Voice Signal Research Articles

Integration of an RSA-2048-bit public key cryptography solution in the development of secure voice recognition processing applications

The authors initially employs the fast Fourier transform (FFT) approach to transforming voice inputs into digital signals before integrating a speech recognition solution (which includes two models: the hidden Markov model (HMM) and the artificial neural network (ANN)). To achieve standard-tone identification of voice signals and digitally store speech, the authors then incorporated a 2048-bit Rivest-Shamir-Adleman (RSA) encryption method to encrypt and decrypt digital speech. The authors’ building team constructed the program using a 256-bit advanced encryption standard - Galois counter mode (AES-GCM) encryption method to assure the application’s effectiveness. The authors successfully created a voice recognition application according to the HMM of ANN. The collected findings suggest that the authors’ secure speech recognition program (named soft voice - RSA) has improved in terms of safety, keeping speech material secret, and speed. It takes roughly 0.2 s to generate a 2048-bit RSA key pair that exceeds the National Institute of Standards and Technology (NIST) standard, 700-1070 ms to process speech, 1-4 ms to encrypt 2048-bit RSA, 6-8 ms to decrypt 2048-bit RSA.

Model predictive PESQ-ANFIS/FUZZY C-MEANS for image-based speech signal evaluation

This paper presents a new method to evaluate the quality of speech signals through images generated from a psychoacoustic model to estimate PESQ (ITU-T P862) values using a first-order Fuzzy Sugeno approach implemented in the Adaptive Neuro-Fuzzy Inference System - ANFIS. The factors feeding the network were obtained using an image-processing technique from the perceptual model coefficients. All simulations were performed using a database containing clean and corrupted signals by eight types of noises found in everyday situations. The proposal uses the PESQ values of the signals to train the network. The analyses proved that the predictive performance will depend on the choice of a psychoacoustic model, the factor extraction technique, the combination of these factors, the fuzzification algorithm, and the type of membership function in the ANFIS input space. The data sets for training and testing for each signal directory were randomly created and executed fifty times. The proposal achieves the best prediction values for PESQ when the averages of the measurements reach MAPE ≤0.09, RMSE ≤0.20, and R2≥95. In general, the approach provided satisfactory results compared to Multilayer Perceptron networks with their different learning algorithms, compared to another psychoacoustic model, to ITU-T P.563 and other non-intrusive methods that evaluate the quality of voice signals, and it was efficient regardless of the number of signals and the database used.

GTSO: Gradient tangent search optimization enabled voice transformer with speech intelligibility for aphasia

A frequent neurological condition known as aphasia is brought on by injury to language-related brain regions as well as possibly other regions of the brain involved in executive, memory, and attention functions. Due to a lack of speech-language pathologists and the vast expense of treatment, traditional therapy is difficult for aphasia-affected people to access. In this research work, speech intelligibility for aphasia is done by the proposed Gradient Tangent Search Optimization (GTSO) algorithm-enabled voice transformer. Here, the median filter is used for pre-processing the signal to reduce noise. The pre-processed voice signal is allowed for feature extraction and voice enhancement stages. Moreover, nonlinear spectral subtraction is used for voice enhancement and voice transformer is used for voice recognition. Also, the voice transformer is trained by GTSO, which is devised by hybridizing Gradient Descent (GD) Optimization and Tangent Search Algorithm (TSA). Then, the output obtained is fed to the language and pronunciation model for recognizing speech, and at last, the speech recognized is converted to text. Furthermore, the GTSO- enabled voice transformer is analyzed for its performance by three metrics, namely recognition accuracy, Positive Predictive Value (PPV), and Negative Predictive Value (NPV), with superior values of 0.919, 0.919, and 0.915.

