Noise Interference Research Articles

The effects of multitalker babble noise on children's cognitive performance

Classroom noise, particularly irrelevant speech or background babble noise, can have detrimental effects on academic tasks and learning more generally. Researchers have proposed two alternative explanations of the interference of babble noise on non-auditory academic tasks, such as reading or math: i) Babble noise may generate interference on these tasks due to the automatic access of speech sounds (babbling) to phonological short-term memory; or ii) by capturing children's attention, thereby diverting general attentional resources from the task. To test these hypotheses, we asked 3rd to 5th graders to perform two visual attention and two verbal working memory tasks (digit span and reading span) in both quiet and noisy conditions. Multitalker babble noise was administered through headphones at 65dB. The results revealed significant noise effects only in the most complex verbal working memory task (reading span). Interestingly, a significant difference between conditions was also observed in one of the visual attention tasks, where higher scores were, however, achieved in the presence of noise. These preliminary findings will be discussed in light of the current literature.

The relationship between singular value decomposition orthogonal space vector and sound field reconstruction in equivalent source method

In acoustic holography, the equivalent source method represents a typical ill-posed inverse problem, characterized by the significant impact of measurement errors on the sought solution. To minimize the interference of noise with the sought solution, we analyze the relationship between orthogonal space vectors obtained through singular value decomposition and acoustic field reconstruction. The research findings indicate that the primary information of the acoustic field exhibits strong correlation with a small number of space vectors, while noise information demonstrates random correlation with all space vectors. Therefore, we retain the space vectors with higher correlation to the acoustic field while filtering out redundant ones, thereby stabilizing and accurately reconstructing the acoustic field. Numerical analysis of the acoustic field reconstruction demonstrates that compared to regularization methods such as Tikhonov and truncated singular value decomposition (TSVD), this approach achieves higher computational accuracy. Furthermore, the text combines practical examples to further explain the reasons behind the superior accuracy of this method.

From simulation to reality: tackling data mismatches in speech enhancement with unsupervised pre-training

In this study, we introduce an innovative speech enhancement methodology that ingeniously combines unsupervised pre-training with supervised fine-tuning. This hybrid approach directly addresses the prevalent data mismatch challenge inherent in traditional supervised speech enhancement methods. Our technique distinctly utilizes unpaired noisy and clean speech data and incorporates varied noises during the pre-training phase. This strategy effectively simulates the benefits of supervised learning, eliminating the need for paired data. Inspired by contrastive learning techniques prevalent in computer vision, our model is adept at preserving essential speech features amidst noise interference. At the heart of our method lies a sophisticated Generative Adversarial Network (GAN) architecture. This includes a generator that proficiently processes both magnitude and complex-domain features, alongside a discriminator meticulously designed to optimize specific evaluation metrics. Through rigorous experimental evaluations, we validate the robustness and versatility of our approach. It consistently delivers superior speech quality, demonstrating remarkable efficacy in real-world scenarios, which are often characterized by complex and unpredictable noise environments.

