Mohamed Farahat

Multidirectional Regression (MDR)-Based Features for Automatic Voice Disorder Detection

BACKGROUND AND OBJECTIVEnObjective assessment of voice pathology has a growing interest nowadays. Automatic speech/speaker recognition (ASR) systems are commonly deployed in voice pathology detection. The aim of this work was to develop a novel feature extraction method for ASR that incorporates distributions of voiced and unvoiced parts, and voice onset and offset characteristics in a time-frequency domain to detect voice pathology.nnnMATERIALS AND METHODSnThe speech samples of 70 dysphonic patients with six different types of voice disorders and 50 normal subjects were analyzed. The Arabic spoken digits (1-10) were taken as an input. The proposed feature extraction method was embedded into the ASR system with Gaussian mixture model (GMM) classifier to detect voice disorder.nnnRESULTSnAccuracy of 97.48% was obtained in text independent (all digits training) case, and over 99% accuracy was obtained in text dependent (separate digits training) case. The proposed method outperformed the conventional Mel frequency cepstral coefficient (MFCC) features.nnnCONCLUSIONnThe results of this study revealed that incorporating voice onset and offset information leads to efficient automatic voice disordered detection.

Formant analysis in dysphonic patients and automatic Arabic digit speech recognition

Background and objectiveThere has been a growing interest in objective assessment of speech in dysphonic patients for the classification of the type and severity of voice pathologies using automatic speech recognition (ASR). The aim of this work was to study the accuracy of the conventional ASR system (with Mel frequency cepstral coefficients (MFCCs) based front end and hidden Markov model (HMM) based back end) in recognizing the speech characteristics of people with pathological voice.Materials and methodsThe speech samples of 62 dysphonic patients with six different types of voice disorders and 50 normal subjects were analyzed. The Arabic spoken digits were taken as an input. The distribution of the first four formants of the vowel /a/ was extracted to examine deviation of the formants from normal.ResultsThere was 100% recognition accuracy obtained for Arabic digits spoken by normal speakers. However, there was a significant loss of accuracy in the classifications while spoken by voice disordered subjects. Moreover, no significant improvement in ASR performance was achieved after assessing a subset of the individuals with disordered voices who underwent treatment.ConclusionThe results of this study revealed that the current ASR technique is not a reliable tool in recognizing the speech of dysphonic patients.

An Investigation of Multidimensional Voice Program Parameters in Three Different Databases for Voice Pathology Detection and Classification

BACKGROUND AND OBJECTIVEnAutomatic voice-pathology detection and classification systems may help clinicians to detect the existence of any voice pathologies and the type of pathology from which patients suffer in the early stages. The main aim of this paper is to investigate Multidimensional Voice Program (MDVP) parameters to automatically detect and classify the voice pathologies in multiple databases, and then to find out which parameters performed well in these two processes.nnnMATERIALS AND METHODSnSamples of the sustained vowel /a/ of normal and pathological voices were extracted from three different databases, which have three voice pathologies in common. The selected databases in this study represent three distinct languages: (1) the Arabic voice pathology database; (2) the Massachusetts Eye and Ear Infirmary database (English database); and (3) the Saarbruecken Voice Database (German database). A computerized speech lab program was used to extract MDVP parameters as features, and an acoustical analysis was performed. The Fisher discrimination ratio was applied to rank the parameters. A t test was performed to highlight any significant differences in the means of the normal and pathological samples.nnnRESULTSnThe experimental results demonstrate a clear difference in the performance of the MDVP parameters using these databases. The highly ranked parameters also differed from one database to another. The best accuracies were obtained by using the three highest ranked MDVP parameters arranged according to the Fisher discrimination ratio: these accuracies were 99.68%, 88.21%, and 72.53% for the Saarbruecken Voice Database, the Massachusetts Eye and Ear Infirmary database, and the Arabic voice pathology database, respectively.

Development and validation of the Arabic pediatric voice handicap index

BACKGROUND AND OBJECTIVEnVoice problems negatively affect how children are perceived both by adults and by their peers. Although voice disorders are common in the pediatric population, there is still a lack of information available to clinicians regarding evaluation and treatment of pediatric voice disorders. The purpose of the present study was to develop an Arabic version of pediatric VHI and to test its validity and reliability.nnnSUBJECTS AND METHODSnFifty children with voice disorders were included in the study. The Arabic version of PVHI was derived in the standard way for test translation. The translated version was then administrated to the parents or caregiver of children with voice disorders and parents of 75 children with no history or symptoms of voice problems. Participants responses were statistically analyzed to assess the validity, and to compare the pathological group with the control group.nnnRESULTSnThe results showed high internal consistency and reliability of the Arabic version of PVHI (Cronbachs α=0.93 and r=0.95, respectively), and high item-domain and domain-total correlation (r=0.86-0.97). There was a statistically significant difference between the control and the voice disordered groups (P<0.001).nnnCONCLUSIONnThe Arabic version of PVHI is considered to be a valid and reliable assessment tool used by the parents and caregivers of children with voice disorders to assess the severity of voice disorders in Arabic language speaking children.

