Reduce Background Noise Research Articles

Detection of foreign materials on Semen Ziziphi Spinosae using hyperspectral imaging technology coupled with convolutional neural networks

The efficacy of Semen Ziziphi Spinosae, a valued medicinal material, can be compromised by the presence of foreign materials, which may also worsen patient conditions and lead to complications. Traditional machine vision techniques often struggle to identify foreign entities that closely resemble Semen Ziziphi Spinosae in color and shape. This study investigates the application of hyperspectral imaging technology for the detection and differentiation of four types of foreign materials (moldy Semen Ziziphi Spinosae shell, wood, and stone) in processing industries. High-resolution hyperspectral imagery was subjected to image segmentation and background noise reduction to separate the contours of the samples within the images. The average spectral signatures of the regions of interest were extracted to construct models such as Convolutional Neural Networks (CNN), Support Vector Machines (SVMs), Mahalanobis distance, Deep Belief Networks, and Generative Adversarial Networks. These models were employed to extract spectral information indicative of foreign matter within the hyperspectral data to identify foreign materialss in Semen Ziziphi Spinosae. Subsequently, the classification outcomes were mapped onto the original hyperspectral images, enabling a visual representation of foreign matter within the seeds. The classification performance of alternative models was compared with that of the CNN model. The results demonstrate that a CNN trained with spectral information from hyperspectral data can accurately identify foreign materialss in Semen Ziziphi Spinosae. The model underwent 30 iterations, achieving an accuracy rate of 99% with a root mean square error (RMSE) of 0.62 for the validation detection, and an accuracy rate of 98% with an RMSE of 0.62 for the validation set.

Integration of Sensory Memory Process Display System for Gait Recognition

AbstractGait is among the most dependable, accurate, and secure methods of biometric identification. However, high power consumption and low computing capability are two major obstacles on wearable sensors‐based gait recognition system. In this work, an integrated system is reported combining a triboelectric nanogenerator (TENG), a memristor (Ag/HfOx/Pt), and perovskite‐based multicolor LEDs (PMCLED) for the visualization and recognition of foot patterns through signal‐on‐none and multi‐wavelength on‐device preprocessing. The flexible TENG acts as a sensory receptor, generating voltage based on the duration and intensity of pressure, which in turn promotes voltage‐triggered synaptic plasticity in the memristor. The PMCLED, with its threshold switching and multi‐wavelength emission characteristics, enables nonlinear filtering and amplification of the synaptic signal from the memristor, resulting in a simplified system design and reduced background noise. Additionally, the effectiveness of on‐device preprocessing is validated based on a 5 × 5 array of integrated devices and software‐built neural network for foot pattern visualization and recognition. The proposed system is able to recognize the on‐device preprocessed images with high accuracy, indicating great potentials in both healthcare monitoring and human‐machine interaction.

Charge-coupled device readout by digital-correlated double sampling

Charge-coupled devices (CCDs) play crucial roles in astronomy owing to their widespread use in the optical band, offering high sensibility, low noise, high dynamic range, and high spatial resolution. Recent advancements in CCDs have focused on improving the sub-electron noise levels for particle detection and enhancing readout speeds through simulation studies. The main objective of this study is to replace the analog processing of CCD signals using the digital-correlated double sampling (DCDS) technique. DCDS allows post-acquisition noise correction through intermittent sampling of an internal reference voltage to provide compact and flexible performance. In this study, DCDS was evaluated using two digital processing systems, namely, a 2.5 mega-samples per second (MSPS) 24-bit analog-to-digital converter (ADC) board and a 250 MSPS 16-bit ADC field-programmable-gate-array( FPGA)-based buffer memory board. The readout noise value at 74 kpix/s (7.1 e) was a significant improvement over that obtained with analog processing (9.7 e). The DCDS implementation demonstrates optimal signal-to-noise ratio for a wide range of readout speeds. Parameters such as the sample positions per pixel, number of samples, and number of pixels were identified to be essential in achieving an accurate gain value. Finally, hardware implementation of the DCDS IP core algorithm on a Xilinx Zynq-7000 AP system-on-a-chip (SoC) showed a significant improvement in power dissipation (7.1 W) compared to the analog Monsoon correlated double sample (CDS) circuit (13.6 W). The DCDS IP core implementation also showed a background noise reduction of up to 34% compared to DCDS offline readout processing using a Python algorithm.