RETRACTED ARTICLE: Hybrid CNN-LSTM model with efficient hyperparameter tuning for prediction of Parkinson’s disease

The patients’ vocal Parkinson’s disease (PD) changes could be identified early on, allowing for management before physically incapacitating symptoms appear. In this work, static as well as dynamic speech characteristics that are relevant to PD identification are examined. Speech changes or communication issues are among the challenges that Parkinson’s individuals may encounter. As a result, avoiding the potential consequences of speech difficulties brought on by the condition depends on getting the appropriate diagnosis early. PD patients’ speech signals change significantly from those of healthy individuals. This research presents a hybrid model utilizing improved speech signals with dynamic feature breakdown using CNN and LSTM. The proposed hybrid model employs a new, pre-trained CNN with LSTM to recognize PD in linguistic features utilizing Mel-spectrograms derived from normalized voice signal and dynamic mode decomposition. The proposed Hybrid model works in various phases, which include Noise removal, extraction of Mel-spectrograms, feature extraction using pre-trained CNN model ResNet-50, and the final stage is applied for classification. An experimental analysis was performed using the PC-GITA disease dataset. The proposed hybrid model is compared with traditional NN and well-known machine learning-based CART and SVM & XGBoost models. The accuracy level achieved in Neural Network, CART, SVM, and XGBoost models is 72.69%, 84.21%, 73.51%, and 90.81%. The results show that under these four machine approaches of tenfold cross-validation and dataset splitting without samples overlapping one individual, the proposed hybrid model achieves an accuracy of 93.51%, significantly outperforming traditional ML models utilizing static features in detecting Parkinson’s disease.

Precision Value, Error Rate and Accuracy of Human Gender Identification Based on Randomized Voice Signals Datasets

Precision Value, Error Rate and Accuracy of Human Gender Identification Based on Randomized Voice Signals Datasets

Combined Method for Informative Feature Selection for Speech Pathology Detection

The task of detecting vocal abnormalities is characterized by a small amount of available data for training, as a consequence of which classification systems that use low-dimensional data are the most relevant. We propose to use LASSO (least absolute shrinkage and selection operator) and BSS (backward stepwise selection) methods together to select the most significant features for the detection of vocal pathologies, in particular amyotrophic lateral sclerosis. Features based on fine-frequency cepstral coefficients, traditionally used in speech signal processing, and features based on discrete estimation of the autoregressive spectrum envelope are used. Spectral features based on the autoregressive process envelope spectrum are extracted using the generative method, which involves calculating a discrete Fourier transform of the report sequence generated using the autoregressive model of the input voice signal. The sequence is generated by the autoregressive model so as to account for the periodic nature of the Fourier transform. This improves the accuracy of the spectrum estimation and reduces the spectral leakage effect. Using LASSO in conjunction with BSS allowed us to improve the classification efficiency using a smaller number of features as compared to using the LASSO method alone.

Influence of phase information on voice pre-processing signal in the authentication system

The article analyzes and investigates directions for improving the quality characteristics of voice authentication systems in various access systems by improving the procedures for pre-processing registration materials. One of the main ways of improving the quality characteristics of user authentication systems, which was studied in the work, is the use of phase information of the voice signal. The actual scientific task of researching new procedures for pre-processing the voice signal of the user of the authentication system is being solved. The purpose of this work is to develop additional preprocessing procedures to reduce noise in voice signals of the authentication system. Refinement of pre-processing procedures was carried out based on the use of phase data of the voice signal. The results are obtained in the process of statistical analysis of simulation results using experimental model data of the authentication system. The phase space of the voice signal allows you to expand the possibilities of pre-processing due to the use of a priori information about the nature of changes in phase data. The scientific novelty of the obtained results lies in the fact that for the first time, a technique was developed, and experimental studies were carried out for the pre-processing of the user’s voice signal using the space of phase data. The practical significance of the obtained results is as follows: the phase information approximation interval was selected taking into account a priori data on the nature of its changes; an original linear approximation of phase data containing one harmonic of a voice signal is proposed; a mechanism for determining two harmonics in the phase data of a voice signal when using the proposed linear approximation is developed; the conducted experimental studies allow to develop a mechanism for compensation of random errors in registration materials. The presented research results are advisable for use in voice authentication systems, improvement of speech recognition systems, and solving speaker identification tasks.

