which is used to remove sudden noises that appears as independent pulses in broiler sound signals. Specifically, a two-stage variable multi-threshold pulse extraction algorithm has been proposed. The main advantages of existing three-threshold pulse extraction algorithm and double-threshold pulse extraction algorithm have been referenced, the threshold setting standard has been clarified, the continuous multi-pulse problem has been given special attention, and the effective signal components in broiler sound signals have been accurately extracted. In this way, the noises in broiler sound signals were removed, and the effective signal components were highlighted. The signal-to-noise ratio (SNR) and root mean square error (RMSE) from signal detection field, as well as the classification accuracy and F1-score from machine learning field, were used to comprehensively evaluate the effect of the signal filtering method proposed in this paper. A large number of tests shown that, compared to existing signal filtering methods, the broiler sound signal processed by the signal filtering method proposed in this paper achieved the maximum SNR and the minimum RMSE. On feature data sets created from broiler sound signals processed by different signal filtering methods, three classifiers all achieved the highest classification accuracy and F1-score on the feature data set corresponding to the signal filtering method proposed in this paper. The feasibility, practicality, and superiority of the signal filtering method proposed in this paper have been widely verified. This study is an important supplement to the broiler health monitoring and broiler sound signal classification research, providing important references for signal filtering research in similar fields.

Formatted Sound

Formatted Sound

Approaches for Respiratory Sound Analysis in Identification of Respiratory Diseases

Purpose: Medical professionals throughout the world prefer to use conventional stethoscopes to listen to respiratory sounds. Listening to respiratory sounds through stethoscopes is a subjective matter, and proper diagnosis of the disease depends on the skills and ability of the doctor. Computerized analysis of respiratory sounds can help doctors and researchers to characterize different abnormal respiratory patterns and make informed decisions.
 Materials and Methods: This study includes previously reported work in different normal and abnormal respiratory sounds. The IEEE, PubMed, Google Scholar and Elsevier databases were searched and studies with the keywords of lung sound analysis, respiratory sound analysis, and respiratory sound classification were included. Detailed characteristics of normal and abnormal respiratory sounds are mentioned. In addition, Time-amplitude characteristics of different respiratory sound plots are obtained using MATLAB and ICBHI database. This study systematically discusses different approaches for respiratory sound analysis like visual analysis of the time-amplitude signals, frequency analysis, and spectral analysis using fast Fourier transform, statistical analysis, and machine learning approach. A list of relevant datasets is mentioned that can help researchers to do further analysis in this domain.
 Results: The careful observations and analysis show the possibility of predicting respiratory diseases by extracting suitable parameters such as the frequency response and spectral characteristics of the signal. Power spectral density can help us to calculate the maximum, median frequency over an extended period. Using machine learning we can estimate the energy, entropy, spectral features, and wavelets of the signals.
 Conclusion: Computer-based respiratory sound analysis can help medical professionals in making informed decisions. This will help in early diagnosis and devise effective treatment plans for the patients.

Synchronous Sound Recognition and Energy Harvesting by Flexible Piezoelectric PLLA/VB2 Composites.

In the present study, poling-free PLLA/VB2 piezoelectric composites are fabricated to achieve synchronous sound recognition and energy harvesting. The addition of VB2 can interact with PLLA by intermolecular hydrogen bonding, inducing the dipole orientation of C=O in PLLA. Meanwhile, VB2 can promote crystallization of PLLA through heterogeneous nucleation. The combination of the two strategies significantly improves the piezoelectric performance of PLLA/VB2 composites. The PLLA/VB2 can detect the sound frequency with an accuracy of 0.1% in the range of 0-20 kHz to recognize characteristic sounds from a specific source. PLLA/VB2 can also convert sound into electrical energy synchronously with an energy density of 0.2 W/cm-3 to power up LEDs. Therefore, PLLA/VB2 shows great potential in the field of information and energy synchronous collection.

