Voiceprint Features Research Articles

Voiceprint-based method for sensing droplet generation and mode transition from a coaxial microfluidic device

A voiceprint-based method is proposed for sensing microdroplets generated from a coaxial microfluidic device in this study. Microdroplet holds significant utility in various fields, such as drug delivery and molecular biology. Real-time sensing of droplet generation is crucial for ensuring droplet quality control. Current sensing techniques, such as high-speed vision, are hindered by cost and system complexity limitations. In our approach, voiceprint features were extracted from the sound accompanying microdroplet generation using the short-time Fourier transform (STFT). These features were employed to determine droplet generation frequency and mode transitions. Experimental validation was conducted using a coaxial capillary microfluidic device capable of generating sub-100-micron droplets via controlled flowrates of water and nitrogen gas in the inner and outer capillaries, respectively. The generation frequency from hundreds to thousands hertz were successfully detected in the experiment. Additionally, real-time detections of dripping-jetting and jetting-dripping mode transition were successfully achieved using the proposed voiceprint method. This work offers a simple, robust and cost-effective solution for sensing microdroplets generated from a microfluidic device.

Research on Parkinson's disease recognition algorithm based on sample enhancement

Parkinson's disease patients have early vocal cord damage, and their voiceprint characteristics differ significantly from those of healthy individuals, which can be used to identify Parkinson's disease. However, the samples of the voiceprint dataset of Parkinson's disease patients are insufficient, so this paper proposes a double self-attention deep convolutional generative adversarial network model for sample enhancement to generate high-resolution spectrograms, based on which deep learning is used to recognize Parkinson's disease. This model improves the texture clarity of samples by increasing network depth and combining gradient penalty and spectral normalization techniques, and a family of pure convolutional neural networks (ConvNeXt) classification network based on Transfer learning is constructed to extract voiceprint features and classify them, which improves the accuracy of Parkinson's disease recognition. The validation experiments of the effectiveness of this paper's algorithm are carried out on the Parkinson's disease speech dataset. Compared with the pre-sample enhancement, the clarity of the samples generated by the proposed model in this paper as well as the Fréchet inception distance (FID) are improved, and the network model in this paper is able to achieve an accuracy of 98.8%. The results of this paper show that the Parkinson's disease recognition algorithm based on double self-attention deep convolutional generative adversarial network sample enhancement can accurately distinguish between healthy individuals and Parkinson's disease patients, which helps to solve the problem of insufficient samples for early recognition of voiceprint data in Parkinson's disease. In summary, the method effectively improves the classification accuracy of small-sample Parkinson's disease speech dataset and provides an effective solution idea for early Parkinson's disease speech diagnosis.

Differentiation between depression and bipolar disorder in child and adolescents by voice features

ObjectiveMajor depressive disorder (MDD) and bipolar disorder (BD) are serious chronic disabling mental and emotional disorders, with symptoms that often manifest atypically in children and adolescents, making diagnosis difficult without objective physiological indicators. Therefore, we aimed to objectively identify MDD and BD in children and adolescents by exploring their voiceprint features.MethodsThis study included a total of 150 participants, with 50 MDD patients, 50 BD patients, and 50 healthy controls aged between 6 and 16 years. After collecting voiceprint data, chi-square test was used to screen and extract voiceprint features specific to emotional disorders in children and adolescents. Then, selected characteristic voiceprint features were used to establish training and testing datasets with the ratio of 7:3. The performances of various machine learning and deep learning algorithms were compared using the training dataset, and the optimal algorithm was selected to classify the testing dataset and calculate the sensitivity, specificity, accuracy, and ROC curve.ResultsThe three groups showed differences in clustering centers for various voice features such as root mean square energy, power spectral slope, low-frequency percentile energy level, high-frequency spectral slope, spectral harmonic gain, and audio signal energy level. The model of linear SVM showed the best performance in the training dataset, achieving a total accuracy of 95.6% in classifying the three groups in the testing dataset, with sensitivity of 93.3% for MDD, 100% for BD, specificity of 93.3%, AUC of 1 for BD, and AUC of 0.967 for MDD.ConclusionBy exploring the characteristics of voice features in children and adolescents, machine learning can effectively differentiate between MDD and BD in a population, and voice features hold promise as an objective physiological indicator for the auxiliary diagnosis of mood disorder in clinical practice.

Towards an Environmentally Robust Speech Assistant System for Emergency Medical Services.