Internet speech denoising method based on IGAN algorithm

At present, to settle the question of excessive noise in the speech signal during the call of mobile devices in China, the research proposes that the Wiener filter and the generative adversarial network are combined into the IGAN algorithm. Firstly, the Wiener filter regularization algorithm is introduced to construct the preprocessing model of the speech signal; then the preprocessing model is fused with the generative adversarial network algorithm to construct the denoising model. Finally, the performance analysis and simulation experiments of the application effect of the model are carried out. The results show that in the experiment comparing IGAN with five traditional algorithms, when the SNR ratio is increased to 17.5 dB, the MOS and PESQ scores under the IGAN method can reach 4.9 and 3.5 respectively, and the DNN effect is second only to IGAN. Other algorithms perform poorly. Then compare the number of iterations and the loss value between the two. When the network voice signal begins to converge, the loss value corresponding to DNN is 1.132; while the loss value of IGAN is about 0.573, it can be found that the loss value of IGAN has dropped by half, which shows that IGAN Build the model with a smaller loss value. And IGAN tends to converge when iteratively is performed for about 200 times, and the average peak SNR can reach up to 33.85 dB, an increase of nearly 1.02 dB, and the effect is remarkable. This all shows that the IGAN algorithm has the best denoising performance for network speech signals, improves the denoising efficiency, and is conducive to obtaining a denoising signal with a higher fit with the clean signal, so that mobile devices can better serve the people.

Low Resource Language Analysis Using Deep Learning Algorithm for Gender Classification

Voice signals are the essential input source for applications based on human and computer interaction technology. Gender identification through voice signals is one of the most challenging tasks. For voice signal based analysis, deep learning algorithms provide an alternative to traditional and conventional algorithms for classification. To identify the gender through voice signals of female, male and ‘first-time’ transgender, the deep learning algorithm is used to improve the robustness of the identification model with the Mel Frequency Cepstrum Coefficients (MFCC) as a feature of the voice signals. This article presents the identification accuracy of gender with the help of recorded live voice signals. The voice samples of the third gender are recorded in the Hindi language. These Hindi language voice samples of transgender are very low resources and are unavailable at any recognized sources. The simulation results do not depend on the duration of the signals and are text independent. The recurrent neural network – Bidirectional Long Short-term Memory (RNN – BiLSTM) algorithm has been simulated on the recorded voice signals. The simulation outcome is compared with the earlier reported results in the literature. The gender-wise average accuracy of the proposed model is achieved as 91.44%, 94.94%, and 96.11% for males, females, and transgender, respectively, using voice signals. The identification accuracy of transgender is high in comparison to other genders. On the other hand, the average accuracy of the proposed model is obtained as 94.16%.

Establishing the identity of persons

Establishing the identity of persons is a predominant police method with a preventive character, intended to combat both possible crimes, but also to discover delinquents. Establishing the identity involves checking the documents provided with a photo of both Romanian citizens and foreigners who enter our country or are in transit. More and more often, the identity of people is established when crossing state borders, thus the state of danger can be removed. We can say that the procedure of establishing the identity is a measure that the judicial bodies resort to, and with the help of witnesses or victims, they establish the identity of people with the help of technical methods. Throughout life, both the Romanian Constitution and the Criminal Code have tried to diversify and improve identification methods, to be as simple as possible and to reach the best possible result in the shortest possible time with the aim of reducing the criminal phenomenon . In the theme we chose to write the establishment of the identity of the persons, the stages of this process, the persons subject to identification, but also the circumstances in which this process is carried out. We will detail the cases in which establishing identification is possible and under what conditions, but especially the presentation of the 3 cases through which establishing identity is possible, establishing identity through portrait photography, through voice signals, but not least through external signals.

Deriving Vocal Fold Oscillation Information from Recorded Voice Signals Using Models of Phonation.