Enhancing Insect Sound Classification Using Dual-Tower Network: A Fusion of Temporal and Spectral Feature Perception

In the modern field of biological pest control, especially in the realm of insect population monitoring, deep learning methods have made further advancements. However, due to the small size and elusive nature of insects, visual detection is often impractical. In this context, the recognition of insect sound features becomes crucial. In our study, we introduce a classification module called the “dual-frequency and spectral fusion module (DFSM)”, which enhances the performance of transfer learning models in audio classification tasks. Our approach combines the efficiency of EfficientNet with the hierarchical design of the Dual Towers, drawing inspiration from the way the insect neural system processes sound signals. This enables our model to effectively capture spectral features in insect sounds and form multiscale perceptions through inter-tower skip connections. Through detailed qualitative and quantitative evaluations, as well as comparisons with leading traditional insect sound recognition methods, we demonstrate the advantages of our approach in the field of insect sound classification. Our method achieves an accuracy of 80.26% on InsectSet32, surpassing existing state-of-the-art models by 3 percentage points. Additionally, we conducted generalization experiments using three classic audio datasets. The results indicate that DFSM exhibits strong robustness and wide applicability, with minimal performance variations even when handling different input features.

Identifying pediatric heart murmurs and distinguishing innocent from pathologic using deep learning

ObjectiveTo develop a deep learning algorithm to perform multi-class classification of normal pediatric heart sounds, innocent murmurs, and pathologic murmurs. MethodsWe prospectively enrolled children under age 18 being evaluated by the Division of Pediatric Cardiology. Parents provided consent for a deidentified recording of their child's heart sounds with a digital stethoscope. Innocent murmurs were validated by a pediatric cardiologist and pathologic murmurs were validated by echocardiogram. To augment our collection of normal heart sounds, we utilized a public database of pediatric heart sound recordings (Oliveira, 2022). We propose two novel approaches for this audio classification task. We train a vision transformer on either Markov transition field or Gramian angular field image representations of the frequency spectrum. We benchmark our results against a ResNet-50 CNN trained on spectrogram images. ResultsOur final dataset consisted of 366 normal heart sounds, 175 innocent murmurs, and 216 pathologic murmurs. Innocent murmurs collected include Still's murmur, venous hum, and flow murmurs. Pathologic murmurs included ventricular septal defect, tetralogy of Fallot, aortic regurgitation, aortic stenosis, pulmonary stenosis, mitral regurgitation and stenosis, and tricuspid regurgitation. We find that the Vision Transformer consistently outperforms the ResNet-50 on all three image representations, and that the Gramian angular field is the superior image representation for pediatric heart sounds. We calculated a one-vs-rest multi-class ROC curve for each of the three classes. Our best model achieves an area under the curve (AUC) value of 0.92 ± 0.05, 0.83 ± 0.04, and 0.88 ± 0.04 for identifying normal heart sounds, innocent murmurs, and pathologic murmurs, respectively. ConclusionWe present two novel methods for pediatric heart sound classification, which outperforms the current standard of using a convolutional neural network trained on spectrogram images. To our knowledge, we are the first to demonstrate multi-class classification of pediatric murmurs. Multiclass output affords a more explainable and interpretable model, which can facilitate further model improvement in the downstream model development cycle and enhance clinician trust and therefore adoption.

Modification of an Airway Training Mannequin to Teach Engagement of the Hyoepiglottic Ligament.