ADAPTIVE METHOD OF FORMING COMPLEX SIGNALS ENSEMBLES BASED ON MULTI-LEVEL RECURRENT TIME-FREQUENCY SEGMENT MODELING

The article investigates the implementation of an adaptive method for forming ensembles of complex signals based on multilevel recurrent time-frequency segmentation. It addresses the key challenges faced by cognitive wireless networks operating in dynamic radio frequency environments with high levels of interference, necessitating rapid adaptation to changes in the spectral characteristics of signals. The study substantiates the need for adaptive filters and specific transformations to enhance signal processing quality, particularly in environments with high variability in frequency characteristics and significant noise interference. The proposed method of multilevel recurrent time-frequency segmentation allows for the modification of time segment durations and the use of segments of varying lengths, providing flexibility in signal processing and adaptation to current conditions. This adaptability enables optimal signal processing for each individual case, taking into account short-term impulses, long-term fluctuations, and various types of noise and distortions. This approach effectively separates frequency components and reduces interference between them, which is crucial for maintaining high signal quality and communication stability in cognitive networks. It has been proven that the use of adaptive filters such as LMS (Least Mean Squares) and RLS (Recursive Least Squares), as well as fast Fourier Transform (STFT), wavelet, and Hilbert transforms at different stages of multilevel time-frequency segmentation, significantly enhances signal interference resistance and energy efficiency. Comparative analysis of signal metrics before and after filtering and transformation shows an increase in signal quality by 14,3–24,5% and a reduction in noise levels by 21,7–29,6%. The wavelet transform, in particular, proved to be highly effective, allowing for precise extraction of useful frequency components from the noise background and improving signal parameters through dynamic adjustment to specific radio environment conditions. Experimental results confirm the effectiveness of the proposed method, demonstrating its ability to ensure consistently high-quality processing of complex signal ensembles even in dynamic cognitive radio environments.

Optimization of speech intelligibility in street-facing rooms of adult care home based on acoustic simulation

Due to the limited availability of urban land in China, many adult care facilities have resorted to constructing roadside living spaces. However, this has led to a significant issue of traffic noise disturbance. Besides, many rooms lack of control over indoor reverberation. As a result, the communication efficiency of the residents might be greatly impacted. This study aims to investigate the impact of traffic noise level, room size, and surface sound absorption on speech transmission index (STI), based on a typical room layout and conducted using acoustic simulation. The simulation results indicated that in order to achieve the required STI over 0.79 for elderly residents, it is imperative to control the road noise interference below 40 dBA and ensure that the room reverberation time under 0.42 s. To achieve this, it is recommended that for a road with a noise emission level of 72 dBA, the distance between the roadside room and the road should not less than 10 m. Additionally, windows with Rw+Ctr over 28 dB without road sound barriers (over 20 dB with sound barriers) should be installed. Besides, the room area needs to be controlled within 20 m2 and an acoustic ceiling with NRC>0.65 should be installed.

Dual-stream dynamic graph structure network for document-level relation extraction

Extracting structured information from unstructured text is crucial for knowledge management and utilization, which is the goal of document-level relation extraction. Existing graph-based methods face issues with information confusion and integration, limiting the reasoning capabilities of the model. To tackle this problem, a dual-stream dynamic graph structural network is proposed to model documents from various perspectives. Leveraging the richness of document information, a static document heterogeneous graph is constructed. A dynamic heterogeneous document graph is then induced based on this foundation to facilitate global information aggregation for entity representation learning. Additionally, the static document graph is decomposed into multi-level static semantic graphs, and multi-layer dynamic semantic graphs are further induced, explicitly segregating information from different levels. Information from different streams is effectively integrated via an information integrator. To mitigate the interference of noise during the reasoning process, a noise regularization mechanism is also designed. The experimental results on three extensively utilized publicly accessible datasets for document-level relation extraction demonstrate that our model achieves F1 scores of 62.56%, 71.1%, and 86.9% on the DocRED, CDR, and GDA datasets, respectively, significantly outperforming the baselines. Further analysis also demonstrates the effectiveness of the model in multi-entity scenarios.

A novel image inpainting method based on a modified Lengyel–Epstein model

With the increasing popularity of digital images, developing advanced algorithms that can accurately reconstruct damaged images while maintaining high visual quality is crucial. Traditional image restoration algorithms often struggle with complex structures and details, while recent deep learning methods, though effective, face significant challenges related to high data dependency and computational costs. To resolve these challenges, we propose a novel image inpainting model, which is based on a modified Lengyel–Epstein (LE) model. We discretize the modified LE model by using an explicit Euler algorithm. A series of restoration experiments are conducted on various image types, including binary images, grayscale images, index images, and color images. The experimental results demonstrate the effectiveness and robustness of the method, and even under complex conditions of noise interference and local damage, the proposed method can exhibit excellent repair performance. To quantify the fidelity of these restored images, we use the peak signal-to-noise ratio (PSNR), a widely accepted metric in image processing. The calculation results further demonstrate the applicability of our model across different image types. Moreover, by evaluating CPU time, our method can achieve ideal repair results within a remarkably brief duration. The proposed method validates significant potential for real-world applications in diverse domains of image restoration and enhancement.

