Sound Recognition Research Articles

The hybrid of BERT and deep learning models for Indonesian sentiment analysis

<span>Artificial intelligence (AI) is one example of how data science innovation has advanced quickly in recent years and has greatly improved human existence. Neural networks, which are a type of machine learning model, are a fundamental component of deep learning in the field of AI. Deep learning models can carry out feature extraction and classification tasks in a single design because of their numerous neural network layers. Modern machine learning algorithms have been shown to perform worse than this model on tasks including text classification, audio recognition, imaginary, and pattern recognition. Deep learning models have outperformed AI-based methods in sentiment analysis and other text categorization tasks. Text data can originate from a number of places, including social media. Sentiment analysis is the computational examination of textual expressions of ideas and feelings. This study employs the convolutional neural network (CNN), long-short term memory (LSTM), CNN-LSTM, and LSTM-CNN models in a deep learning framework using bidirectional encoder representations from transformers (BERT) data representation to assess the performance of machine learning. The implementation of the model utilises YouTube discussion data pertaining to political films associated with the Indonesian presidential election of 2024. Confusion metrics, including as accuracy, precision, and recall, are then used to analyse the model’s performance.</span>

Research on Piano Curriculum Education and Its Performance Ecosystem Based on Network Flow Optimization

Abstract This paper investigates music education, where an efficient and accurate performance evaluation system in the piano teaching and performance ecosystem is increasingly becoming an essential tool for improving teaching quality and performance level. The objective evaluation of students’ performance skills can be achieved by carefully analyzing piano performances using the network flow optimization technique. This technique optimizes the performance evaluation system’s audio recognition ability by analyzing the piano audio signal and solving the multi-constraint nonlinear optimization problem in a limited time domain. This paper establishes a network flow optimization model, applies the multi-constraint nonlinear optimization technique, and combines the non-negative matrix decomposition and dynamic time regularization algorithm to analyze the piano performance for experiments. After optimization processing, hundreds of piano audio samples were collected, and the audio recognition accuracy was improved by 20%. By optimizing and processing the audio signals from the network stream, the evaluation system could detect polyphony more accurately and track the musical score effectively, improving accuracy and efficiency. Using the non-negative matrix decomposition algorithm, the accuracy of detecting polyphony can reach 85%, while the dynamic temporal regularization algorithm can match the position of the musical score with 95% accuracy. The accuracy of piano performance evaluation is optimized by this network flow optimization method, providing new technical means for music education, and promoting the quality of teaching and performance.

Factores sociodemográficos, audiológicos y audioprotésicos relacionados con la calidad de vida en pacientes con prótesis auditivas en Madrid (España)

Background and objectiveThe purpose of a prosthetic adaptation is not only to improve language understanding and sound recognition, but to improve the patient's quality of life.The purpose of this investigation is to measure quality of life of patients with hearing aids, and investigate which sociodemographic, audiological and audioprosthetic variables affect it. Material and methodsMulticenter cross-sectional descriptive study in the Community of Madrid (España). Sample 54 patients and Effectiveness of Auditory Rehabilitation (EAR) scale was used. ResultsMean age 66.4 years; 55.6% men. The mean score of 10 audiological EAR items was 64.54 (SD 16.43). The mean score of 10 ear audioprosthetic items was 71.84 (SD 13.49).Age, sex, work activity, level of education, degree of hearing loss, logoaudiometry results, free field, number and format of hearing aids, prescriber of the prostheses and year of manufacture of the prostheses, are associated with different items of the EAR scale (P<.05). ConclusionsThe audiological quality of life ranges from regular to good, and audioprosthetics is close to good.Younger age, female sex and work activity are associated with better quality of life. People with good logoaudiometric results are associated with better quality of life. Monaural adaptations, retroauricular hearing aids, more modern hearing aids and that the patient does not self-describe hearing aids, are associated with better quality of life.Hearing aids improve the quality of life of patients, provided that sociodemographic, audiological and audioprosthetic characteristics, specific to each patient are taken into account to make a personalized and optimal audioprosthetic adjustment.

