Voice Pathology Detection System Research Articles

A Robust Voice Pathology Detection System Based on the Combined BiLSTM–CNN Architecture

Voice recognition systems have become increasingly important in recent years due to the growing need for more efficient and intuitive human-machine interfaces. The use of Hybrid LSTM networks and deep learning has been very successful in improving speech detection systems. The aim of this paper is to develop a novel approach for the detection of voice pathologies using a hybrid deep learning model that combines the Bidirectional Long Short-Term Memory (BiLSTM) and the Convolutional Neural Network (CNN) architectures. The proposed model uses a combination of temporal and spectral features extracted from speech signals to detect the different types of voice pathologies. The performance of the proposed detection model is evaluated on a publicly available dataset of speech signals from individuals with various voice pathologies(MEEI database). The experimental results showed that the hybrid BiLSTM-CNN model outperforms several classifiers by achieving an accuracy of 98.86\%. The proposed model has the potential to assist health care professionals in the accurate diagnosis and treatment of voice pathologies, and improving the quality of life for affected individuals.

A comparison of data augmentation methods in voice pathology detection

To distinguish pathological voices from healthy voices, automatic voice pathology detection systems can be built using machine learning (ML) and deep learning (DL) techniques. To fully exploit such systems, large quantities of training data are typically required. The amount of training data is, however, small in the area of pathological voice, and therefore data augmentation (DA) becomes a potential technology to artificially increase the quantity of training data. This study presents a systematic comparison between various DA methods in the detection of pathological voice, including three time domain methods (noise addition, pitch shifting and time stretching), one time–frequency domain method (SpecAugment), and two vocoder-based methods (harmonic-to-noise ratio (HNR) modification and glottal pulse length modification). Detection systems were built using four popular spectral feature representations (static mel-frequency cepstral coefficients (MFCCs), dynamic MFCCs, spectrogram and mel-spectrogram). As classifiers, two widely used ML models (support vector machine (SVM) and random forest (RF)) and two DL models (long short-term memory (LSTM) network and convolutional neural network (CNN) with 1-dimensional (1-D) and 2-dimensional (2-D) architectures) were used. These systems were trained using a small number of training samples from two popular databases of pathological voice (HUPA and SVD) to find the best feature/classifier combination for each database. As a result, one ML-based detection system (mel-spectrogram/SVM for HUPA and SVD) and two DL-based detection systems (dynamic MFCCs/2-D CNN for HUPA and mel-spectrogram/2-D CNN for SVD) were selected for the comparison of the DA methods. The results show that by using DA in the system training, detection accuracy increased compared to the baseline systems that were trained without using DA. This improvement in accuracy was, however, clearly larger for the 2D-CNN system than for the SVM system. Furthermore, all six DA methods improved accuracy of the 2-D CNN system compared to the baseline system for both databases. The highest improvements were achieved using the time–frequency domain SpecAugment DA method, which improved accuracy by 1.5% and 3.8% (absolute) for the HUPA and SVD database, respectively.

MMHFNet: Multi-modal and multi-layer hybrid fusion network for voice pathology detection

Automatic voice pathology detection using non-invasive techniques that utilize patients’ speech and electroglottograph (EGG) signals play a vital role in diagnosis and early medical intervention. In this paper, a novel deep Multi-Modal and Multi-Layer Hybrid Fusion Network (MMHFNet) is proposed to improve the performance of non-invasive voice pathology detection systems. MMHFNet simultaneously incorporates complementary information of different modalities (speech and EGG signals). It also vertically combines the low-level features, extracted from shallow layers, and high-level features, extracted from deep layers, to take the full advantage of spatio-spectral information of different layers for multi-layer fusion. The features extracted by MMHFNet are then fed into an LSTM classification network to diagnose the voice pathology. Comprehensive experiments are conducted on the publicly available Saarbruecken Voice Database (SVD) to evaluate the performance of the proposed MMHFNet. This dataset is used in two manners; one using its all samples and the other with selected samples to form the largest balanced SVD dataset. Experimental results demonstrated that the proposed MMHFNet achieves accuracy rates of 91% and 96.05% for datasets with all and balanced samples, respectively.