This airway trainer modification is designed to instruct all levels of training in emergency medicine in order to familiarize trainees with airway anatomy and obtain superior views of the glottic inlet. During intubation with a standard geometry laryngoscope, such as the Macintosh blade, placement of the distal end of the blade within the vallecula and engagement of the median glossoepiglottic fold, also referred to as the midline vallecular fold (MVF), has long been championed by experts in airway management for its ability to improve glottic inlet visualization. This notion was further supported by the recent publication of a retrospective video review by Driver et al.1 Unfortunately, airway anatomy, including engagement of the MVF, does not receive the emphasis it deserves during intubation training of emergency medicine residents. Emergency physicians often have limited time to perform complete airway examinations, but a sound recognition and appreciation of the laryngeal inlet can serve as a roadmap to optimal laryngoscopy.2Recent advancements in airway education emphasize visualization of airway anatomy with review of video laryngoscopy (VL) recordings to identify routine VL errors in vallecula manipulation, such as failure to engage the MVF. 3 Simulation can continue to play an essential role in enhancing trainees' airway skills. Current airway trainers lack functional fidelity components, such an engageable MVF, resulting in a missed opportunity to teach airway skills and anatomy in a safe and controlled setting.4, 5 To address these concerns, we modified an existing airway task trainer with the addition of a simulated MVF to expose trainees to airway anatomy and adequate MVF engagement resulting in epiglottic elevation. By the end of this education session, participants should be able to:Identify relevant airway anatomy during intubation, including base of the tongue, epiglottis, midline vallecular fold, anterior arytenoids.Appreciate the value of a stepwise anatomically guided approach to intubation.Become familiar with the midline vallecular fold and underlying anatomy, including the hyoepiglottic ligament, and how proper placement of the laryngoscope can result in improved glottic visualization. The TrueCorp AirSim airway task trainer was modified with the addition of a simulated MVF. Prior to the modification described here, there were no dynamic trainers with the functional fidelity needed to teach trainees how to engage the MVF with proper placement of the distal tip of the laryngoscope. Once the trainer was created, learners are introduced to relevant anatomy through the initial lecture to unsure baseline knowledge. During the lecture, videos and images are reviewed to demonstrate the importance of an anatomical roadmap to successful intubation. Learners then practiced with the modified task trainer to gain hands-on experience with laryngoscope placement and improved glottic visualization. A short verbal debriefing was performed at the end of the skills session to address any remaining questions. Pre- and post-simulation surveys were completed by attendees of a weekly didactic session, ranging from medical students, PGY 1-4 emergency medicine residents, and emergency medicine attending physicians. Pre- and post-simulation familiarity with airway anatomy and comfortability with MVF engagement was assessed using a 5-point Likert scale. Twenty-six participants ranging from medical students to attending physicians completed a pre- and post-simulation survey. Overall, feedback from leaners was positive. Learners were excited to learn new airway management techniques and requested an expansion of current airway curriculum based on the success of this implementation. This modified task trainer places an emphasis on teaching airway anatomy to trainees with the addition of functional fidelity by adding an engageable element providing the trainee with feedback on successful placement of the laryngoscope. This simple and cost-effective modification can add value to existing airway management curriculums by serving as a visual cue of airway anatomy and instructing trainees on proper placement of the laryngoscope. Our results showed participants experienced increased comfort with airway anatomy recognition and engagement of MVF for difficult intubations. Participants found the trainer effective with the simulated MVF resulting in glottic elevation and recommended this for future simulation. Participants were eager to learn additional airway techniques to improve their laryngoscopy skills, suggesting an area of growth for emergency medicine didactic curriculums. Airway, midline vallecular fold, anatomy, difficult airway, education.

Human Scream Detection and Analysis for Controlling Crime Rate using Machine Learning and Deep Learning

Abstract: This paper addresses the problem of automatic detection and recognition of impulsive sounds, such as glass breaks, human screams, gunshots, explosions or door slams. A complete detection and recognition system is described and evaluated on a sound database containing more than 800 signals distributed among six different classes. Emphasis is set on robust techniques, allowing the use of this system in a noisy environment. The detection algorithm, based on a median filter, features a highly ro- bust performance even under important background noise conditions. In the recognition stage, two statistical classifiers are compared, using Gaussian Mixture Models (GMM) and Hidden Markov Models (HMM), respec- tively. It can be shown that a rather good recognition rate (98% at 70dB and above 80% for 0dB signal-to-noise ratios) can be reached, even under severe gaussian white noise degradations.

FUZ-SMO: A fuzzy slime mould optimizer for mitigating false alarm rates in the classification of underwater datasets using deep convolutional neural networks