Bird Sound Identification System using Deep Learning

This paper identifies the model for classifying the bird sounds using the Convolutional Neural Network (CNN) algorithm. CNN are considered as one of the powerful toolkits developed in the machine learning and that have shown to be more efficient particularly in the field of image processing and sound recognition. The two-step verification process which will participating in the creation of datasets and neural network input. This system uses the collection of labelled and categorized recordings. Spectrograms are generated from the downloaded data which is used as the input for the neural network. The experiments are conducted and it will match with the different configurations, which including the number of bird species and Spectrograms. As a result, we can identify the bird species from its audio recordings. By identifying the bird species on a large scale, it provides a vital information about our ecosystems and biodiversity. The changes in the ecological environment can be reflected by the quantity and composition of bird species. It is one of the major challenges which leads to recognition of many bird species based on their audio. In modern years, the deep learning techniques namely convolutional neural networks (CNN) have played a major role in many areas of science and also successfully provided efficient methodologies, such as pattern recognition, object detection in images, and classification of patterns in audios and speech recognition.

Wave2Graph: Integrating spectral features and correlations for graph-based learning in sound waves

This paper investigates a novel graph-based representation of sound waves inspired by the physical phenomenon of correlated vibrations. We propose a Wave2Graph framework for integrating multiple acoustic representations, including the spectrum of frequencies and correlations, into various neural computing architectures to achieve new state-of-the-art performances in sound classification. The capability and reliability of our end-to-end framework are evidently demonstrated in voice pathology for low-cost and non-invasive mass-screening of medical conditions, including respiratory illnesses and Alzheimer’s Dementia. We conduct extensive experiments on multiple public benchmark datasets (ICBHI and ADReSSo) and our real-world dataset (IJSound: Respiratory disease detection using coughs and breaths). Wave2Graph framework consistently outperforms previous state-of-the-art methods with a large magnitude, up to 7.65% improvement, promising the usefulness of graph-based representation in signal processing and machine learning.

Determination of Hopper Fullness of Smart Screw Press Using Machine Learning

Problem statement. This research addresses the challenge of accurately determining the fullness of the hopper within a screw press for optimal oil extraction efficiency and quality. Existing weight or volume-based measurement methods can often struggle with determining the feed hopper fullness due to variable oil weights during extraction stages, material heterogeneity, environmental influences and imprecise instrument calibration. Purpose. The study proposes a novel solution via the application of machine learning, specifically aiming to develop and validate a technique that uses acoustic signals to calculate screw press bowl load. Methodology. To implement this solution, the study uses quantitative research, data collection and data analysis, supervised learning. The method is based on the processing of audio data received from microphones located near the auger and the use of machine learning algorithms, such as sound classification. Model training process was facilitated by ML tool Arduino. Findings. The results of this study, facilitated by effective data analysis via ML tools, demonstrate that the evaluated filling level of the screw press hopper can effectively be determined by the sound signals produced and corresponding machine learning algorithms. Originality. The distinct advantage of this approach lies in its ability to automate the monitoring and operational control process of the oil press, thereby improving device efficiency and resource conservation. Practical value. The proposed approach allows to automate the process of determining the fullness of the bowl and monitor the condition of the auger by its sound characteristics. This solution can be utilized in the oil production industry to enhance the productivity of the screw presses. This research underscores the promise of machine learning applications and the potential for future research focusing on improving model adaptability and developing predictive maintenance systems. These future investigative scopes could essentially revolutionize monitoring and operational practices within the oil extraction industry.

Classification and Recognition of Lung Sounds Based on Improved Bi-ResNet Model

Classification and Recognition of Lung Sounds Based on Improved Bi-ResNet Model

Classification of adventitious respiratory sounds through histogram of oriented gradients

Las enfermedades respiratorias representan una de las principales causas de muerte en el mundo. La prevención, el diagnóstico oportuno y el tratamiento efectivo son pilares fundamentales para reducir la propagación de enfermedades, así como su impacto negativo en la sociedad. El presente trabajo está enfocado en desarrollar un modelo computacional, a través del uso del algoritmo Histograma de Gradientes Orientados (HOG) en conjunto con técnicas de aprendizaje de máquina, capaz de clasificar sonidos respiratorios adventicios; para apoyar en el diagnóstico oportuno de enfermedades respiratorias. Para ello, se propone utilizar al HOG como extractor de características, el cual no ha sido explorado en la literatura actual sobre la clasificación de sonidos respiratorios. De igual manera, se plantea usar distintos algoritmos de aprendizaje de máquina, como: Máquina de Soporte Vectorial (SVM), K-Vecinos más Cercanos (KNN) y Bosques Aleatorios (RF). Asimismo, evaluar el modelo según el marco de trabajo proveído por la base de datos ICBHI17. La principal contribución del presente trabajo es el análisis de diferentes configuraciones del histograma de gradientes orientados para optimizar los modelos de aprendizaje de máquina. En donde, después de una serie de experimentos, nuestro mejor modelo surgió con la configuración Alternativa 4 (ALT 4); que obtuvo como resultados: 55.07% ACC, 34.37% BAL, 51.52% SCC, 75.87% SPE y 27.18% SEN.