During phonation, the vocal folds exhibit a self-sustained oscillatory motion, which is influenced by the physical properties of the speaker's vocal folds and driven by the balance of bio-mechanical and aerodynamic forces across the glottis. Subtle changes in the speaker's physical state can affect voice production and alter these oscillatory patterns. Measuring these can be valuable in developing computational tools that analyze voice to infer the speaker's state. Traditionally, vocal fold oscillations (VFOs) are measured directly using physical devices in clinical settings. In this paper, we propose a novel analysis-by-synthesis approach that allows us to infer the VFOs directly from recorded speech signals on an individualized, speaker-by-speaker basis. The approach, called the ADLES-VFT algorithm, is proposed in the context of a joint model that combines a phonation model (with a glottal flow waveform as the output) and a vocal tract acoustic wave propagation model such that the output of the joint model is an estimated waveform. The ADLES-VFT algorithm is a forward-backward algorithm which minimizes the error between the recorded waveform and the output of this joint model to estimate its parameters. Once estimated, these parameter values are used in conjunction with a phonation model to obtain its solutions. Since the parameters correlate with the physical properties of the vocal folds of the speaker, model solutions obtained using them represent the individualized VFOs for each speaker. The approach is flexible and can be applied to various phonation models. In addition to presenting the methodology, we show how the VFOs can be quantified from a dynamical systems perspective for classification purposes. Mathematical derivations are provided in an appendix for better readability.

Using PIC18 Microcontrollers to Generate Chaotic Signals Based on Logistic Mapping

In this paper, simulation and hardware implementation of the device for generating chaotic signals based on logistic mapping using microcontrollers of the РІС18 series was carried out. The operation of the device was investigated in the mode of generating chaotic oscillations at different values of the control parameter λ. By certain hardware and software modification, this generator can be used as a voice signal encryption The results of simulation and experimental studies confirm the possibility of using PIC18 microcontrollers for the implementation of chaotic oscillation generators based on discrete mappings, as well as using these controllers in the hardware implementation of language information encryption devices.

Attention-Based Fusion of Ultrashort Voice Utterances and Depth Videos for Multimodal Person Identification

Multimodal deep learning, in the context of biometrics, encounters significant challenges due to the dependence on long speech utterances and RGB images, which are often impractical in certain situations. This paper presents a novel solution addressing these issues by leveraging ultrashort voice utterances and depth videos of the lip for person identification. The proposed method utilizes an amalgamation of residual neural networks to encode depth videos and a Time Delay Neural Network architecture to encode voice signals. In an effort to fuse information from these different modalities, we integrate self-attention and engineer a noise-resistant model that effectively manages diverse types of noise. Through rigorous testing on a benchmark dataset, our approach exhibits superior performance over existing methods, resulting in an average improvement of 10%. This method is notably efficient for scenarios where extended utterances and RGB images are unfeasible or unattainable. Furthermore, its potential extends to various multimodal applications beyond just person identification.

Emotion Classification Based on CWT of ECG and GSR Signals Using Various CNN Models

Emotions expressed by humans can be identified from facial expressions, speech signals, or physiological signals. Among them, the use of physiological signals for emotion classification is a notable emerging area of research. In emotion recognition, a person’s electrocardiogram (ECG) and galvanic skin response (GSR) signals cannot be manipulated, unlike facial and voice signals. Moreover, wearables such as smartwatches and wristbands enable the detection of emotions in people’s naturalistic environment. During the COVID-19 pandemic, it was necessary to detect people’s emotions in order to ensure that appropriate actions were taken according to the prevailing situation and achieve societal balance. Experimentally, the duration of the emotion stimulus period and the social and non-social contexts of participants influence the emotion classification process. Hence, classification of emotions when participants are exposed to the elicitation process for a longer duration and taking into consideration the social context needs to be explored. This work explores the classification of emotions using five pretrained convolutional neural network (CNN) models: MobileNet, NASNetMobile, DenseNet 201, InceptionResnetV2, and EfficientNetB7. The continuous wavelet transform (CWT) coefficients were detected from ECG and GSR recordings from the AMIGOS database with suitable filtering. Scalograms of the sum of frequency coefficients versus time were obtained and converted into images. Emotions were classified using the pre-trained CNN models. The valence and arousal emotion classification accuracy obtained using ECG and GSR data were, respectively, 91.27% and 91.45% using the InceptionResnetV2 CNN classifier and 99.19% and 98.39% using the MobileNet CNN classifier. Other studies have not explored the use of scalograms to represent ECG and GSR CWT features for emotion classification using deep learning models. Additionally, this study provides a novel classification of emotions built on individual and group settings using ECG data. When the participants watched long-duration emotion elicitation videos individually and in groups, the accuracy was around 99.8%. MobileNet had the highest accuracy and shortest execution time. These subject-independent classification methods enable emotion classification independent of varying human behavior.