An Efficient SMOTE-Based Deep Learning Model for Voice Pathology Detection

The Saarbruecken Voice Database (SVD) is a public database used by voice pathology detection systems. However, the distributions of the pathological and normal voice samples show a clear class imbalance. This study aims to develop a system for the classification of pathological and normal voices that uses efficient deep learning models based on various oversampling methods, such as the adaptive synthetic sampling (ADASYN), synthetic minority oversampling technique (SMOTE), and Borderline-SMOTE directly applied to feature parameters. The suggested combinations of oversampled linear predictive coefficients (LPCs), mel-frequency cepstral coefficients (MFCCs), and deep learning methods can efficiently classify pathological and normal voices. The balanced datasets from ADASYN, SMOTE, and Borderline-SMOTE are used to validate and evaluate the various deep learning models. The experiments are conducted using model evaluation metrics such as the recall, specificity, G, and F1 value. The experimental results suggest that the proposed voice pathology detection (VPD) system integrating the LPCs oversampled by the SMOTE and a convolutional neural network (CNN) can effectively yield the highest accuracy at 98.89% when classifying pathological and normal voices. Finally, the performances of oversampling algorithms such as the ADASYN, SMOTE, and Borderline-SMOTE are discussed. Furthermore, the performance of SMOTE is superior to conventional imbalanced data oversampling algorithms, and it can be used to diagnose pathological signals in real-world applications.

Voice Pathology Detection Using a Two-Level Classifier Based on Combined CNN–RNN Architecture

The construction of an automatic voice pathology detection system employing machine learning algorithms to study voice abnormalities is crucial for the early detection of voice pathologies and identifying the specific type of pathology from which patients suffer. This paper’s primary objective is to construct a deep learning model for accurate speech pathology identification. Manual audio feature extraction was employed as a foundation for the categorization process. Incorporating an additional piece of information, i.e., voice gender, via a two-level classifier model was the most critical aspect of this work. The first level determines whether the audio input is a male or female voice, and the second level determines whether the agent is pathological or healthy. Similar to the bulk of earlier efforts, the current study analyzed the audio signal by focusing solely on a single vowel, such as /a/, and ignoring phrases and other vowels. The analysis was performed on the Saarbruecken Voice Database,. The two-level cascaded model attained an accuracy and F1 score of 88.84% and 87.39%, respectively, which was superior to earlier attempts on the same dataset and provides a steppingstone towards a more precise early diagnosis of voice complications.

An Analytical Study of Speech Pathology Detection Based on MFCC and Deep Neural Networks.

Diseases of internal organs other than the vocal folds can also affect a person's voice. As a result, voice problems are on the rise, even though they are frequently overlooked. According to a recent study, voice pathology detection systems can successfully help the assessment of voice abnormalities and enable the early diagnosis of voice pathology. For instance, in the early identification and diagnosis of voice problems, the automatic system for distinguishing healthy and diseased voices has gotten much attention. As a result, artificial intelligence-assisted voice analysis brings up new possibilities in healthcare. The work was aimed at assessing the utility of several automatic speech signal analysis methods for diagnosing voice disorders and suggesting a strategy for classifying healthy and diseased voices. The proposed framework integrates the efficacy of three voice characteristics: chroma, mel spectrogram, and mel frequency cepstral coefficient (MFCC). We also designed a deep neural network (DNN) capable of learning from the retrieved data and producing a highly accurate voice-based disease prediction model. The study describes a series of studies using the Saarbruecken Voice Database (SVD) to detect abnormal voices. The model was developed and tested using the vowels /a/, /i/, and /u/ pronounced in high, low, and average pitches. We also maintained the “continuous sentence” audio files collected from SVD to select how well the developed model generalizes to completely new data. The highest accuracy achieved was 77.49%, superior to prior attempts in the same domain. Additionally, the model attains an accuracy of 88.01% by integrating speaker gender information. The designed model trained on selected diseases can also obtain a maximum accuracy of 96.77% (cordectomy × healthy). As a result, the suggested framework is the best fit for the healthcare industry.

Multi-modal voice pathology detection architecture based on deep and handcrafted feature fusion

Automatic voice pathology detection systems can effectively help clinicians by enabling objective assessment and diagnosis in early stage of voice pathologies. This paper suggests a novel multi-modal architecture utilizing speech and electroglottography (EGG) signals and investigates their effectiveness in automatic detection of voice pathology. The proposed multi-modal framework combines two parallel Convolutional Neural Networks (CNNs), one for voice signals and the other for EGG signals, to obtain deep features. Classical handcrafted features are also obtained in the same manner. These features are then concatenated to obtain a more prominent feature set. In addition, a feature selection method is applied to remove redundant features. Finally, a SVM classifier is utilized to detect the voice pathology. In order to measure the performance of the proposed pathology detection system, various experiments are conducted on Saarbruecken Voice Database (SVD) without excluding any available pathology or sample. The experimental results show that the proposed voice pathology detection method achieves accuracy up to 90.10% using all speech and EGG samples. Also, sensitivity, specificity and F1-score results of 92.9%, 84.6% and 92.57% are obtained, respectively. The proposed method provides better performance than those given in the literature using all SVD samples through cross-validation testing. Hence, it is promising for automatic detection applications of voice pathology.