NEXUS: A 28nm 3.3pJ/SOP 16-Core Spiking Neural Network with a Diamond Topology for Real-Time Data Processing.

The realization of brain-scale spiking neural networks (SNNs) is impeded by power constraints and low integration density. To address these challenges, multi-core SNNs are utilized to emulate numerous neurons with high energy efficiency, where spike packets are routed through a network-on-chip (NoC). However, the information can be lost in the NoC under high spike traffic conditions, leading to performance degradation. This work presents NEXUS, a 16-core SNN with a diamond-shaped NoC topology fabricated in 28-nm CMOS technology. It integrates 4096 leaky integrate-and-fire (LIF) neurons with 1M 4-bit synaptic weights, occupying an area of 2.16 mm2. The proposed NoC architecture is scalable to any network size, ensuring no data loss due to contending packets with a maximum routing latency of 5.1μs for 16 cores. The proposed congestion management method eliminates the need for FIFO in routers, resulting in a compact router footprint of 0.001 mm2. The proposed neurosynaptic core allows for increasing the processing speed by up to 8.5× depending on input sparsity. The SNN achieves a peak throughput of 4.7 GSOP/s at 0.9 V, consuming a minimum energy per synaptic operation (SOP) of 3.3 pJ at 0.55 V. A 4-layer feed-forward network is mapped onto the chip, classifying MNIST digits with 92.3% accuracy at 8.4Kclassification/ s and consuming 2.7-μJ/classification. Additionally, an audio recognition task mapped onto the chip achieves 87.4% accuracy at 215-μJ/classification.

Improving Audio Recognition with Randomized Area Ratio Patch Masking: A Data Augmentation Perspective

Improving Audio Recognition with Randomized Area Ratio Patch Masking: A Data Augmentation Perspective

Speech recognition enhancement based on wireless network sensors application in interactive intelligent teaching system

The speech function used in the multi-dimensional speech recognition model based on MTL and RNN is the commonly used MFCC function, and in feature extraction, after various filtering and conversion, deleting part of the speech information is a requirement for 3D audio recognition. Use multidimensional information as much as possible. Based on this, this article not only brings the development of convolutional neural network intelligent teaching, but also proposes a new education model. Heuristic education like flipped classroom is still the content of education research in recent years, and it is important to the current education form in China. It is mainly based on the traditional lecture mode or the classroom form. This article focuses on undergraduate education. It is designed in the classroom based on the video data of the undergraduate interactive activities and the interactive system. It has important research significance and practicality. At the same time, the interactive content of the traditional teaching method is used to perform voice recognition, and the recognition effect of the main body of the interactive system is further improved through the voice information. The spatial perspective is used to divide the lens perspective into seminars and experimental forms, and the pixel change value of each frame provides a specific reference for it to determine the reflection of student interaction activities and the evaluation of student seminars. This article introduces the implementation process of interactive content and interactive activities of the teaching system in the classroom, introduces the speech recognition framework of the MARS Chinese teaching system, uses the model principle, and compares the general speech data set test with the actual ARST model audio. The results show that, MAS model performance is more advantageous.

Artificial Neural Network Trained for Sound Recognition Exhibiting Human-like Sensitivity to Sound Amplitude Modulation

Artificial Neural Network Trained for Sound Recognition Exhibiting Human-like Sensitivity to Sound Amplitude Modulation

Feature Aggregation in Joint Sound Classification and Localization Neural Networks

Feature Aggregation in Joint Sound Classification and Localization Neural Networks

Sound Classification for Javanese Eagle Based on Improved Mel-Frequency Cepstral Coefficients and Deep Convolutional Neural Network

Sound Classification for Javanese Eagle Based on Improved Mel-Frequency Cepstral Coefficients and Deep Convolutional Neural Network

Automated Cough Sound Analysis for Detecting Childhood Pneumonia.