Proposing a new approach based on convolutional neural networks and random forest for the diagnosis of Parkinson's disease from speech signals

Parkinson which occurs because of affected motor system by central nervous system is a neurodegenerative disease which is often seen in community. This disease, which is frequently seen especially in the elderly, brings problems such as speech disorders in patients. It is seen that with the rapidly developing deep learning and machine learning methods in recent years, it is possible to distinguish speech disorders in PD patients at a high rate and quickly. In this study, PD diagnosis was performed using datasets containing voice signals of healthy individuals and PD patients (PD_Dataset and PDO_Dataset). Current convolutional neural networks (CNN) and machine learning (ML) algorithms for PD diagnosis have been examined and a comparative performance analysis has been made. In addition, a different method called SkipConNet + RF based on CNN and random forest (RF) has been proposed for PD diagnosis. With the proposed SkipConNet, important features were obtained from the speech signals; then, the estimation process was performed using the RF algorithm. The proposed method provided an improvement between 3% and 17.19% in the performance of RF algorithms. In addition, the SkipConNet + RF method showed the highest success with 99.11% accuracy in the PD_Dataset dataset and 98.30% in the PDO_Dataset dataset.

CovidCoughNet: A new method based on convolutional neural networks and deep feature extraction using pitch-shifting data augmentation for covid-19 detection from cough, breath, and voice signals

This study proposes a new deep learning-based method that demonstrates high performance in detecting Covid-19 disease from cough, breath, and voice signals. This impressive method, named CovidCoughNet, consists of a deep feature extraction network (InceptionFireNet) and a prediction network (DeepConvNet). The InceptionFireNet architecture, based on Inception and Fire modules, was designed to extract important feature maps. The DeepConvNet architecture, which is made up of convolutional neural network blocks, was developed to predict the feature vectors obtained from the InceptionFireNet architecture. The COUGHVID dataset containing cough data and the Coswara dataset containing cough, breath, and voice signals were used as the data sets. The pitch-shifting technique was used to data augmentation the signal data, which significantly contributed to improving performance. Additionally, Chroma features (CF), Root mean square energy (RMSE), Spectral centroid (SC), Spectral bandwidth (SB), Spectral rolloff (SR), Zero crossing rate (ZCR), and Mel frequency cepstral coefficients (MFCC) feature extraction techniques were used to extract important features from voice signals. Experimental studies have shown that using the pitch-shifting technique improved performance by around 3% compared to raw signals. When the proposed model was used with the COUGHVID dataset (Healthy, Covid-19, and Symptomatic), a high performance of 99.19% accuracy, 0.99 precision, 0.98 recall, 0.98 F1-Score, 97.77% specificity, and 98.44% AUC was achieved. Similarly, when the voice data in the Coswara dataset was used, higher performance was achieved compared to the cough and breath studies, with 99.63% accuracy, 100% precision, 0.99 recall, 0.99 F1-Score, 99.24% specificity, and 99.24% AUC. Moreover, when compared with current studies in the literature, the proposed model was observed to exhibit highly successful performance. The codes and details of the experimental studies can be accessed from the relevant Github page: (https://github.com/GaffariCelik/CovidCoughNet).

Stretchable Organohydrogel with Adhesion, Self-Healing, and Environment-Tolerance for Wearable Strain Sensors.