Demonstration of a container-less method for investigating high-temperature alloy properties using ED-XRD.

As new alloys are being developed for additive manufacturing (AM) applications, questions related to the temperature-dependent structural and compositional stability of these alloys remain. In this work, the benefits and limitations of a unique method for testing this stability are presented. This system employs the use of polychromatic synchrotron light to perform energy-dispersive x-ray diffraction (ED-XRD) on an electrostatically levitated sample at high temperatures. In comparison with a traditional angular-dispersive setup, the container-less electrostatic levitation method has unique advantages, including quicker acquisition times, simultaneous compositional information through fluorescence emissions, a reduction in background noise, and, importantly, concurrent/subsequent measurement of thermophysical properties. This combined method is ideal for phase transition studies by holding the levitated sample at a stable position and temperature through controlled heating and temperature management. To illustrate these capabilities, we show ED-XRD data of the well-known martensitic phase transition (hcp to bcc) in Ti-6Al-4V. In addition, results from the novel alloy Ni51Cu44Cr5 are presented. This alloy is shown to maintain an fcc structure upon heating. However, the concentration of Cu is reduced at high temperatures, resulting in a decrease in the lattice constant. As concurrent thermophysical properties are probed, these preliminary structure and composition experiments demonstrate the capabilities of this technique to determine the composition-processing-structure-properties of metal alloys for AM.

Advancing Leukocyte Classification: A Cutting‐Edge Deep Learning Approach for AI‐Driven Clinical Diagnosis

ABSTRACTWhite blood cells (WBCs) are crucial components of the immune system, responsible for detecting and eliminating pathogens. Accurate detection and classification of WBCs are essential for various clinical diagnostics. This study aims to develop an AI framework for detecting and classifying WBCs from microscopic images using a customized YOLOv5 model with three key modifications. Firstly, the C3 module in YOLOv5's backbone is replaced with the innovative C3TR structure to enhance feature extraction and reduce background noise. Secondly, the BiFPN is integrated into the neck to improve feature localization and discrimination. Thirdly, an additional layer in the head enhances detection of small WBCs. Experiments on the BCCD dataset, comprising 352 microscopic blood smear images with leukocytes, demonstrated the framework's superiority over state‐of‐the‐art methods, achieving 99.4% accuracy. Furthermore, the model exhibits computational efficiency, operating over five times faster than existing YOLO models. These findings underscore the framework's promise in medical diagnostics, showcasing deep learning's supremacy in automated cell classification.

Loose particle Detection: The optimal detection condition and weak loose particle impulse extraction

To achieve effective detection of loose particles within small cavities in microelectronic devices, this paper proposes the optimal detection conditions of loose particles in ceramic packaging for microelectronic devices based on simulation, and presents a method for weak signal reconstruction using weighted sparse representation. To address the challenge of ineffective detection of loose particles under recommended vibration conditions, a particle-cavity collision dynamics model is established. Subsequently, the detection laws of loose particles under different accelerations, frequencies, and cavity heights are studied through simulation, leading to the establishment of optimal detection conditions for microelectronic devices with varying cavity heights. To address the issue of weak impulses being submerged in background noise under optimal detection conditions, sparse representation is utilized for signal reconstruction. First, a Laplace wavelet dictionary is constructed according to the impulse characteristics. Second, the generalized minimax-concave (GMC) penalty function is applied as a sparse regularization term to preserve signal amplitude. Meanwhile, a weight matrix based on kurtosis and singular value is designed to threshold sparse coefficients. The results demonstrate that the proposed optimal detection conditions and signal reconstruction method effectively detect loose particles. Compared with other algorithms, the proposed method reduces background noise in the particle impact noise detection (PIND) signals while maintaining impulse amplitude; it also improves signal reconstruction accuracy and offers valuable insights into effective loose particle detection in microelectronic packaging devices.