Pneumonia is one of the leading causes of death in children. Prompt diagnosis and treatment can help prevent these deaths, particularly in resource poor regions where deaths due to pneumonia are highest. Clinical symptom-based screening of childhood pneumonia yields excessive false positives, highlighting the necessity for additional rapid diagnostic tests. Cough is a prevalent symptom of acute respiratory illnesses and the sound of a cough can indicate the underlying pathological changes resulting from respiratory infections. In this study, we propose a fully automated approach to evaluate cough sounds to distinguish pneumonia from other acute respiratory diseases in children. The proposed method involves cough sound denoising, cough sound segmentation, and cough sound classification. The denoising algorithm utilizes multi-conditional spectral mapping with a multilayer perceptron network while the segmentation algorithm detects cough sounds directly from the denoised audio waveform. From the segmented cough signal, we extract various handcrafted features and feature embeddings from a pretrained deep learning network. A multilayer perceptron is trained on the combined feature set for detecting pneumonia. The method we propose is evaluated using a dataset comprising cough sounds from 173 children diagnosed with either pneumonia or other acute respiratory diseases. On average, the denoising algorithm improved the signal-to-noise ratio by 44%. Furthermore, a sensitivity and specificity of 91% and 86%, respectively, is achieved in cough segmentation and 82% and 71%, respectively, in detecting childhood pneumonia using cough sounds alone. This demonstrates its potential as a rapid diagnostic tool, such as using smartphone technology.

Joint Energy-based Model for Semi-supervised Respiratory Sound Classification: A Method of Insensitive to Distribution Mismatch.

Semi-supervised learning effectively mitigates the lack of labeled data by introducing extensive unlabeled data. Despite achieving success in respiratory sound classification, in practice, it usually takes years to acquire a sufficiently sizeable unlabeled set, which consequently results in an extension of the research timeline. Considering that there are also respiratory sounds available in other related tasks, like breath phase detection and COVID-19 detection, it might be an alternative manner to treat these external samples as unlabeled data for respiratory sound classification. However, since these external samples are collected in different scenarios via different devices, there inevitably exists a distribution mismatch between the labeled and external unlabeled data. For existing methods, they usually assume that the labeled and unlabeled data follow the same data distribution. Therefore, they cannot benefit from external samples. To utilize external unlabeled data, we propose a semi-supervised method based on Joint Energy-based Model (JEM) in this paper. During training, the method attempts to use only the essential semantic components within the samples to model the data distribution. When non-semantic components like recording environments and devices vary, as these non-semantic components have a small impact on the model training, a relatively accurate distribution estimation is obtained. Therefore, the method exhibits insensitivity to the distribution mismatch, enabling the model to leverage external unlabeled data to mitigate the lack of labeled data. Taking ICBHI 2017 as the labeled set, HF_Lung_V1 and COVID-19 Sounds as the external unlabeled sets, the proposed method exceeds the baseline by 12.86.

Texture Feature and Mel-Spectrogram Analysis for Music Sound Classification

Texture Feature and Mel-Spectrogram Analysis for Music Sound Classification

Lung Sound Classification With Multi-Feature Integration Utilizing Lightweight CNN Model

Lung Sound Classification With Multi-Feature Integration Utilizing Lightweight CNN Model

Convolution Neural Networks of Dynamically Sized Filters with Modified Stochastic Gradient Descent Optimizer for Sound Classification

Convolution Neural Networks of Dynamically Sized Filters with Modified Stochastic Gradient Descent Optimizer for Sound Classification

Supervised Contrastive Learning Framework and Hardware Implementation of Learned ResNet for Real-time Respiratory Sound Classification.

This paper presents a supervised contrastive learning (SCL) framework for respiratory sound classification and the hardware implementation of learned ResNet on field programmable gate array (FPGA) for real-time monitoring. At the algorithmic level, multiple techniques such as features augmentation and MixUp are combined holistically to mitigate the impact of data scarcity and imbalanced classes in the training dataset. Bayesian optimization further enhances the classification accuracy through parameter tuning in pre-processing and SCL. The proposed framework achieves 0.8725 total score (including runtime score) on a ResNet-18 model in both event and record multi-class classification tasks using the SJTU Paediatric Respiratory Sound Database (SPRSound). In addition, algorithm-hardware co-optimizations including Quantization-Aware Training (QAT), merge of network layers, optimization of memory size and number of parallel threads are performed for hardware implementation on FPGA. This approach reduces 40% model size and 70% computation latency. The learned ResNet is implemented on a Xilinx Zynq ZCU102 FPGA with 16ms latency and less than 2% inference score degradation compared to the software model.