Domain Features Research Articles

Graph neural network incorporating time-varying frequency domain features with application in spatial wind speed field prediction

Precise forecasting of wind speed is vital to guarantee safe travel on bridges. Nevertheless, current research primarily concentrates on single-point prediction. When it comes to forecasting spatial wind fields, graph neural networks prove to be powerful methods, but many of them have yet to take into account the impact of frequency domain attributes. To address this, a novel model called the graph neural network with time-varying frequency features (GTF) is proposed. Its core layer employs wavelet transforms in matrix form to extract various frequency sub-series, followed by the use of adaptive adjacency matrices to identify their spatial characteristics. Furthermore, aggregating all frequency band information and exploring spatial features further through multi-kernel convolutions. The predictive performance of different models for wind speed forecasting is assessed by utilizing spatial wind field data collected on a large-span bridge. Experimental results demonstrate that spatiotemporal model GTF outperforms the other models in terms of predictive accuracy. The quantity of wind observation points and their level of correlation exert a certain impact on the GTF model, while hyperparameters such as stacking depth and wavelet decomposition parameters have minimal effects. Finally, recommended parameters for the GTF model are provided.

AVATAR: Adversarial self-superVised domain Adaptation network for TARget domain

This paper introduces AVATAR (adversarial self-supervised domain adaptation network for target domain), a novel unsupervised domain adaptation method designed to address the challenge of transferring knowledge from a well-labeled source domain to an unlabeled target domain. AVATAR’s key contributions lie in its unique combination of adversarial learning and self-supervised learning techniques, which enhance the model’s adaptability and accuracy in new, unlabeled environments. The technical innovations of AVATAR include a domain adversarial learning component that reduces domain discrepancy by aligning source and target domain features in a shared feature space, a self-supervised learning module that leverages pseudo-labels and instance weights to refine target domain discrimination boundaries, and a sample selection strategy guided by within-cluster distances to focus on aligning informative samples while mitigating the impact of outliers. By integrating these components, AVATAR provides a comprehensive framework for tackling complex unsupervised domain adaptation tasks, particularly when the domain gap is significant. The method balances domain-invariant feature learning with domain-specific adjustments, enabling effective adaptation to dynamically changing environments. Extensive experiments on multiple benchmark datasets demonstrate AVATAR’s superior performance compared to existing domain adaptation methods, especially in scenarios with limited labeled target domain data. These results highlight AVATAR’s potential as a versatile and robust solution for domain adaptation challenges in various real-world applications.

Machine Learning Predicts Phenoconversion from Polysomnography in Isolated REM Sleep Behavior Disorder.

Isolated rapid eye movement (REM) sleep behavior disorder (iRBD) is a prodromal stage of alpha-synucleinopathies. This study aimed at developing a fully-automated machine learning framework for the prediction of phenoconversion in patients with iRBD by using data recorded during polysomnography (PSG). A total of 66 patients with iRBD were included, of whom 18 converted to an overt alpha-synucleinopathy within 2.7 ± 1.0 years. For each patient, a baseline PSG was available. Sleep stages were scored automatically, and time and frequency domain features were derived from electromyography (EMG) and electroencephalography (EEG) signals in REM and non-REM sleep. Random survival forest was employed to predict the time to phenoconversion, using a four-fold cross-validation scheme and by testing several combinations of features. The best test performances were obtained when considering EEG features in REM sleep only (Harrel's C-index: 0.723 ± 0.113; Uno's C-index: 0.741 ± 0.11; integrated Brier score: 0.174 ± 0.06). Features describing EEG slowing had high importance for the machine learning model. This is the first study employing machine learning applied to PSG to predict phenoconversion in patients with iRBD. If confirmed in larger cohorts, these findings might contribute to improving the design of clinical trials for neuroprotective treatments.

A step length estimation method based on frequency domain feature analysis and gait recognition for pedestrian dead reckoning

Purpose Step length is a key factor for pedestrian dead reckoning (PDR), which affects positioning accuracy and reliability. Traditional methods are difficult to handle step length estimation of dynamic gait, which have larger error and are not adapted to real walking. This paper aims to propose a step length estimation method based on frequency domain feature analysis and gait recognition for PDR, which considers the effects of real-time gait. Design/methodology/approach The new step length estimation method transformed the acceleration of pedestrians from time domain to frequency domain, and gait characteristics of pedestrians were obtained and matched with different walking speeds. Findings Many experiments are conducted and compared with Weinberg and Kim models, and the results show that the average errors of the new method were improved by about 2 meters to 5 meters. It also shows that the proposed method has strong stability and device robustness and meets the accuracy requirements of positioning. Originality/value A sliding window strategy used in fast Fourier transform is proposed to implement frequency domain analysis of the acceleration, and a fast adaptive gait recognition mechanism is proposed to identify gait of pedestrians.