An elastic piezoelectric nanomembrane with double noise reduction for high-quality bandpass acoustics

Polymer piezoelectrics with high electromechanical energy conversion (HEEC) are very promising for flexible acoustoelectric devices. However, reducing thickness and improving ordered polarization and ferroelectricity while maintaining high mechanical strength pose enormous fabrication challenges for polymer piezoelectric membranes—additionally, noise management in the acoustoelectric conversion remains an open issue. Here, we present a hydro-levitation superspreading approach for fabricating polymer nanomembranes with ordered crystalline phases and sub-nanostructures on the water surface. The elastic piezoelectric nanomembrane (EPN) is only 335 nanometers thick and consists of a conductance-stable piezoelectric layer sandwiched between two elastic damping layers. Such an all-in-one EPN can reduce background noise with low autocorrelation in the environment, suppress spurious noise caused by poor circuit contact, and achieve bandpass filtering of acoustic signals at human voice frequencies. This nanomembrane holds promise in repairing the auditory system of patients with tympanic membrane perforation and in a wide range of other acoustoelectric conversion fields.

Optical Properties and Applications of Diffraction Grating Using Localized Surface Plasmon Resonance with Metal Nano-Hemispheres.

This study investigates the optical properties of diffraction gratings using localized surface plasmon resonance (LSPR) with metal nano-hemispheres. We fabricated metal nano-hemisphere gratings (MNHGS) with Ga, Ag, and Au and examined their wavelength-selective diffraction properties. Our findings show that these gratings exhibit peak diffraction efficiencies at 300 nm, 500 nm, and 570 nm, respectively, corresponding to the LSPR wavelengths of each metal. The MNHGs were created through thermal nanoimprint and metal deposition, followed by annealing. The experimental and simulation results confirmed that the MNHGs selectively diffract light at their resonance wavelengths. Applying these findings to third-order nonlinear laser spectroscopy (MPT-TG method) enhances measurement sensitivity by reducing background noise through the selective diffraction of pump light while transmitting probe light. This innovation promises a highly sensitive method for observing subtle optical phenomena, enhancing the capabilities of nonlinear laser spectroscopy.

Enhanced Blue Band Vegetation Index (The Re-Modified Anthocyanin Reflectance Index (RMARI)) for Accurate Farmland Shelterbelt Extraction

Farmland shelterbelts are aimed at farmland protection and productivity improvement, environmental protection and ecological balance, as well as land use planning and management. Farmland shelterbelts play a vital role in determining the structural integrity and overall effectiveness of farmland, and assessing the dynamic changes within these protective forests accurately and swiftly is essential to maintaining their protective functions as well as for policy formulation and effectiveness evaluation in relevant departments. Traditional methods for extracting farmland shelterbelt information have faced significant challenges due to the large workload required and the inconsistencies in the accuracy of existing methods. For example, the existing vegetation index extraction methods often have significant errors, which remain unresolved. Therefore, developing a more efficient extraction method with greater accuracy is imperative. This study focused on Youyi Farm in Heilongjiang Province, China, utilizing satellite data with spatial resolutions ranging from 0.8 m (GF-7) to 30 m (Landsat). By taking into account the growth cycles of farmland shelterbelts and variations in crop types, the optimal temporal window for extraction is identified based on phenological analysis. The study introduced a new index—the Re-Modified Anthocyanin Reflectance Index (RMARI)—which is an improvement on existing vegetation indexes, such as the NDVI and the improved original ARI. Both the accuracy and extraction results showed significant improvements, and the feasibility of the RMARI was confirmed. The study proposed four extraction schemes for farmland shelterbelts: (1) spectral feature extraction, (2) extraction using vegetation indexes, (3) random forest extraction, and (4) RF combined with characteristic index bands. The extraction process was implemented on the GEE platform, and results from different spatial resolutions were compared. Results showed that (1) the bare soil period in May is the optimal time period for extracting farmland shelterbelts; (2) the RF method combined with characteristic index bands produces the best extraction results, effectively distinguishing shelterbelts from other land features; (3) the RMARI reduces background noise more effectively than the NDVI and ARI, resulting in more comprehensive extraction outcomes; and (4) among the satellite images analyzed—GF-7, Planet, Sentinel-2, and Landsat OLI 8—GF-7 achieves the highest extraction accuracy (with a Kappa coefficient of 0.95 and an OA of 0.97), providing the most detailed textural information. However, comprehensive analysis suggests that Sentinel-2 is more suitable for large-scale farmland shelterbelt information extraction. This study provides new approaches and technical support for periodic dynamic forestry surveys, providing valuable reference points for agricultural ecological research.

Compressed sensing reconstruction for high-SNR, rapid dissolved 129Xe gas exchange MRI.