Automated speech recognition technology with robust performance in various environments is highly needed by emergency clinicians, but there are few successful cases. One main challenge is the wide variety of environmental interference involved during a typical prehospital care emergency service such as background noises and overlapping speech. To solve this problem, we try to establish an environmentally robust speech assistant system with the help of the proposed personalized speech enhancement (PSE) method, which utilizes the target physician's voiceprint feature to suppress non-target signal components. We demonstrate its potential value using both general public test set and our real EMS test set by evaluating the objective speech quality metrics, DNSMOS, and the recognition accuracy. Hopefully, the proposed method will raise EMS efficiency and security against non-target speech.

MEConformer: Highly representative embedding extractor for speaker verification via incorporating selective convolution into deep speaker encoder

Transformer models have demonstrated superior performance across various domains, including computer vision, natural language processing, and speech recognition. The success of these models can be attributed to their robust parallel capacity and high computation speed, primarily reliant on the attention layer. In the domain of speaker recognition, state-of-the-art results have been achieved using convolutional neural network (CNN) architectures, particularly with speaker embeddings represented by x-vectors and r-vectors. However, existing CNN-based methods tend to focus on local features while overlooking the global dependence of voiceprint features, resulting in the loss of crucial information. Moreover, the presence of noise in audio data is an influential factor that cannot be disregarded, as it significantly impacts the extraction of discriminative speaker embeddings. To address these challenges, we propose a novel model called the Multi-Scale Expand Convolution Transformer (MEConformer). This model aims to convert variable-length audio into a fixed low-dimensional representation. The MEConformer leverages a CNN framework with expanded receptive fields to capture frame-level features effectively. Additionally, we introduce a transformer encoder that incorporates contextual dependencies, enabling the extraction of both frame-level and discourse-level feature representations. Furthermore, we present a multi-scale residual aggregation strategy, which facilitates the efficient transmission of voiceprint information across the model. By combining these innovative components, the MEConformer achieves a state-of-the-art Equal Error Rate (EER) of 3.72% on the VoxCeleb1 test set. Furthermore, it demonstrates EERs of 5.94% and 3.72% on the VoxCeleb1-H and VoxCeleb-E datasets, respectively. The code for the proposed MEConformer model will be made publicly available at https://codeocean.com/capsule/4563012/tree.

Research on percussion-based bolt looseness monitoring under noise interference and insufficient samples

Loose bolts are the key cause of tower collapse. The maintenance of bolts in transmission towers remains at the stage of individual inspection, and it is urgent to develop practical bolt looseness monitoring methods for engineering applications. The percussion-based method has shown its full potential due to not relying on fixed signal generators and sensors. However, its performance can severely degrade under noise interference and data scarcity. To address this problem, the new voiceprint feature that resist noise interference and classifier that alleviate sample shortages are proposed in this study, namely all-pole group delay function (APGDF) and prototypical networks. The proposed new bolt torque monitoring method is composed of the two. Under the condition that each bolt torque has only 50 percussion sound samples and −6dB signal-to-noise ratio (SNR), the accuracy of the proposed method for single bolt looseness monitoring is 77.87 %, and the accuracy of multi-bolt looseness monitoring is 80.60 %, which is significantly better than existing feature-based methods. In addition, the monitoring of bolt looseness with highly few samples and the data dimensionality reduction analysis are carried out to demonstrate the superiority of this method. The percussion point needs to be close to the loose bolt to achieve the best monitoring effect, and the percussion intensity does not affect the monitoring effect. The proposed method is expected to become the fundamental mode of bolt looseness monitoring in engineering practice.

Voiceprint Recognition under Cross-Scenario Conditions Using Perceptual Wavelet Packet Entropy-Guided Efficient-Channel-Attention–Res2Net–Time-Delay-Neural-Network Model