Road target recognition based on radar range-Doppler spectrum with GS – ResNet

ABSTRACT Road target recognition ability of automotive millimetre-wave (mmWave) radar is crucial in areas such as autonomous driving, advanced driver assistance systems (ADAS), and automated emergency braking systems (AEBS). Current mmWave radar systems are primarily utilized for speed, distance, and angle measurements, with limited capability or unsatisfactory performance in target classification. In response to this limitation, this paper proposes a novel method for road target recognition, using radar range-Doppler spectrum as input data and introducing a global attention mechanism and SCConv module. First, the range-Doppler spectrum is processed by the clutter removal algorithm block to remove background clutter and vibration interference. Second, considering the small features and susceptibility to noise interference in the range-Doppler spectrum, we have devised a deep residual network based on a global attention mechanism, significantly enhancing the model’s accuracy in range-Doppler spectrum classification. Finally, we introduce the SCConv module and improve the downsampling module in ResNet to enhance the model’s classification accuracy. Experimental results demonstrate that the model achieves an average accuracy of 99.79% in classifying six types of road targets, significantly outperforming other methods. This research is of significant importance in advancing the understanding of road traffic conditions by autonomous driving systems and enhancing system safety.

WCNN-RSN: a novel fault diagnosis method for rolling bearing using multimodal feature fusion

Abstract Fault diagnosis of rolling bearings is significant for the safe operation of engineering equipment. Many intelligent diagnostic methods have been successfully developed. However, it is often susceptible to noisy environments. Therefore, the paper proposes a rolling bearing fault diagnosis method based on multimodal information fusion in time and time–frequency domains by combining an improved 1D-convolutional neural network (CNN) with ResNet50 wavelet improved CNN-ResNet (WCNN-RSN). The algorithm employs the Multi-Head Attention (MHA) mechanism to complementarily fuse fault features in different scales, achieving fault diagnosis by fully extracting fault features. The experimental results show that the diagnostic effect of WCNN-RSN is better than that of the comparison methods under noise interference, which proves that the proposed method possesses good anti-noise and generalization ability.

Anti-noise weld seam tracking algorithm based on spatio-temporal memory mechanism

In laser vision-based robotic welding, existing seam tracking methods are seriously affected by noise and lack effective utilization of spatio-temporal information during welding process. To address this, this paper proposes an anti-noise weld seam tracking algorithm based on spatio-temporal memory mechanism. First, a memory mechanism with welding history memory information is designed, which can better adapt to seam appearance changes and noise interference during welding. Subsequently, a laser stripe tracker based on spatio-temporal memory is constructed, it enables the current frame to adaptively search historical valid information to eliminate effects of noise and appearance changes. The experimental results show that the proposed method has an average response speed of 43 FPS and an average tracking error of 1.35 pixels for various weld seams. The actual tracking error is less than 0.6 mm. The introduction of memory mechanism improves the weld tracking accuracy by 52.1 % compared to a single tracking template.

Readout circuit noise analysis and low-noise design for piezoelectric micro-machined ultrasonic transducers with large parasitic capacitance.

Readout circuits are fundamental components in many application systems that utilize piezoelectric micro-machined ultrasonic transducers (pMUTs). This study models the noise and signal transfer functions of trans-impedance amplifiers (TIAs), charge-sensitive circuits, and voltage-mode readout circuits in detail. A series of simulations and experiments were conducted to elucidate the advantages and disadvantages of these circuit types. Both theoretical and experimental results indicate that the intrinsic capacitance of large pMUTs can significantly degrade the quality of the readout signal. Furthermore, while the TIA-based readout circuit demonstrates clear gain advantages, it is also susceptible to considerable noise interference. This work proposes an improved readout circuit design that effectively mitigates noise interference while preserving the gain advantages of the TIA architecture. The implemented prototype circuit successfully reduces the noise from 73 mVp-p to 13 mVp-p.