Stretchable hydrogels as landmark soft materials have been efficiently utilized in the field of wearable sensing devices. However, these soft hydrogels mostly cannot integrate transparency, stretchability, adhesiveness, self-healing, and environmental adaptability into one system. Herein, a fully physically cross-linked poly(hydroxyethyl acrylamide)-gelatin dual-network organohydrogel is prepared in a phytic acid-glycerol binary solvent via a rapid ultraviolet light initiation. The introduction of gelatin as the second network endows the organohydrogel with desirable mechanical performance (high stretchability up to 1240%). The presence of phytic acid not only synergizes with glycerol to impart environment-tolerance to the organohydrogel (from -20 to 60 °C) but also increases the conductivity. Moreover, the organohydrogel demonstrates a durable adhesive performance toward diverse substrates, a high self-healing efficiency through heat treatment, and favorable optical transparency (transmittance of 90%). Furthermore, the organohydrogel achieves high sensitivity (gauge factor of 2.18 at 100% strain) and rapid response time (80 ms) and could detect both tiny (a low detection limit of 0.25% strain) and large deformations. Therefore, the assembled organohydrogel-based wearable sensors are capable of monitoring human joint motions, facial expression, and voice signals. This work proposes a facile route for multifunctional organohydrogel transducers and promises the practical application of flexible wearable electronics in complex scenarios.

Emotion-Recognition Algorithm Based on Weight-Adaptive Thought of Audio and Video

Emotion recognition commonly relies on single-modal recognition methods, such as voice and video signals, which demonstrate a good practicability and universality in some scenarios. Nevertheless, as emotion-recognition application scenarios continue to expand and the data volume surges, single-modal emotion recognition proves insufficient to meet people’s needs for accuracy and comprehensiveness when the amount of data reaches a certain scale. Thus, this paper proposes the application of multimodal thought to enhance emotion-recognition accuracy and conducts corresponding data preprocessing on the selected dataset. Appropriate models are constructed for both audio and video modalities: for the audio-modality emotion-recognition task, this paper adopts the “time-distributed CNNs + LSTMs” model construction scheme; for the video-modality emotion-recognition task, the “DeepID V3 + Xception architecture” model construction scheme is selected. Furthermore, each model construction scheme undergoes experimental verification and comparison with existing emotion-recognition algorithms. Finally, this paper attempts late fusion and proposes and implements a late-fusion method based on the idea of weight adaptation. The experimental results demonstrate the superiority of the multimodal fusion algorithm proposed in this paper. When compared to the single-modal emotion-recognition algorithm, the accuracy of recognition is increased by almost 4%, reaching 84.33%.

A novel feature extraction method based on TQWT and instantaneous energy variation for Parkinson’s disease detection

Voice disorder is an early symptom of Parkinson’s disease (PD), and extracting effective voice features is of great significance for PD detection. The voice features based on tunable Q-factor wavelet transform (TQWT) have promising performance in PD detection only using conventional energy and entropy features. To further develop the potential of TQWT, a novel feature extraction method named instantaneous energy variation based on TQWT (IEV-TQWT) is proposed. Firstly, TQWT is adopted to perform multi-scale decomposition to obtain the oscillation information of the voice signals. Next, IEV-TQWT features are obtained by calculating instantaneous energy variation vectors from the spectrograms of sub-signals. Finally, the IEV-TQWT features are input to multiple classifiers to verify the PD classification performance. The results have shown that IEV-TQWT features with explicit physical information have a significant improvement in classification performance. In addition, IEV-TQWT features outperform other advanced features on the CPPDD dataset and reach mainstream level on SPDD dataset, indicating that IEV-TQWT features can be used as an effective assisted diagnosis tool of PD.

A Machine Learning Based Parkinson Prediction System – A Comprehensive Review

Parkinson's Disorder (PD) is a progressive neurodegenerative disorder, which is incurable. Diagnosis of PD at an early stage aids in the delay of the progression. It requires an accurate and robust system to provide early diagnosis of PD. Machine Learning (ML) based techniques help in developing of PD diagnosis system. This study presents a complete review of the various machine learning techniques along with their working principle that helps for the development of PD diagnosis system. This research highlights the summary of methodologies and also presents a generic framework for the PD diagnosis based on voice signals.