Comparative analysis of features and classification techniques in breast cancer detection for Biglycan biomarker images.

Breast cancer (BC) is considered the world's most prevalent cancer. Early diagnosis of BC enables patients to receive better care and treatment, hence lowering patient mortality rates. Breast lesion identification and classification are challenging even for experienced radiologists due to the complexity of breast tissue and variations in lesion presentations. This work aims to investigate appropriate features and classification techniques for accurate breast cancer detection in 336 Biglycan biomarker images. The Biglycan biomarker images were retrieved from the Mendeley Data website (Repository name: Biglycan breast cancer dataset). Five features were extracted and compared based on shape characteristics (i.e., Harris Points and Minimum Eigenvalue (MinEigen) Points), frequency domain characteristics (i.e., The Two-dimensional Fourier Transform and the Wavelet Transform), and statistical characteristics (i.e., histogram). Six different commonly used classification algorithms were used; i.e., K-nearest neighbours (k-NN), Naïve Bayes (NB), Pseudo-Linear Discriminate Analysis (pl-DA), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF). The histogram of greyscale images showed the best performance for the k-NN (97.6%), SVM (95.8%), and RF (95.3%) classifiers. Additionally, among the five features, the greyscale histogram feature achieved the best accuracy in all classifiers with a maximum accuracy of 97.6%, while the wavelet feature provided a promising accuracy in most classifiers (up to 94.6%). Machine learning demonstrates high accuracy in estimating cancer and such technology can assist doctors in the analysis of routine medical images and biopsy samples to improve early diagnosis and risk stratification.

Entropy-guided robust feature domain adaptation for electroencephalogram-based cross-dataset drowsiness recognition

To accurately identify driver drowsiness using Electroencephalogram (EEG), a significant amount of time is typically required to gather data from either the same subject or multiple subjects under the same experimental condition. The prolonged period required for data collection impedes the practical application of EEG. In this paper, we consider the challenging task of cross-dataset driver drowsiness recognition, where the EEG data collected by different devices are expected to be conveniently recognized by a classifier trained on an existing dataset. In order to solve the problem of distribution drift, we propose an Entropy-Guided Robust Feature (EGRF) adaptation framework. This framework utilizes the Entropy Minimization (EM) technique for domain alignment and an ensemble-like structure, consisting of multiple branch classifiers and a dropout layer, to enhance the robustness. The proposed method has been tested across two public datasets and achieves 2-class recognition accuracies of 77.4% and 85.9%. The innovative feature-robust block, combined with the EM loss, leads to substantial performance improvement, proving the effectiveness of our framework for cross-dataset driver drowsiness recognition. Our research demonstrates a promising direction for development of a calibration-free driver drowsiness monitoring system in the future.

Does mental fatigue affect performance in racket sports? A systematic review

Mental fatigue impairs performance across several sports domains. However, a systematic review on its effects on racket sports performance has been lacking due to the previous scarcity of studies. This review aims to provide a comprehensive review the effects of mental fatigue on racket players’ performance, with a discussion of the underlying mechanisms. A thorough search was conducted across five databases, including Web of Science, PubMed, SCOPUS, SPORTDiscus (via EBSCOhost), and the Psychological and Behavioral Science Collection (via EBSCOhost). The PICOS framework established the inclusion criteria: (1) healthy racket sports players; (2) induction of mental fatigue in both field and laboratory settings; (3) comparison of mental fatigue interventions with a control group (e.g., watching a movie or reading a magazine); (4) assessment of performance outcomes, including physical performance, skilled performance, and perceptual-cognitive performance; and (5) randomized controlled trials (RCTs), non-randomized controlled trials (non-RCTs), and non-randomized non-controlled trials. Mental fatigue manipulation, subjective evaluation, and (neuro)physiological markers were synthesized to support the successful induction of mental fatigue. Performance was categorized into tennis, table tennis, badminton, and padel based on the characteristics of specific racket sports domains. Secondary outcomes, such as the rate perception of effort (RPE) and motivation, were synthesized to explain the mechanisms based on the prominent theory of the Psychobiological model of endurance performance. Six studies revealed that mental fatigue impacts stroke performance in table tennis, affecting speed, accuracy, faults, and only second-serve accuracy in tennis. The response time of psychomotor performance increased in table tennis, padel, and badminton. Meanwhile, mental fatigue increased the RPE and remained unchanged in heart rate, blood glucose, and lactate, consistent with the Psychobiological model of endurance performance. Additionally, attention is suggested as a significant underlying psychobiological factor.