Sonar sound datasets are of significant importance in the domains of underwater surveillance and marine research as they enable experts to discern intricate patterns within the depths of the water. Nevertheless, the task of classifying sonar sound datasets continues to pose significant challenges. In this study, we present a novel approach aimed at enhancing the precision and efficacy of sonar sound dataset classification. The integration of deep long-short-term memory (DLSTM) and convolutional neural networks (CNNs) models is employed in order to capitalize on their respective advantages while also utilizing distinctive feature engineering techniques to achieve the most favorable outcomes. Although DLSTM networks have demonstrated effectiveness in tasks involving sequence classification, attaining their optimal performance necessitates careful adjustment of hyperparameters. While traditional methods such as grid and random search are effective, they frequently encounter challenges related to computational inefficiencies. This study aims to investigate the unexplored capabilities of the fuzzy slime mould optimizer (FUZ-SMO) in the context of LSTM hyperparameter tuning, with the objective of addressing the existing research gap in this area. Drawing inspiration from the adaptive behavior exhibited by slime moulds, the FUZ-SMO proposes a novel approach to optimization. The amalgamated model, which combines CNN, LSTM, fuzzy, and SMO, exhibits a notable improvement in classification accuracy, outperforming conventional LSTM architectures by a margin of 2.142%. This model not only demonstrates accelerated convergence milestones but also displays significant resilience against overfitting tendencies.

Graph-Based Audio Classification Using Pre-Trained Models and Graph Neural Networks.

Sound classification plays a crucial role in enhancing the interpretation, analysis, and use of acoustic data, leading to a wide range of practical applications, of which environmental sound analysis is one of the most important. In this paper, we explore the representation of audio data as graphs in the context of sound classification. We propose a methodology that leverages pre-trained audio models to extract deep features from audio files, which are then employed as node information to build graphs. Subsequently, we train various graph neural networks (GNNs), specifically graph convolutional networks (GCNs), GraphSAGE, and graph attention networks (GATs), to solve multi-class audio classification problems. Our findings underscore the effectiveness of employing graphs to represent audio data. Moreover, they highlight the competitive performance of GNNs in sound classification endeavors, with the GAT model emerging as the top performer, achieving a mean accuracy of 83% in classifying environmental sounds and 91% in identifying the land cover of a site based on its audio recording. In conclusion, this study provides novel insights into the potential of graph representation learning techniques for analyzing audio data.

Training environmental sound classification models for real-world deployment in edge devices

The interest in smart city technologies has grown in recent years, and a major challenge is to develop methods that can extract useful information from data collected by sensors in the city. One possible scenario is the use of sound sensors to detect passing vehicles, sirens, and other sounds on the streets. However, classifying sounds in a street environment is a complex task due to various factors that can affect sound quality, such as weather, traffic volume, and microphone quality. This paper presents a deep learning model for multi-label sound classification that can be deployed in the real world on edge devices. We describe two key components, namely data collection and preparation, and the methodology to train the model including a pre-train using knowledge distillation. We benchmark our models on the ESC-50 dataset and show an accuracy of 85.4%, comparable to similar state-of-the-art models requiring significantly more computational resources. We also evaluated the model using data collected in the real world by early prototypes of luminaires integrating edge devices, with results showing that the approach works well for most vehicles but has significant limitations for the classes “person” and “bicycle”. Given the difference between the benchmarking and the real-world results, we claim that the quality and quantity of public and private data for this type of task is the main limitation. Finally, all results show great benefits in pretraining the model using knowledge distillation.

Research on lung sound classification model based on dual-channel CNN-LSTM algorithm

ulmonary diseases have a significant impact on human health and life safety, and abnormalities in the lungs are a direct response to lung diseases. Establishing an effective lung sound classification model that can assist in diagnosis is of great significance for electronic auscultation.In addressing the issue of lung sound signal classification, this study introduces a deep learning classification model based on a dual-channel CNN-LSTM algorithm. Initially, Mel-scale Frequency Cepstral Coefficients (MFCC) are employed for feature extraction from the dataset, transforming lung sound signals into Mel spectrograms. On this foundation, a dual-channel algorithm classification model is constructed, with parallel Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) modules. The CNN module is designed to capture spatial dimension features of the input data, while the LSTM module focuses on temporal dimension features. These two feature sets are fused together, enabling the model to classify lung sounds and thereby assisting in diagnosing pulmonary diseases for healthcare practitioners. This experiment used the ICBHI2017 Challenge Lungs dataset and obtained 5054 pieces of data through data augmentation and sampling techniques.The results show that the accuracy, recall, and F1 score of this model reach 99.01%, 99.13%, and 0.9915, respectively, significantly superior to other models, highlighting its practical application value.