A novel damage index for crack identification of a drilling riser during deployment based on the modal vibration energy flow

Early detection of structural damage especially small cracks in marine deepwater drilling risers is of paramount importance. Small cracks are always hard to detect because of weak vibration signals if using traditional damage indices, such as natural frequencies and mode shapes including modal displacements, cross-section slopes, and curvatures. Especially when the deepwater riser is during deployment, the variable suspension riser length and strong sea environment noise make the small crack identification more difficult. To address this problem, this study formulates a new concept of damage detection by integrating the vibration energy flow theory into the vibration-based damage detection (VDD) technique. A novel damage-sensitive feature (DSF) named modal vibration energy flow (MVEF) is established for detecting and locating the small cracks in deepwater drilling risers. The capability of the approach is verified by using the same riser model and the numerical results in the literature. The sensitivities versus crack positions and depths, variable suspension riser length, and sea noise are studied in detail. Results show that the proposed index MVEF is more sensitive than the classic traditional DSFs, i.e., modal slope, modal strain (or curvature), and modal strain energy. In total, the MVEF approach can accurately identify the small cracks and is robust against noise interference, suitable for detecting and locating small cracks in the deepwater drilling riser during deployment.

Application of End-to-End Perception Framework Based on Boosted DETR in UAV Inspection of Overhead Transmission Lines

As crucial predecessor tasks for fault detection and transmission line inspection, insulators, anti-vibration hammers, and arc sag detection are critical jobs. Due to the complexity of the high-voltage transmission line environment and other factors, target detection work on transmission lines remains challenging. A method for high-voltage transmission line inspection based on DETR (TLI-DETR) is proposed to detect insulators, anti-vibration hammers, and arc sag. This model achieves a better balance in terms of speed and accuracy than previous methods. Due to environmental interference such as mountainous forests, rivers, and lakes, this paper uses the Improved Multi-Scale Retinex with Color Restoration (IMSRCR) algorithm to make edge extraction more robust with less noise interference. Based on the TLI-DETR’s feature extraction network, we introduce the edge and semantic information by Momentum Comparison (MoCo) to boost the model’s feature extraction ability for small targets. The different shooting angles and distances of drones result in the target images taking up small proportions and impeding each other. Consequently, the statistical profiling of the area and aspect ratio of transmission line targets captured by UAV generate target query vectors with prior information to enable the model to adapt to the detection needs of transmission line targets more accurately and effectively improve the detection accuracy of small targets. The experimental results show that this method has excellent performance in high-voltage transmission line detection, achieving up to 91.65% accuracy and a 55FPS detection speed, which provides a technical basis for the online detection of transmission line targets.

PeriodNet: Noise-Robust Fault Diagnosis Method Under Varying Speed Conditions.

Rolling bearings are critical components in modern mechanical systems and have been extensively equipped in various rotating machinery. However, their operating conditions are becoming increasingly complex due to diverse working requirements, dramatically increasing their failure risks. Worse still, the interference of strong background noises and the modulation of varying speed conditions make intelligent fault diagnosis very challenging for conventional methods with limited feature extraction capability. To this end, this study proposes a periodic convolutional neural network (PeriodNet), which is an intelligent end-to-end framework for bearing fault diagnosis. The proposed PeriodNet is constructed by inserting a periodic convolutional module (PeriodConv) before a backbone network. PeriodConv is developed based on the generalized short-time noise resist correlation (GeSTNRC) method, which can effectively capture features from noisy vibration signals collected under varying speed conditions. In PeriodConv, GeSTNRC is extended to the weighted version through deep learning (DL) techniques, whose parameters can be optimized during training. Two open-source datasets collected under constant and varying speed conditions are adopted to assess the proposed method. Case studies demonstrate that PeriodNet has excellent generalizability and is effective under varying speed conditions. Experiments adding noise interference further reveal that PeriodNet is highly robust in noisy environments.