(1) Background: Voiceprint recognition technology uses individual vocal characteristics for identity authentication and faces many challenges in cross-scenario applications. The sound environment, device characteristics, and recording conditions in different scenarios cause changes in sound features, which, in turn, affect the accuracy of voiceprint recognition. (2) Methods: Based on the latest trends in deep learning, this paper uses the perceptual wavelet packet entropy (PWPE) method to extract the basic voiceprint features of the speaker before using the efficient channel attention (ECA) block and the Res2Net block to extract deep features. The PWPE block removes the effect of environmental noise on voiceprint features, so the perceptual wavelet packet entropy-guided ECA–Res2Net–Time-Delay-Neural-Network (PWPE-ECA-Res2Net-TDNN) model shows an excellent robustness. The ECA-Res2Net-TDNN block uses temporal statistical pooling with a multi-head attention mechanism to weight frame-level audio features, resulting in a weighted average of the final representation of the speech-level feature vectors. The sub-center ArcFace loss function is used to enhance intra-class compactness and inter-class differences, avoiding classification via output value alone like the softmax loss function. Based on the aforementioned elements, the PWPE-ECA-Res2Net-TDNN model for speaker recognition is designed to extract speaker feature embeddings more efficiently in cross-scenario applications. (3) Conclusions: The experimental results demonstrate that, compared to the ECAPA-TDNN model using MFCC features, the PWPE-based ECAPA-TDNN model performs better in terms of cross-scene recognition accuracy, exhibiting a stronger robustness and better noise resistance. Furthermore, the model maintains a relatively short recognition time even under the highest recognition rate conditions. Finally, a set of ablation experiments targeting each module of the proposed model is conducted. The results indicate that each module contributes to an improvement in the recognition performance.

Research on Transformer Voiceprint Feature Extraction Oriented to Complex Noise Environment

Transformer fault diagnosis based on acoustic characteristics is a new non-contact and non-destructive monitoring method. It has the advantages that the acoustic signal detection is not disturbed by electric and magnetic fields, and the monitoring process does not affect the normal operation of the transformer. Aiming at the difficulty of extracting transformer voiceprint features in complex noise environment, a transformer voiceprint feature extraction method based on Variable Mode Extraction (VME) is proposed. In this method, the center frequency of the Intrinsic Mode Function(IMF) is set according to the generation mechanism of transformer radiated noise, thus the uncertainty of decomposition results caused by random distribution and other frequency search methods is eliminated; Then, taking the frequency-domain energy aggregation of IMF and the minimum center frequency energy of residual signal as the optimization objectives, the cyclic iterative decomposition is used to identify and extract the transformer voiceprint features, so as to reduce the impact of environmental noise and other equipment noise. The analysis results of simulation signals and field signals show that this method can effectively reduce the impact of environmental noise and extract more clear and accurate transformer voiceprint features.

Multidimensional voiceprint feature assessment system for identifying the depression in children and adolescents: a diagnostic test.

We designed a diagnostic test to evaluate the effectiveness and accuracy of a multidimensional voiceprint feature diagnostic assessment (MVFDA) system vs. the 24-item Hamilton Rating Scale for Depression (HAMD-24) for adjunctive diagnosis of children and adolescents with major depressive disorder (MDD). This study included 55 children aged 6-16 years who were clinically diagnosed with MDD according to the DSM-5 and analyzed by professional physicians, and 55 healthy children (typically developing). Each subject completed a voice recording and was scored on the HAMD-24 scale by a trained rater. We calculated the validity indices, including sensitivity, specificity, Youden's index, likelihood ratio, and other indices including predictive value, diagnostic odds ratio, diagnostic accuracy, and area under the curve (AUC), to assess the effectiveness of the MVFDA system in addition to the HAMD-24. The sensitivity (92.73 vs. 76.36%) and the specificity (90.91 vs. 85.45%) of the MVFDA system are significantly higher than those of the HAMD-24. The AUC of the MVFDA system is also higher than that of the HAMD-24. There is a statistically significant difference between the groups (p < 0.05), and both of them have high diagnostic accuracy. In addition, the diagnostic efficacy of the MVFDA system is higher than that of HAMD-24 in terms of the Youden index, diagnostic accuracy, likelihood ratio, diagnostic odds ratio, and predictive value. The MVFDA has performed well in clinical diagnostic trials for the identification of MDD in children and adolescents by capturing objective sound features. Compared with the scale assessment method, the MVFDA system could be further promoted in clinical practice due to its advantages of simple operation, objective rating, and high diagnostic efficiency.