Three-dimensional hyperpolarized 129Xe gas exchange imaging suffers from low SNR and long breath-holds, which could be improved using compressed sensing (CS). The purpose of this work was to assess whether gas exchange ratio maps are quantitatively preserved in CS-accelerated dissolved-phase 129Xe imaging and to investigate the feasibility of CS-dissolved 129Xe imaging with reduced-cost natural abundance (NA) xenon. 129Xe gas exchange imaging was performed at 1.5 T with a multi-echo spectroscopic imaging sequence. A CS reconstruction with an acceleration factor of 2 was compared retrospectively with conventional gridding reconstruction in a cohort of 16 healthy volunteers, 5 chronic obstructive pulmonary disease patients, and 23 patients who were hospitalized following COVID-19 infection. Metrics of comparison included normalized mean absolute error, mean gas exchange ratio, and red blood cell (RBC) image SNR. Dissolved 129Xe CS imaging with NA xenon was assessed in 4 healthy volunteers. CS reconstruction enabled acquisition time to be halved, and it reduced background noise. Median RBC SNR increased from 6 (2-18) to 11 (2-100) with CS, and there was strong agreement between CS and gridding mean ratio map values (R2 = 0.99). Image fidelity was maintained for gridding RBC SNR > 5, but below this, normalized mean absolute error increased nonlinearly with decreasing SNR. CS increased the mean SNR of NA 129Xe images 3-fold. CS reconstruction of dissolved 129Xe imaging improved image quality with decreased scan time, while preserving key gas exchange metrics. This will benefit patients with breathlessness and/or low gas transfer and shows promise for NA-dissolved 129Xe imaging.

Enhanced CRISPR/Cas-Based Immunoassay through Magnetic Proximity Extension and Detection.

Clustered regularly interspaced short palindromic repeats (CRISPR)/Cas-associated systems have recently emerged as a focal point for developing next-generation molecular diagnosis, particularly for nucleic acid detection. However, the detection of proteins is equally critical across diverse applications in biology, medicine, and the food industry, especially for diagnosing and prognosing diseases like cancer, Alzheimer's and cardiovascular conditions. Despite recent efforts to adapt CRISPR/Cas systems for protein detection with immunoassays, these methods typically achieved sensitivity only in the femtomolar to picomolar range, underscoring the need for enhanced detection capabilities. To address this, we developed CRISPR-AMPED, an innovative CRISPR/Cas-based immunoassay enhanced by magnetic proximity extension and detection. This approach combines proximity extension assay (PEA) with magnetic beads that converts protein into DNA barcodes for quantification with effective washing steps to minimize non-specific binding and hybridization, therefore reducing background noise and increasing detection sensitivity. The resulting DNA barcodes are then detected through isothermal nucleic acid amplification testing (NAAT) using recombinase polymerase amplification (RPA) coupled with the CRISPR/Cas12a system, replacing the traditional PCR. This integration eliminates the need for thermocycling and bulky equipment, reduces amplification time, and provides simultaneous target and signal amplification, thereby significantly boosting detection sensitivity. CRISPR-AMPED achieves attomolar level sensitivity, surpassing ELISA by over three orders of magnitude and outperforming existing CRISPR/Cas-based detection systems. Additionally, our smartphone-based detection device demonstrates potential for point-of-care applications, and the digital format extends dynamic range and enhances quantitation precision. We believe CRISPR-AMPED represents a significant advancement in the field of protein detection.

Non-uniform optical phased array based on dual-adaption genetic algorithm improved by chaos sequence

To address the issue of diminishing peak side lobe levels (PSLL) in non-uniform optical phased array (OPA) as steering angle increases, we introduce a dual-adaption genetic algorithm (DAGA) based on chaos sequence to optimize the antenna array layout. By leveraging chaos mapping traversal and randomness, this approach enhances the diversity of the initial antenna layout, thereby improving the algorithm's capacity to escape local optima. Concurrently, we also reduce background noise during the array steering process to enhance PSLL at large steering angle. In this study, we optimize non-uniform antenna arrays with 64-, 128-, and 256-channels. The results demonstrate that at a steering angle of 80°, the PSLL is improved by 2.18, 2.81, and 3.59 dB, respectively, compared to the conventional genetic algorithm (GA). Notably, for a 256-channel array, the PSLL can be optimized to an impressive -18.46 dB using this method. To our knowledge, this represents the lowest PSLL achieved for an equivalent number of channels. Our research offers valuable insights for the practical implementation of OPAs as transmitters in chip-scale frequency modulated continuous wave (FMCW) light detection and ranging (LiDAR) systems.