The supernumerary robotic limbs of brain-computer interface based on asynchronous steady-state visual evoked potential

Brain-computer interface (BCI) based on steady-state visual evoked potential (SSVEP) have attracted much attention in the field of intelligent robotics. Traditional SSVEP-based BCI systems mostly use synchronized triggers without identifying whether the user is in the control or non-control state, resulting in a system that lacks autonomous control capability. Therefore, this paper proposed a SSVEP asynchronous state recognition method, which constructs an asynchronous state recognition model by fusing multiple time-frequency domain features of electroencephalographic (EEG) signals and combining with a linear discriminant analysis (LDA) to improve the accuracy of SSVEP asynchronous state recognition. Furthermore, addressing the control needs of disabled individuals in multitasking scenarios, a brain-machine fusion system based on SSVEP-BCI asynchronous cooperative control was developed. This system enabled the collaborative control of wearable manipulator and robotic arm, where the robotic arm acts as a "third hand", offering significant advantages in complex environments. The experimental results showed that using the SSVEP asynchronous control algorithm and brain-computer fusion system proposed in this paper could assist users to complete multitasking cooperative operations. The average accuracy of user intent recognition in online control experiments was 93.0%, which provides a theoretical and practical basis for the practical application of the asynchronous SSVEP-BCI system.

Gated recurrent unit and temporal convolutional network with soft thresholding and attention mechanism for tool wear prediction

Predicting tool wear significantly improves cutting efficiency and quality in intelligent manufacturing. Traditional recurrent neural networks suffer from vanishing or exploding gradients and need to be improved prediction accuracy. Therefore, this paper proposes a gated recurrent unit and temporal convolutional network with soft thresholding and attention mechanism (TCN-BiGRU-SA). Monotonicity, robustness, and trendability indicators are used to assess time and frequency domain features. Then, evaluation results of these three indicators are weighted to identify the sensitive features with the degradation trend. The attention mechanism is proposed to adaptively adjust the soft thresholding, and the SA is added to TCN-BiGRU to remain helpful features. Finally, the proposed model is validated using an experimental dataset. Compared to the TCN-BiGRU model without the SA mechanism, the predicted results show that the average mean absolute error and root mean square error are reduced by 48.29 % and 36.39 %, respectively.

A one-step fabrication method of flexible magnetostrictive fiber ribbon based on Fe50Co50 alloy and its characteristics study

Magnetostrictive materials are widely used in sensors, actuators and micro-nano electronics because of their excellent performance. However, traditional rigid magnetostrictive materials are difficult to adapt to the flexible and deformable structure of flexible electronic devices. In order to solve the deformation, sensing and control problems in the field of flexible electronics, a one-step new method of is proposed to deposit Fe50Co50 fiber ribbons with reciprocated and loop structures on flexible substrate. Helmholtz coil is designed to test the magnetostrictive positive effect ability of Fe50Co50 ribbon, and its magnetostrictive strain curve is analyzed. Furthermore, frequency domain characteristics of Fe50Co50 ribbon are tested, and the influence of externally driving magnetic field on elastic layer materials and resonance output characteristics is analyzed. The experimental results show that Fe50Co50 ribbon exhibits good low-frequency magnetic field characteristics. And free end displacement of Fe50Co50 ribbon based on loop structure, under 12 mT alternating magnetic field and 134 mT bias magnetic field, reaches a peak-to-peak value of 870 μm for first-order resonance, and 320 μm for second-order resonance. This verifies that Fe50Co50 ribbon possesses the expected properties that magnetostrictive materials should have, and innovatively breaks through the technical bottleneck of manufacturing flexible micro-nano magnetostrictive energy exchange components.