Voice pathology detection using convolutional neural networks with electroglottographic (EGG) and speech signals

This paper presents a convolutional neural network (CNN) based automated noninvasive voice pathology detection system. The proposed system functions in two steps. First, it discriminates pathological voices from healthy ones, and then, it classifies the discriminated pathological voices into one of the three pathologies. Two CNNs are used for these purposes; one works as a binary classifier to identify pathological voices. The other one works as a multiclass classifier for categorizing the voice pathologies. This work investigates the effectiveness of electroglottographic (EGG) and speech signals to detect and classify pathological voices using sustained vowel ('/a/') samples. EGG signals can assess the vibratory pattern of the vocal folds during voiced sound. On the other hand, the speech signals add spectral color to the EGG signals. Hence, their contributions for pathology identification and segregation differ, as demonstrated in this work. The Saarbrücken Voice Database (SVD) is used in this investigation. The results show that the proposed system achieves a higher accuracy (more than 9%) in identifying pathological voices from healthy ones with speech signals than EGG signals. However, categorizing pathological voices into different pathology types demonstrates higher accuracy (more than 12%) with EGG signals than speech signals. A comparative performance analysis of the proposed system is presented with these two signals in terms of clinical and statistical measures. The obtained results of this work are also compared with those of other related published works.

Class-Imbalanced Voice Pathology Detection and Classification Using Fuzzy Cluster Oversampling Method

The Massachusetts Eye and Ear Infirmary (MEEI) database is an international-standard training database for voice pathology detection (VPD) systems. However, there is a class-imbalanced distribution in normal and pathological voice samples and different types of pathological voice samples in the MEEI database. This study aimed to develop a VPD system that uses the fuzzy clustering synthetic minority oversampling technique algorithm (FC-SMOTE) to automatically detect and classify four types of pathological voices in a multi-class imbalanced database. The proposed FC-SMOTE algorithm processes the initial class-imbalanced dataset. A set of machine learning models was evaluated and validated using the resulting class-balanced dataset as an input. The effectiveness of the VPD system with FC-SMOTE was further verified by an external validation set and another pathological voice database (Saarbruecken Voice Database (SVD)). The experimental results show that, in the multi-classification of pathological voice for the class-imbalanced dataset, the method we propose can significantly improve the diagnostic accuracy. Meanwhile, FC-SMOTE outperforms the traditional imbalanced data oversampling algorithms, and it is preferred for imbalanced voice diagnosis in practical applications.

Convergence of Artificial Intelligence and Internet of Things in Smart Healthcare: A Case Study of Voice Pathology Detection

The integration of artificial intelligence (AI) and the Internet of Things (IoT) has tremendous prospects in smart healthcare. The advancement of AI in the form of deep learning brought a revolution in automatic classification and detection systems. In addition, next-generation wireless communications such as 5G networking brought speed and the seamless transmission of data. With the convergence of these elements, the smart healthcare sector is currently booming. Particularly during the post-COVID-19 pandemic, the necessity of smart healthcare has come to light more than before. A significant number of people suffer from voice pathology. This pathology can be easily cured if detected early. In this study, a voice pathology detection system within a smart healthcare framework is proposed. The inputs are obtained by the IoT, namely microphones and electroglottography (EGG) devices to capture voice and EGG signals, respectively. Spectrograms are obtained from these signals and fed into a pretrained convolutional neural network (CNN). The features extracted from the CNN are fused and processed using a bi-directional long short-term memory network. The proposed system is evaluated using a publicly available database, called the Saarbruecken voice database. The experimental results show that bimodal input performs better than a single input. An accuracy of 95.65% is obtained for the proposed system.

Kullback–Leibler divergence and sample skewness for pathological voice quality assessment

This paper proposes new features aiming to improve the performance of an automatic voice pathology detection system. The features are designed precisely in terms of voice pathologies effects upon the speech signal. The system is intended to deliver high accuracy with a low number of parameters. Kullback–Leibler divergence (KLD) applied to consecutive frames of the speech signal provides a measure of voice instability. In this work, the KLD is applied to frame’s histogram and a modified form of its spectrum named higher amplitude suppression spectrum (HASS). The H-KLD (histogram KLD) and the HASS-KLD are two of the three features presently approached. An additional feature that provides the level of damping of the voice pitch period waveform is proposed, the short-term sample skewness of the signal. The H-KLD, the HASS-KLD, and the sample skewness are features employed along with mel-frequency cepstral coefficients (MFCC) in a voice pathology detection system. The system is composed of a Gaussian mixture models (GMM) classifier and two generalized extreme value (GEV) distribution classifiers. They are fused by means of a Gaussian naïve Bayes classifier. A standard subset of the Massachusetts Eye and Ear Infirmary (MEEI) voice disorders database is adopted for evaluating the system. The obtained global success rate of 99.55% shows that the proposed features are suitable for pathological voice quality assessment.