Microfluidic-enabled aptamer-modified liposomal probes for targeted transient triplet differential photoacoustic imaging

Photoacoustic (PA) imaging, merging high spatial resolution and deep tissue penetration, holds promise for biomedical applications, particularly cancer diagnosis. The effectiveness of PA imaging heavily relies on the use of contrast agents that enhance the PA signal. However, the efficient preparation of targeted PA contrast agents remains a challenge. Here, we report the development of microfluidic-enabled aptamer-modified liposomal probes for targeted transient triplet differential (TTD) PA imaging. Utilizing projection micro stereolithography (PµSL) 3D printing, we fabricated cost-effective microfluidic chips for the rapid synthesis of methylene blue (MB)-loaded anti-programmed cell death ligand-1 (anti-PDL1) aptamer-modified liposomes (Apt-MB-Lip). We conducted the TTD-PA imaging of Apt-MB-Lip to improve imaging sensitivity by reducing background noise. In vivo TTD-PA experiments demonstrated the superior targeting ability and sustained presence of the Apt-MB-Lip in tumors. Our findings underscore the potential of these targeted probes for advanced diagnostic and therapeutic applications.

Fault Detection of Rotating Machines Using poly-Coherent Composite Spectrum of Measured Vibration Responses with Machine Learning

This study presents an efficient vibration-based fault detection method for rotating machines utilising the poly-coherent composite spectrum (pCCS) and machine learning techniques. pCCS combines vibration measurements from multiple bearing locations into a single spectrum, retaining amplitude and phase information while reducing background noise. The use of pCCS significantly reduces the number of extracted parameters in the frequency domain compared to using individual spectra at each measurement location. This reduction in parameters is crucial, especially for large industrial rotating machines, as processing and analysing extensive datasets demand significant computational resources, increasing the time and cost of fault detection. An artificial neural network (ANN)-based machine learning model is then employed for fault detection using these reduced extracted parameters. The methodology is developed and validated on an experimental rotating machine at three different speeds: below the first critical speed, between the first and second critical speeds, and above the second critical speed. This range of speeds represents the diverse dynamic conditions commonly encountered in industrial settings. This study examines both healthy machine conditions and various simulated fault conditions, including misalignment, rotor-to-stator rub, shaft cracks, and bearing faults. By combining the pCCS technique with machine learning, this study enhances the reliability, efficiency, and practical applicability of fault detection in rotating machines under varying dynamic conditions and different machine conditions.

Measurement of photo- and radio-luminescence of thin ThF[formula omitted] films

We conducted measurements on the photo- and radio-luminescence of thin ThF4 films in both the UV and visible ranges. In the UV range, we found that both luminescences are at a similar level as the internal dark counting noise of the photo-multiplier-tube (PMT). Our results suggest that thin ThF4 crystals could be used as a target for the search for 229mTh and as a medium for the future nuclear clock. The measurements indicate that using a small and thin ThF4 film can reduce background noise while maintaining the signal at the same level, achieved by increasing the 229Th enrichment. Our developed apparatus is now ready for direct measurements of 229mTh excitation and decay in ThF4.

Dual-branch collaborative Siamese network for visual tracking

This paper introduces a dual-branch collaborative Siamese network architecture, CoSiNet, for visual object tracking. The network has a shallow branch for precise target localization and a deep branch for extracting rich semantic information. It integrates two specialized modules - Channel Attention and Spatial Channel Attention Feature Enhancement - for improved feature extraction and background noise reduction. An Adaptive Fusion Module combines response maps from both branches to create an enriched final response map. Experimental results show our algorithm outperforms several contemporary techniques on four different public datasets (OTB100, OTB50, DTB70, TColor128), demonstrating the competitiveness of CoSiNet.

A comparative review of the application value of FAPI PET/CT and 18F-FDG PET/CT in lung cancer.