Multivariable model for gait pattern differentiation in elderly patients with hip and knee osteoarthritis: A wearable sensor approach

BackgroundHip and knee osteoarthritis (OA) patients demonstrate distinct gait patterns, yet detecting subtle abnormalities with wearable sensors remains uncertain. This study aimed to assess a predictive model's efficacy in distinguishing between hip and knee OA gait patterns using accelerometer data. MethodParticipants with hip or knee OA underwent overground walking assessments, recording lower limb accelerations for subsequent time and frequency domain analyses. Logistic regression with regularization identified associations between frequency domain features of acceleration signals and OA, and k-nearest neighbor classification distinguished knee and hip OA based on selected acceleration signal features. FindingsWe included 57 knee OA patients (30 females, median age 68 [range 49–89], median BMI 29.7 [range 21.0–45.9]) and 42 hip OA patients (19 females, median age 70 [range 47–89], median BMI 28.3 [range 20.4–37.2]). No significant difference could be found in the time domain's averaged shape of acceleration signals. However, in the frequency domain, five selected features showed a diagnostic ability to differentiate between knee and hip OA. Using these features, a model achieved a 77 % accuracy in classifying gait cycles into hip or knee OA groups, with average precision, recall, and F1 score of 77 %, 76 %, and 78 %, respectively. InterpretationThe study demonstrates the effectiveness of wearable sensors in differentiating gait patterns between individuals with hip and knee OA, specifically in the frequency domain. The results highlights the promising potential of wearable sensors and advanced signal processing techniques for objective assessment of OA in clinical settings.

Novel GIL mechanical fault diagnosis method based on multi-sensor data feature fusion and TDEAVOA-ELM

The gas insulated transmission line (GIL), a crucial component of the power system, faces challenges in mechanical fault diagnosis including difficulties in quantifying sensor signal selection, balancing recognition accuracy, and model training speed. This paper proposes a GIL mechanical fault diagnosis method based on the feature fusion of multi-channel vibration sensor signals and an improved optimization extreme learning machine (ELM). Initially, three optimal signals are selected based on the correlation coefficients of multiple signals, and their time–frequency domain features are extracted. These features are then fused using neighborhood preserving embedding (NPE) and input into the improved optimized ELM model. The enhanced optimization algorithm reduces the likelihood of falling into local optima, thereby improving the model’s recognition performance. Experimental results demonstrate that this method effectively enhances the recognition accuracy of mechanical faults in GIL equipment and enables rapid diagnosis.

Advanced Sensing System for Sleep Bruxism across Multiple Postures via EMG and Machine Learning.

Diagnosis of bruxism is challenging because not all contractions of the masticatory muscles can be classified as bruxism. Conventional methods for sleep bruxism detection vary in effectiveness. Some provide objective data through EMG, ECG, or EEG; others, such as dental implants, are less accessible for daily practice. These methods have targeted the masseter as the key muscle for bruxism detection. However, it is important to consider that the temporalis muscle is also active during bruxism among masticatory muscles. Moreover, studies have predominantly examined sleep bruxism in the supine position, but other anatomical positions are also associated with sleep. In this research, we have collected EMG data to detect the maximum voluntary contraction of the temporalis and masseter muscles in three primary anatomical positions associated with sleep, i.e., supine and left and right lateral recumbent positions. A total of 10 time domain features were extracted, and six machine learning classifiers were compared, with random forest outperforming others. The models achieved better accuracies in the detection of sleep bruxism with the temporalis muscle. An accuracy of 93.33% was specifically found for the left lateral recumbent position among the specified anatomical positions. These results indicate a promising direction of machine learning in clinical applications, facilitating enhanced diagnosis and management of sleep bruxism.