Simulation research on music feature recognition based on mobile big data and smart sensors

Abstract With the increasing importance of music information retrieval, the construction of effective music recognition methods has gradually become one of the research focuses. The vocal map features of the collected music pronunciation signals are extracted. The research in this paper is primarily based on the basic physical characteristics of music notes; once these characteristics are identified, then they are mathematically extracted and analysed (voiceprint feature method), and a recognition model is established. On this basis, the process of adaptive separation and recognition of music signals is completed. Finally, the performance of different recognition types is verified and evaluated through experiments. The results show that the average accuracy rate of the modified algorithm within a certain range reaches 73.6%; additionally, the average accuracy rate is increased by 10.95% compared with the audio recognition based on Internet of Things (IoT) data, and is more accurate than the audio recognition method based on data collection, showing an improvement of 20.75%. This shows that the modified recognition algorithm adopted in the present research has stable and high accuracy for comprehensive music types with different characteristics. Finally, the identification method proposed in this paper shortens the time by 85.71% compared with the identification method of data collection, and shortens the identification time by 83.33% compared with the IoT identification method. This greatly improves the recognition of different musical feature types.

A motor bearing fault voiceprint recognition method based on Mel-CNN model

The occurrence of bearing faults is often accompanied by noise signals, and noise sensors have the characteristics of non-contact and flexible arrangement; hence, this paper proposes a bearing fault diagnosis method based on voiceprint features and deep learning. First, the high-frequency component of the motor noise is removed with the help of variational mode decomposition (VMD) to extract the Mel spectrum voiceprint features. Secondly, the Mel voiceprint features are re-extracted with the help of convolutional neural networks (CNN) to fully obtain the high-dimensional abstract features characterizing the bearing faults. Finally, the Mel-CNN model is exploited to achieve bearing fault diagnosis. Applying the Mel-CNN model proposed in this paper to motor noise data with bearing faults, the results show that the Mel spectral features can accurately characterize bearing faults and that the Mel-CNN model outperforms ACDIN, WDCNN, TICNN, the improved LeNet-5 model, and four CNN-derived models.

Monitoring of Agglomeration in Fluidized-Bed Reactor Based on Voiceprint Features Recognition with Unbalanced Samples

Monitoring of Agglomeration in Fluidized-Bed Reactor Based on Voiceprint Features Recognition with Unbalanced Samples

Voiceprint Feature Extraction of Large Power Transformers in Uninterrupted Diagnosis and Early Warning Technology

Condition-based maintenance is to select the most suitable maintenance method according to the real-time operating state of the converter. Transformer condition evaluation and fault diagnosis is an important basis for condition maintenance, and it is also the key to ensure the normal implementation of condition maintenance. The main purpose of this paper is to study the application of voiceprint feature extraction in large-scale power transformers in uninterruptible power failure diagnosis and early warning technology. In this paper, a comprehensive and in-depth study of the state quantity of transformer uninterrupted detection is carried out. Experiments show that when CR<0.10, the matrix is satisfactory and consistent, and the weight distribution is reasonable.

Audible acoustic characteristics of epoxy resins with partial discharge

The epoxy resin is the main solid insulating material for electrical equipment. PD (partial discharge) is an important factor leading to epoxy resin aging or failure. Fault detection technology based on audible acoustic imaging has the advantages of real-time monitoring, visibility, and flexibility and is gradually being used in the field of electrical equipment insulation state monitoring. However, the audible voiceprint features of epoxy resins with typical PD defects are not clear, which is not conducive to effective detection and fault diagnosis. Therefore, in this study, the study of audible voiceprint features of epoxy resins with a metal burr, pollution, metal foreign matters, and surface discharge defects was carried out. The discharge audible signals were obtained, and their time and frequency domain features were analyzed. The results show that the discharge audible signals of four PD defects can reflect the occurrence of PD simultaneously with pulse current signals. But the characteristics are obviously different in the time domain, which are embodied in listening perception, persistence, amplitude, and phase. In the frequency domain, the frequency spectra of discharge audible signals of four defects are mainly 5–10 and 13–24 kHz. Furthermore, the three feature vectors of frequency spectrum complexity, high-frequency energy factor, and maximum frequency point are extracted, which can well distinguish the discharge audible signals of four PD defects.