CRISP: A cross-modal integration framework based on the surprisingly popular algorithm for multimodal named entity recognition

The multimodal named entity recognition task on social media involves recognizing named entities with textual and visual information, which is of great significance for information processing. Nevertheless, many existing models still face the following challenges. First, in the process of cross-modal interaction, the attention mechanism sometimes focuses on trivial parts in the images that are not relevant to entities, which not only neglects valuable information but also inevitably introduces visual noise. Second, the gate mechanism is widely used for filtering out visual information to reduce the influence of noise on text understanding. However, the gate mechanism neglects capturing fine-grained semantic relevance between modalities, which easily affects the filtration process. To address these issues, we propose a cross-modal integration framework based on the surprisingly popular algorithm, aiming at enhancing the integration of effective visual guidance and reducing the interference of irrelevant visual noise. Specifically, we design a dual-branch interaction module that includes the attention mechanism and the surprisingly popular algorithm, allowing the model to focus on valuable but overlooked parts in the images. Furthermore, we compute the matching degree between modalities at the multi-granularity level, using the Choquet integral to establish a more reasonable basis for filtering out visual noise. We have conducted extensive experiments on public datasets, and the experimental results demonstrate the advantages of our model.

A robust double-channel affine projection sign algorithm for blind acoustic interferences cancellation

This brief proposes a double-channel direct affine projection sign (DC-DAPS) algorithm for blind speech enhancement applications, especially in the presence of strong acoustic noise, and intensive non-Gaussian impulsive interferences. We also derive a full analysis of the stability of the proposed DC-DAPS algorithm. The performance evaluation of the proposed algorithm confirms its accuracy even under different noisy scenarios, and demonstrates that our approach outperforms the double-channel direct affine projection (DC-DAP), and the double-channel direct normalized least mean square (DC-DNLMS) algorithms. Simulation results showed that the proposed DC-DAPS algorithm could effectively achieve improved performance in combating acoustic noise and impulsive interferences, and speeding up the convergence rate even with highly correlated input signals such as the speech signal.

A Novel Accurate Peak Extraction Algorithm of Mass Spectrometry Based on Iterative Adaptive Curve Fitting.

In the analysis of mass spectrometry, the peak identification from the overlapped region is necessary yet difficult. Although various methods have been developed to identify these peaks, especially the continuous wavelet transformation, their applications are still limited and it is hard to deal with the complex overlapped peaks. In this study, a novel peak extraction algorithm of mass spectrometry based on iterative adaptive curve fitting is proposed to address these challenges. It fully utilizes the global optimization characteristics of adaptive curve fitting. Initial peak parameters are obtained using a window searching method, and the residuals between the adaptive fitting peak and the original data indicate the fit's effectiveness and provide information about the peaks in overlap. Using this information, we performed iterative adaptive fitting, continuously updating the overlapped peaks until the residuals met the completion criteria. All of the peaks within the overlapped region can be successfully extracted by the final fitting. The proposed method is evaluated by the simulated data, the real signal from a public data set, and the spectra of two different mass spectrometry instruments. The results demonstrate that this method can more effectively extract peaks with severe overlap and multiple overlapped peaks, resist noise interference, and offer the potential to process peaks with a high dynamic range. More importantly, the proposed method accurately identifies overlapped peaks in the actual spectra from various mass spectrometry instruments, which helps the qualitative and quantitative analyses to a great extent.