Development of the Arabic Version of Dysphagia Handicap Index (DHI)

The Dysphagia Handicap Index (DHI) is a 25-item self-administered questionnaire. It is a noninvasive tool for measuring the handicapping effect of dysphagia on the physical, functional, and emotional aspects of people’s lives. The purposes of the present study were to develop an Arabic version of the DHI and to evaluate its validity, consistency, and reliability in the normal Arabic population with oropharyngeal dysphagia. This was a prospective study that was carried out at the Communication and Swallowing Disorders Unit, King Saud University. The generated Arabic DHI was administered to 94 patients with oropharyngeal dysphagia and 98 control subjects. Internal consistency and test-retest reliability were evaluated. The results of the patients and the control group were compared. The Arabic DHI showed excellent internal consistency (Cronbach’s αxa0=xa00.95). Also, good test–retest reliability was found for the total scores of the Arabic DHI (rxa0=xa00.9, pxa0=xa00.001). There was a significant difference between the DHI scores of the control group and those of the oropharyngeal dysphagia group (pxa0<xa00.001). This study demonstrated that the Arabic DHI is a valid tool for self-assessment of the handicapping effect of dysphagia on the physical, functional, and emotional aspects of patients and can be used by Arabic language speakers.

Intra- and Inter-database Study for Arabic, English, and German Databases: Do Conventional Speech Features Detect Voice Pathology?

A large population around the world has voice complications. Various approaches for subjective and objective evaluations have been suggested in the literature. The subjective approach strongly depends on the experience and area of expertise of a clinician, and human error cannot be neglected. On the other hand, the objective or automatic approach is noninvasive. Automatic developed systems can provide complementary information that may be helpful for a clinician in the early screening of a voice disorder. At the same time, automatic systems can be deployed in remote areas where a general practitioner can use them and may refer the patient to a specialist to avoid complications that may be life threatening. Many automatic systems for disorder detection have been developed by applying different types of conventional speech features such as the linear prediction coefficients, linear prediction cepstral coefficients, and Mel-frequency cepstral coefficients (MFCCs). This study aims to ascertain whether conventional speech features detect voice pathology reliably, and whether they can be correlated with voice quality. To investigate this, an automatic detection system based on MFCC was developed, and three different voice disorder databases were used in this study. The experimental results suggest that the accuracy of the MFCC-based system varies from database to database. The detection rate for the intra-database ranges from 72% to 95%, and that for the inter-database is from 47% to 82%. The results conclude that conventional speech features are not correlated with voice, and hence are not reliable in pathology detection.

Voice pathology detection with MDVP parameters using Arabic voice pathology database

This paper investigates the use of Multi-Dimensional Voice Program (MDVP) parameters to automatically detect voice pathology in Arabic voice pathology database (AVPD). MDVP parameters are very popular among the physician / clinician to detect voice pathology; however, MDVP is a commercial software. AVPD is a newly developed speech database designed to suit a wide range of experiments in the field of automatic voice pathology detection, classification, and automatic speech recognition. This paper is the first step to evaluate MDVP parameters in AVPD using sustained vowel /a/. The experimental results demonstrate that some of the acoustic features show an excellent ability to discriminate between normal and pathological voices. The overall best accuracy is 81.33% by using SVM classifier.

Application of in-plant control measures in some Egyptian micro-scale dairy enterprises and its impact on heavy metal contents of their products

Egypt is encouraging micro-scale enterprises as proved to be one of the most important reasons of economic growth. Most of the annual milk production is processed in micro-scale dairy enterprises located in squatter areas with high health risks and negative environmental impact. The aim of this study was to assess the effectiveness of in-plant control measures in controlling lead and cadmium levels in dairy products from nine Egyptian micro-scale enterprises. The results revealed that white cheese enterprises had the highest mean lead and cadmium contents; both in their raw milk (0.712 and 0.134xa0mg/L, respectively) and final products (0.419 and 0.061xa0mg/kg). Higher compliance percentages were found with cadmium levels specified in the Egyptian standards than with lead levels and ranged from 59.4% in raw milk to 100% in dry milk for cadmium levels and from 8.3% in white cheese to 66.7% in ice cream for lead; moreover, none of the collected raw milk samples were complying with the lead levels. After implementation of in-plant control measures, lower lead levels were found in all samples with reduction percentages ranging from 35.2% in raw milk from the ice cream enterprises to 73.2% in yoghurt; moreover, higher percentages of samples complied with cadmium levels. This study highlights the urgent need for applying in-plant control measures to the Egyptian micro-scale dairy enterprises to improve both safety and quality of their products.