Deep Learning with LPC and Wavelet Algorithms for Driving Fault Diagnosis

Vehicle fault detection and diagnosis (VFDD) along with predictive maintenance (PdM) are indispensable for early diagnosis in order to prevent severe accidents due to mechanical malfunction in urban environments. This paper proposes an early voiceprint driving fault identification system using machine learning algorithms for classification. Previous studies have examined driving fault identification, but less attention has focused on using voiceprint features to locate corresponding faults. This research uses 43 different common vehicle mechanical malfunction condition voiceprint signals to construct the dataset. These datasets were filtered by linear predictive coefficient (LPC) and wavelet transform(WT). After the original voiceprint fault sounds were filtered and obtained the main fault characteristics, the deep neural network (DNN), convolutional neural network (CNN), and long short-term memory (LSTM) architectures are used for identification. The experimental results show that the accuracy of the CNN algorithm is the best for the LPC dataset. In addition, for the wavelet dataset, DNN has the best performance in terms of identification performance and training time. After cross-comparison of experimental results, the wavelet algorithm combined with DNN can improve the identification accuracy by up to 16.57% compared with other deep learning algorithms and reduce the model training time by up to 21.5% compared with other algorithms. Realizing the cross-comparison of recognition results through various machine learning methods, it is possible for the vehicle to proactively remind the driver of the real-time potential hazard of vehicle machinery failure.

Target Speaker Extraction by Fusing Voiceprint Features

It is a critical problem to accurately separate clean speech in the multispeaker scenario for different speakers. However, in most cases, smart devices such as smart phones interact with only one specific user. As a consequence, the speech separation models adopted by these devices only have to extract the target speaker’s speech. A voiceprint, which reflects the speaker’s voice characteristics, provides prior knowledge for the target speech separation. Therefore, how to efficiently integrate voiceprint features into the existing speech separation models to improve their performance for the target speech separation is an interesting problem not fully explored. This paper attempts to solve this issue to some extent and our contributions are as follows. First, two different voiceprint features (i.e., MFCCs and d-vector) are explored in the performance enhancement for three speech separation models. Second, three different feature fusion methods are proposed to efficiently fuse the voiceprint features with the magnitude spectrograms originally used in the speech separation models. Third, a target speech extraction method which utilizes the fused features is proposed for two speaker-independent models. Experiments demonstrate that the speech separation models integrated with voiceprint features using three feature fusion methods can effectively extract the target speaker’s speech.

Research and application of spoken English evaluation system based on biological voiceprint feature recognition

Research and application of spoken English evaluation system based on biological voiceprint feature recognition

Research and application of spoken English evaluation system based on biological voiceprint feature recognition

The design of oral English evaluation system based on biological voiceprint feature recognition technology can deal with the shortcomings of speech teaching in traditional computer-aided technology, and can improve the learning interest and learning effect of oral English learners. This time, MFCC method is selected to construct the evaluation model of oral English, which can achieve good speech recognition effect. Through hierarchical recognition strategy, the algorithm mechanism of oral English is further optimised. Through simulation analysis, it can be seen that the proposed system design can objectively reflect the actual oral English level of oral English evaluators, and has good application effect and practical value.

Anchor voiceprint recognition in live streaming via RawNet-SA and gated recurrent unit

With the sharp booming of online live streaming platforms, some anchors seek profits and accumulate popularity by mixing inappropriate content into live programs. After being blacklisted, these anchors even forged their identities to change the platform to continue live, causing great harm to the network environment. Therefore, we propose an anchor voiceprint recognition in live streaming via RawNet-SA and gated recurrent unit (GRU) for anchor identification of live platform. First, the speech of the anchor is extracted from the live streaming by using voice activation detection (VAD) and speech separation. Then, the feature sequence of anchor voiceprint is generated from the speech waveform with the self-attention network RawNet-SA. Finally, the feature sequence of anchor voiceprint is aggregated by GRU to transform into a deep voiceprint feature vector for anchor recognition. Experiments are conducted on the VoxCeleb, CN-Celeb, and MUSAN dataset, and the competitive results demonstrate that our method can effectively recognize the anchor voiceprint in video streaming.

Secure E - Voting System using Voiceprint

Electronic voting systems are considered to be one of the modern systems that are widely used recently. The great challenge which is facing researchers in this field is how to verify the voter. This paper discussed and implemented online secure E- voting system depends on speech recognition. The proposed system represents a very important stage in identity of the voter personality. The researcher used voiceprint feature (Pitch Detection), where the system included the recognition of voiceprint through the use of (MFCC) method, which proved a great success for sample of society that has been used in the proposed system. The researcher has faced many problems in dealing with human voice as a means of proof. The work required a set of processors for the sound signal (Preprocessing), the addition that the researcher has done is no intensive circumstances or special requirements for the of recording voice but, the system works through very normal circumstances as it has been benefited from merging and propose recording machinery and processing the voice by using hybrid way that using (framing and windowing). The results of voiceprint recognition with a ratio that is more than 98%. These results had a great role in achieving privacy and data integration for the later stages of the proposed system.