The novel methods of insulation detection based on Adaptive Levenberg–Marquardt algorithm and Third-Order Variable Forgetting Factor Recursive Least Squares-Decouple algorithm

Electric vehicles (EVs) are central to the future of automotive development, with high-voltage insulation performance critical for operational safety. Existing insulation detection methods face challenges such as limited scope, low accuracy, poor interference resistance, and slow response. This study introduces two insulation detection models based on the unbalanced bridge method and low-frequency signal injection, analyzing their theoretical effectiveness and confirming superior detection capability in the unbalanced bridge method. Furthermore, to address feedback voltage waveform issues in this method, an adaptive Levenberg–Marquardt (ALM) algorithm is proposed to prevent the divergence typically seen in traditional approaches. Additionally, a decoupling algorithm utilizing a Third-order Variable Forgetting Factor Recursive Least Squares (TVFF-Decouple) simplifies algorithm complexity significantly while enabling anomaly detection. Finally, AEKF and SRCKF algorithms were used for observation, identifying an optimal combination that reduces noise interference effectively. Simulations and bench tests demonstrate that the proposed methods swiftly and accurately detect positive and negative insulation resistances and equivalent Y capacitance under various conditions.

A novel adaptive parameter zeroing neural network for the synchronization of complex chaotic systems and its field programmable gate array implementation

This article proposes a novel adaptive-parameter zeroing neural network (NAP-ZNN) to control the synchronization of complex chaotic systems. Different from previous zeroing neural networks (ZNNs), the NAP-ZNN model incorporates adaptive-parameter, a unique blend of time-varying convergence factor and fuzzy control parameter, which is adjusted continuously according to the real-time synchronizing error, offering greater flexibility. The NAP-ZNN model aims to address the time-varying problem in complex-valued domain, which is scarcely explored, it rapidly impels two complex chaotic systems to synchronize within predetermined time and effectively mitigates noise interference. Moreover, the upper bound of the convergence time is theoretically calculated in noiseless environments, and the disturbance-resistant property is demonstrated under various noisy disturbances. The control performance of NAP-ZNN model has been separately compared to other general ZNNs (NAP-ZNN synchronizes at 0.097 s while three general ZNNs spend 0.43 s, 0.78 s and 0.84 s, and only NAP-ZNN complete synchronization within 0.1 s under noisy interferences while general ZNNs fail) and the traditional adaptive control method through two synchronization simulation (RMSE of NAP-ZNN under sinusoidal noise is 3.165 × 10-3 while traditional is 3.383 at t = 1 s). The numerical outcomes clearly illustrate the superior performance of the NAP-ZNN model in comparison to other synchronization strategies. The hardware implementation of the NAP-ZNN model has been successfully realized through the Field Programmable Gate Array (FPGA), and the chaos synchronization process has been vividly captured via an oscilloscope, further reinforcing the practicality and effectiveness of the NAP-ZNN model.

De-noising magnetotelluric data based on machine learning

The magnetotelluric (MT) sounding is a common geophysical exploration technique, but it is highly polluted by various types of cultural noise. In the realm of MT data processing, traditional techniques often rely on the quality of the measured MT data. Conventional MT time domain denoising methods tend to eliminate valuable signals, potentially leading to unreliable resistivity estimates. To address this concern, we propose employing machine learning to effectively suppress strong noise interference in MT data, thereby preventing the loss of valuable signals. We augment this approach with mathematical morphological filtering (MMF) to capture low-frequency signals, preserving their integrity. We constructed a signal sample library based on a substantial volume of signal samples. Through consistent training, we establish a support vector machine (SVM) classification model that distinguishes high-quality signal fragments from noisy signals. Subsequently, we use adaptive K-singular value decomposition (K-SVD) dictionary learning to extract noise profiles and suppress noisy signals. To validate the feasibility of our method, we apply machine learning to measured data from two distinct observation areas. The measured data were analyzed and processed, and the results were compared with the robust results. This method can effectively eliminate large-scale strong interference in time domain sequences and preserve more low-frequency slow change information and high-quality signals in the reconstructed signals. The apparent resistivity phase curve of synthetic data is smoother and more continuous, and the data quality in the low-frequency range is significantly improved. The results can more accurately and reliably reflect underground electrical structure information.