Implementation of voice pathology detection system using feature selection

Implementation of voice pathology detection system using feature selection

A Solution to the Security Authentication Problem in Smart Houses Based on Speech

Voice-operated smart houses often face security problems when there is pathology in the voice of an individual. If an error occurs during the process of authentication, then the system should detect whether this error is due to pathology or someone is trying to deceive the system. In the case of successful pathology detection, the system offers a second option of the pin code. Pathology detection is one of the major components in this research work. Voice pathology is the disorder of the vocal fold, which is normally diagnosed in people working in different areas, such as education, courtroom, etc. Many researchers have proposed different voice pathology detection systems (VPDS) where they used a common feature extraction technique, i.e., Mel Frequency cepstral coefficient (MFCC), or compared it with their proposed technique and produced results that are different in almost every case. In this paper, we propose a system that is based on MFCC features fused with pitch and it achieves 99.97% accuracy of pathology detection for the MEEI data set. This voice pathology detection accuracy is better as compared to most of the VPDS available for MEEI.

Towards robust voice pathology detection

Automatic objective non-invasive detection of pathological voice based on computerized analysis of acoustic signals can play an important role in early diagnosis, progression tracking and even effective treatment of pathological voices. In search towards such a robust voice pathology detection system we investigated 3 distinct classifiers within supervised learning and anomaly detection paradigms. We conducted a set of experiments using a variety of input data such as raw waveforms, spectrograms, mel-frequency cepstral coefficients (MFCC) and conventional acoustic (dysphonic) features (AF). In comparison with previously published works, this article is the first to utilize combination of 4 different databases comprising normophonic and pathological recordings of sustained phonation of the vowel /a/ unrestricted to a subset of vocal pathologies. Furthermore, to our best knowledge, this article is the first to explore gradient boosted trees and deep learning for this application. The following best classification performances measured by F1 score on dedicated test set were achieved: XGBoost (0.733) using AF and MFCC, DenseNet (0.621) using MFCC, and Isolation Forest (0.610) using AF. Even though these results are of exploratory character, conducted experiments do show promising potential of gradient boosting and deep learning methods to robustly detect voice pathologies.

Voice Pathology Detection Using Deep Learning on Mobile Healthcare Framework

The feasibility and popularity of mobile healthcare are currently increasing. The advancement of modern technologies, such as wireless communication, data processing, the Internet of Things, cloud, and edge computing, makes mobile healthcare simpler than before. In addition, the deep learning approach brings a revolution in the machine learning domain. In this paper, we investigate a voice pathology detection system using deep learning on the mobile healthcare framework. A mobile multimedia healthcare framework is also designed. In the voice pathology detection system, voices are captured using smart mobile devices. Voice signals are processed before being fed to a convolutional neural network (CNN). We use a transfer learning technique to use the existing robust CNN models. In particular, the VGG-16 and CaffeNet models are investigated in the paper. The Saarbrucken voice disorder database is used in the experiments. Experimental results show that the voice pathology detection accuracy reaches up to 97.5% using the transfer learning of CNN models.

Smart Health Solution Integrating IoT and Cloud: A Case Study of Voice Pathology Monitoring

The integration of the IoT and cloud technology is very important to have a better solution for an uninterrupted, secured, seamless, and ubiquitous framework. The complementary nature of the IoT and the could in terms of storage, processing, accessibility, security, service sharing, and components makes the convergence suitable for many applications. The advancement of mobile technologies adds a degree of flexibility to this solution. The health industry is one of the venues that can benefit from IoT–Cloud technology, because of the scarcity of specialized doctors and the physical movement restrictions of patients, among other factors. In this article, as a case study, we discuss the feasibility of and propose a solution for voice pathology monitoring of people using IoT–cloud. More specifically, a voice pathology detection system is proposed inside the monitoring framework using a local binary pattern on a Mel-spectrum representation of the voice signal, and an extreme learning machine classifier to detect the pathology. The proposed monitoring framework can achieve high accuracy of detection, and it is easy to use.

Automatic voice pathology detection and classification using vocal tract area irregularity

In this paper, an automatic voice pathology detection (VPD) system based on voice production theory is developed. More specifically, features are extracted from vocal tract area, which is connected to the glottis. Voice pathology is related to a vocal fold problem, and hence the vocal tract area which is connected to vocal folds or glottis should exhibit irregular patterns over frames in case of a sustained vowel for a pathological voice. This irregular pattern is quantified in the form of different moments across the frames to distinguish between normal and pathological voices. The proposed VPD system is evaluated on the Massachusetts Eye and Ear Infirmary (MEEI) database and Saarbrucken Voice Database (SVD) with sustained vowel samples. Vocal tract irregularity features and support vector machine classifier are used in the proposed system. The proposed system achieves 99.22%±0.01 accuracy on the MEEI database and 94.7%±0.21 accuracy on the SVD. The results indicate that vocal tract irregularity measures can be used effectively in automatic voice pathology detection.