Classification of Pathological Voices Using Glottal Signal Parameters

Automatic detection and assessment of Vocal Folds pathologies using signal processing techniques knows an extensively challenge use in the voice or speech research community. This paper contributes the application of the Recurrence Quantification Analysis (RQA) to a glottal signal waveform in order to evaluate the dynamic process of Vocal Folds (VFs) for diagnosis and classify the voice disorders. The proposed solution starts by extracting the glottal signal waveform from the voice signal through an inverse filtering algorithm. In the next step, the parameters of RQA are determined via the Recurrent Plot (RP) structure of the glottal signal where the normal voice is considered as a reference. Finally, these parameters are used as input features set of a hybrid Particle Swarm Optimization-Support Vector Machines (PSO-SVM) algorithms to segregate between normal and pathological voices. For the test validation, we have adopted the collection of Saarbrucken Voice Database (SVD) where we have selected the long vowel /a:/ of 133 normal samples and 260 pathological samples uttered by four groups of subjects : persons having suffered from vocal folds paralysis, persons having vocal folds polyps, persons having spasmodic dysphonia and normal voices. The obtained results show the effectiveness of RQA applied to the glottal signal as a features extraction technique. Indeed, the PSO-SVM as a classification method presented an effective tool for assessment and diagnosis of pathological voices with an accuracy of 97.41%

Multimodal Voice Pathology Detection With Voice Signal and Integrated Electroglottographic (EGG) Signal From the Saarbrücken Voice Database.

Perception of Disordered Voice: Reaction Time, Accuracy, and Neural Processing.

Wavelet adaptation for automatic voice disorders sorting

Application of Wavelet Analysis and Paraconsistent Feature Extraction in the Classification of Voice Pathologies.

Relative entropy measures applied to healthy and pathological voice characterization

Emotions can be detected through facial expressions, voice signals, and physiological signals such as Galvanic Skin Response (GSR), Electroencephalogram (EEG), and Electrocardiogram (ECG). However, there have been limited studies on using GSR signals for emotion detection. Emotion recognition systems (ERS) use artificial intelligence to diagnose emotions and trigger appropriate actions accurately. This study introduces a novel lightweight deep Convolutional Neural Network (LWDCNN) for emotion classification using GSR data. The LWDCNN model reduces computational complexity while improving the speed and accuracy of the classification. GSR data is normalized based on suitable segmentation. A seven-fold cross-validation technique is employed to classify emotions using LWDCNN based on the arousal and valence dimensions. Emotions are classified based on the social and non-social context of the subjects using GSR data from the AMIGOS (A Dataset for Affect, Personality, and Mood Research on Individuals and Groups) database in both individual (non-social) and group (social) settings. The accuracy of valence classification is 78.83% for individual settings and 79.96% for group settings. The accuracy of arousal classification is 80.62% for individual settings and 84.42% for group settings. This model can effectively be used to diagnose the subjects' mental health by detecting the appropriate emotions. Goa College of Engineering, Affiliated with Goa University, Goa, India.

A novel voice pathology detection technique through deep neural networks utilizing speech and electroglottographic signals

The quality analysis of pathological voice is not only a kind of objective evaluation for the human voice, but also an objective evidence for the application of voice disease diagnosis and the judgment of therapy. In this paper, the pathological voice quality analysis system is composed of five parts, which are voice recording, voice signal processing, and extraction of voice characteristic parameters, choice of these features and evaluation of voice quality. Firstly, this paper gives a brief introduction to the pathological voice quality analysis's background and purpose. Besides, it also details some methods of voice signal processing. For detection of voice period, vague fundamental frequency of voice is extracted firstly by using Fourier transform, and then the accurate detection of the voice period through EGG and wavelet transformation is performed. This method of period detection is highly accurate and practicable. Based on the period of voice, many features of voice such as the fundamental frequency, frequency perturbation, and amplitude perturbation can be extracted. This database is built by collecting healthy and pathological voice samples from Shengjing Hospital and related references. After analyzing the collected voice signals, the result shows that the pathological voice quality analysis system has the well evaluation performance in the practical application. These evaluation results reflect the quality of voice signal and can be used to assistant judge the treatment of voice disease and the recovery condition of treatment.

Vocal disorders are potentially an underreported condition due to invasive diagnostic methods and a lack of general awareness. Traditionally, vocal damage is diagnosed through laryngoscopies, but recent research supports using audio processing and machine learning to distinguish between not only healthy and unhealthy voices but also between different vocal pathologies. This study introduces a framework for classifying multiple vocal pathologies—dysphonia, polyps, nodules, and paralysis, based on previous research focused on two-class classification. The current approach employs continuous wavelet transforms (CWT) and spectrograms from pathological voices, /AH/ and /EE/ audio files from the Indiana University (IU) Health Voice Center, as inputs for a convolutional neural network (CNN) classifier. The images from the wavelet transform achieve higher accuracy than spectrograms for both two-class and multiclass classification. Various wavelet shapes and sizes are compared for accuracy rates and processing time. Different signal-to-noise ratios and augmentation techniques are tested for classification robustness and accuracy. The study also compares male and female voices on classification accuracy and how parameters, like learning rates and filter layers, affect CNN performance. Results indicate that accuracy improves with a 0.0001 learning rate and optimal image sizes, demonstrating the potential for enhancing classification models through precise parameter tuning.

Machine Learning Models With Hyperparameter Optimization for Voice Pathology Classification on Saarbrücken Voice Database.

Methodologies of speech analysis for neurodegenerative diseases evaluation

Classification of functional voice disorders based on phonovibrograms

The development of methods that combine different sources of information for the purposes of medical diagnosis is an essential challenge in the field of medical informatics. In this context, we introduce a machine-learning framework for automatic voice pathology classification and, in particular, a modular deep learning architecture that classifies voice signals stemming from four types of voice disorders. To this end, we design a multimodal deep learning architecture that fuses medical metadata with voice signals. Our classifier is a combination of fully convolutional and feed-forward sub-networks that simultaneously process low-level and mid-level features which are extracted from acoustic signals of varying duration and medical records, respectively. A key objective of our study is to develop an architecture that is capable of processing voice samples of varying duration, in order to enhance the system’s learning and inference capabilities. Our research also focuses on overcoming performance limitations of neural networks that stem from the lack of extensive volumes of training data. We therefore investigate problem specific augmentation techniques based on the feature sequence segmentation and coloured noise injection and we show that the proposed method gives state-of-the-art results, achieving 64.4% classification accuracy, compared to the 63.5% classification score of the best performing method of the 2019 FEMH data challenge.

A measure of the harmonics-to-noise ratio (HNR) in voice signals is used for assisting in the classification of voice pathologies. HNR estimation for voice signals has been investigated using time domain, cepstral, Fourier series and Fourier transform analyses. The present investigation focuses on methods that use a direct application of the Fourier transform to the signal. Three approaches to obtaining a HNR index from the power spectrum are reviewed. The present study uses synthetic voice signals to provide an unambiguous assessment of methods. The study highlights the fact that even though the indices derived from the power spectrum are useful in separating pathological and normal voice data sets, they provide only indirect information regarding the HNR of the glottal signal.