A domain feature decoupling network for rotating machinery fault diagnosis under unseen operating conditions

Operating conditions reflect the mission evolution of rotating machinery in specific application scenarios. The monitoring data under different operating conditions exhibit disparate statistic distributions in terms of amplitude and frequency properties. In the modern operation and maintenance, domain adaptation approaches, which align the feature distributions of source and target domains, are commonly employed to address cross-domain diagnosis challenges. However, the availability of the target domain is serendipitous rather than guaranteed. To meet the engineering requirements, a domain feature decoupling network (DFDN) is proposed to achieve the fault diagnosis of rotating machinery under unseen operating conditions. The core concept of DFDN is to decouple the extracted features into domain-related features and fault-related features. These features are then adaptively integrated into domain-invariant features using a significance fusion method, thereby enabling the feature learning and knowledge transfer from seen source domains to unseen target domains. Furthermore, a self-learning joint optimization strategy is developed for DFDN to facilitate the efficient acquisition of generalized diagnosis knowledge. Two bearing datasets from different test rigs are considered to assess the domain generalization performance of DFDN. The experimental results demonstrate the superiority and potential of this method in coping with zero-shot fault diagnosis under unseen operating conditions.

Prediction of residual life of rotating components based on adaptive dynamic weighting and gated double attention unit

Gears and bearings play vital roles as essential transmission components in mechanical drivetrains. Accurately predicting the remaining useful life (RUL) of these components is paramount to ensure optimal performance and prevent unexpected failures. To enhance the precision of RUL prediction, a novel method has been developed which involves constructing health indicators (HI) and implementing an adaptive dynamic weighting (ADW) on a gated dual attention unit (GDAU). The process commences by extracting multi-dimensional time-frequency domain features from vibration signals, which are then refined using an improved kernel principal component analysis (Adaptive Kernel Principal Component Analysis – AKPCA) to extract key components. Subsequently, the constructed HI is fine-tuned through an optimization process utilizing the exponentially weighted moving average method. Finally, the ADW strategy dynamically adjusts the input weights of the HI, and the GDAU model is employed to predict the RUL of gears and bearings. Experiment and comparison results have validated the effectiveness and advantages of the proposed method.

Semi-supervised learning for real-time anomaly detection in pulsed transfer wire arc additive manufacturing

In Wire-Arc Additive Manufacturing (WAAM), ensuring the quality and integrity of components is of key importance and performing anomaly detection during production is an efficient strategy for preventing defects and maintaining an acceptable quality with lower costs compared to the development of complex supervised learning techniques. This paper presents an approach based on semi-supervised learning for real-time anomaly detection in the production of Inconel 718 components via the Pulsed Transfer WAAM process. The workflow is based on the use of training data obtained by employing established process parameters, similar to what is done in Welding Procedure Qualification Records (WPQRs), to develop a semi-supervised anomaly detection application. The proposed approach involves depositing material using the already established process parameters and collecting the corresponding welding data in terms of welding current and voltage sensor signals. The collected data are then employed to train an unsupervised algorithm by using solely good deposition data to learn hidden complex patterns of normality and hence detect anomalies based on deviations from these patterns. With this aim, global and local features are extracted from the welding current and voltage sensor signals in both time and time-frequency domains via Wavelet Transform technique and a deep learning approach based on a residual convolutional autoencoder. To showcase the effectiveness of the proposed approach, a case study involving wire arc additive manufacturing of Inconel 718 components was conducted. The proposed algorithm was tested and achieved an F-score of 0.895, representing a 30 % improvement over state-of-the-art methods that rely on time domain features for anomaly detection. This research work contributes to the improvement of anomaly detection methodologies, offering substantial advantages over alternative techniques for quality control and reliability of additive manufacturing processes such as WAAM.

State of health estimation for lithium-ion batteries based on multi-scale frequency feature and time domain feature fusion method

Abstract Accurately estimating the state of health (SOH) of lithium-ion batteries is important for improving battery safety performance. The single time-domain feature extraction is hard to efficiently extract discriminative features from strongly nonlinear coupled data, leading to difficulties in accurately estimating the battery SOH. To this end, this paper proposes a multi-scale frequency domain feature and time domain feature fusion method for SOH estimation of lithium-ion batteries based on the Transformer model. Firstly, the voltage, current, temperature and time information of the battery are extracted as time domain features; secondly, the battery signal is processed by a multi-scale filter bank based on Mel-frequency cepstral coefficients (MFCC) to obtain the multi-scale frequency domain features; then, a parallel focusing network (PFN) is designed to fuse the time domain features with the frequency domain features, which yields low-coupling complementary discriminative features; finally, constructing the SOH estimation mechanism based on the Transformer deep network model. The algorithm is validated by NASA and Oxford datasets, the mean's absolute error (MAE) and root mean square error (RMSE) are as low as 0.06% and 0.23%, respectively.