Fibroblast activation protein inhibitor (FAPI) positron emission tomography/computed tomography (PET/CT) is a multimodal imaging technique that combines PET and CT, utilizing FAP inhibitors as radiotracers. Fibroblast activation protein, a serine protease highly expressed in many epithelial tumor-associated fibroblasts, plays a crucial role in tumor stroma formation and remodeling. Through the detection of FAP expression, FAPI PET/CT facilitates the diagnosis and staging of both benign and malignant pulmonary tumors. In contrast to traditional fluorine-18-fluorodeoxyglucose (18F-FDG) PET/CT focusing on glucose metabolism, FAPI PET/CT offers benefits such as enhanced specificity, reduced background noise, accelerated imaging speed, and decreased radiation exposure. This review provides an overview of the progress in applying FAPI PET/CT and 18F-FDG PET/CT in pulmonary malignancies and discusses current challenges and future prospects.

Integration of concentration gradient generator with competitive PCR in a droplet for rapid nucleic acid quantification

Competitive PCR is an efficient way for the measurement of nucleic acids without requiring a standard curve. It uses a competitor template mimicking the target sequence for direct comparison and quantification during amplification. However, manually preparing various concentrations for competitive PCR is labor-intensive. Additionally, target and competitor DNA bands are often inadequately separated on gels due to their similar sizes. This leads to inaccurate distinction and imprecise measurement of bandwidths and intensities, resulting in high standard deviations in quantification. Thus, this study presents an alternative way to combine droplet competitive PCR with the concentration gradient generator in a microfluidic device that simplifies competitive PCR preparation and provides precise control over reaction conditions and sample handling. Generating a wide range of competitor-to-target ratios in a single experiment enhances statistical reliability and isolating individual reactions in droplets reduces background noise and increases sensitivity. Additionally, it eliminates gel electrophoresis, improves consistency and reproducibility, requires smaller sample and reagent volumes, and allows direct sample quantification through a calibration curve for fast, simple quantification. We envision that our platform can offer a promising alternative to digital PCR, addressing its challenges and driving progress in molecular biology and diagnostics.

Highly sensitive microfluidic sensor using integrated optical fiber and real-time single-cell Raman spectroscopy for diagnosis of pancreatic cancer

Pancreatic cancer is notoriously lethal due to its late diagnosis and poor patient response to treatments, posing a significant clinical challenge. This study introduced a novel approach that combines a single-cell capturing platform, tumor-targeted silver (Ag) nanoprobes, and precisely docking tapered fiber integrated with Raman spectroscopy. This approach focuses on early detection and progression monitoring of pancreatic cancer. Utilizing tumor-targeted Ag nanoparticles and tapered multimode fibers enhances Raman signals, minimizes light loss, and reduces background noise. This advanced Raman system allows for detailed molecular spectroscopic examination of individual cells, offering more practical information and enabling earlier detection and accurate staging of pancreatic cancer compared to conventional multicellular Raman spectroscopy. Transcriptomic analysis using high-throughput gene screening and transcriptomic databases confirmed the ability and accuracy of this method to identify molecular changes in normal, early, and metastatic pancreatic cancer cells. Key findings revealed that cell adhesion, migration, and the extracellular matrix are closely related to single-cell Raman spectroscopy (SCRS) results, highlighting components such as collagen, phospholipids, and carotene. Therefore, the SCRS approach provides a comprehensive view of the molecular composition, biological function, and material changes in cells, offering a novel, accurate, reliable, rapid, and efficient method for diagnosing and monitoring pancreatic cancer.

Alaryngeal Speech Enhancement for Noisy Environments Using a Pareto Denoising Gated LSTM

Loss of the larynx significantly alters natural voice production, requiring alternative communication modalities and rehabilitation methods to restore speech intelligibility and improve the quality of life of affected individuals. This paper explores advances in alaryngeal speech enhancement to improve signal quality and reduce background noise, focusing on individuals who have undergone laryngectomy. In this study, speech samples were obtained from 23 Lithuanian males who had undergone laryngectomy with secondary implantation of the tracheoesophageal prosthesis (TEP). Pareto optimized gated LSTM was trained on tracheoesophageal speech data to recognize complex temporal connections and contextual information in speech signals. The system was able to distinguish between actual speech and various forms of noise and artifacts, resulting in a 25% drop in the mean signal-to-noise ratio (SNR) compared to other approaches. According to acoustic analysis, the system significantly decreased the number of unvoiced frames (PVF) from 40% to 10% while maintaining stable proportions of voiced frames (PVS) and average voicing evidence (AVE), indicating the accuracy of the approach in selectively attenuating noise and undesired speech artifacts while preserving important speech information.