MMDG-DTI: Drug–target interaction prediction via multimodal feature fusion and domain generalization

Recently, deep learning has become the essential methodology for Drug–Target Interaction (DTI) prediction. However, the existing learning-based representation methods embed the prior knowledge encapsulated by the training data and, as such, acquire redundant domain information irrelevant to the DTI prediction, compromising the generalization capability of a deep network to unfamiliar instances. To tackle this limitation, we propose a novel DTI prediction method using Multi-Modal feature fusion and Domain Generalization (MMDG-DTI). Specifically, we first use pre-trained Large Language Models (LLMs) to obtain generalized textual features covering nearly the whole biological text vocabulary, with the capacity to handle unseen samples and extract robust and discriminative features. In parallel, we propose a unified structural feature extractor based on a hybrid Graph Neural Network (GNN). The extractor improves the performance of MMDG-DTI by extracting features from another modality and discarding the representation of domain-specific prior substructures. Then, we integrate the complementary information of LLM and GNN features using an innovative classifier, while enhancing the generalization ability with the help of Domain Adversarial Training (DAT) and contrastive learning. Last, we propose a novel cross-domain evaluation protocol to enhance the predication fidelity in practical applications. The quantitative and visualization results obtained on several benchmarking datasets demonstrate that MMDG-DTI achieves state-of-the-art performance under both single-domain and cross-domain settings, confirming the superiority of the proposed method. The datasets and codes will be available on the project homepage: https://github.com/JU-HuaY/MMDG-DTI.

Bridging spatio-temporal discontinuities in global soil moisture mapping by coupling physics in deep learning

The launch of Soil Moisture Active Passive (SMAP) satellite in 2015 has resulted in significant achievements in global soil moisture mapping. Nonetheless, spatiotemporal discontinuities in the soil moisture products have arisen due to the limitations of its orbit scanning gap and retrieval algorithms. To address these issues, this paper presents a physics-constrained gap-filling method, PhyFill for short. The PhyFill method employs a partial convolutional neural network technique to explore spatial domain features of the original SMAP soil moisture data. Then, it incorporates variations in soil moisture induced by precipitation events and dry-down events as penalty terms in the loss function, thereby accounting for monotonicity and boundary constraints in the physical processes governing the dynamic fluctuations of soil moisture. The PhyFill model was applied to SMAP soil moisture data, resulting in continuous spatially daily soil moisture data on a global scale. Three validation strategies are employed: visual inspection through global pattern, simulated missing-region validation, and soil moisture validation with in situ measurements. The results indicated that the reconstructed soil moisture achieved a higher spatial coverage with satisfactory spatial continuity with neighbouring pixels. The simulated validation of the missing regions revealed that the averaged unbiased root mean square difference (ubRMSD) and correlation coefficient (R) were 0.01 m3/m3 and 0.99, respectively versus the gap filled SMAP product. The core validation sites demonstrated that the reconstructed soil moisture data has a consistent ubRMSD compared with the original SMAP soil moisture data (0.04 m3/m3vs. 0.04 m3/m3). The PhyFill method can generate globally continuous, high accurate soil moisture estimates, providing remarkable support for advanced hydrological applications, e.g., global soil moisture dry-down events and patterns.

A novel speaker verification approach featuring multidomain acoustics based on the weighted city block Minkowski distance

AbstractAccess control is vital in interconnected environments like the Internet of Things, Industry 4.0, and smart connectivity, ensuring authorized access for security. Biometric‐based access, particularly speaker verification (SV), enhances security with unique vocal features, offering nonintrusive authentication with continuous monitoring. Single‐domain features prove insufficient in distinguishing similar traits, prompting latest SV advancements to adopt multidomain‐based speech features. This paradigm addresses the limitations of single‐domain features by amalgamating the merits of individual domains, establishing a cutting‐edge approach. It utilizes cepstral–frequency–time domain feature fusion, achieved via cepstral mean‐variance normalization for generalizability. The weighted city block Minkowski distance is proposed to compare reference and test speech templates. Parameters are computed based on the confusion matrix, template matching distance functions, dynamic acoustic conditions, and additive white Gaussian noise. A deep convolutional neural network classifier is assessed on open‐source LibriSpeech and Speaker in the Wild corpora, surpassing the current methodologies.