Closed-set automatic speaker identification using multi-scale recurrent networks in non-native children.

Children may benefit from automatic speaker identification in a variety of applications, including child security, safety, and education. The key focus of this study is to develop a closed-set child speaker identification system for non-native speakers of English in both text-dependent and text-independent speech tasks in order to track how the speaker's fluency affects the system. The multi-scale wavelet scattering transform is used to compensate for concerns like the loss of high-frequency information caused by the most widely used mel frequency cepstral coefficients feature extractor. The proposed large-scale speaker identification system succeeds well by employing wavelet scattered Bi-LSTM. While this procedure is used to identify non-native children in multiple classes, average values of accuracy, precision, recall, and F-measure are being used to assess the performance of the model in text-independent and text-dependent tasks, which outperforms the existing models.

A Novel 3-Step Tuning Fork Hearing Test; Preliminary Report on Its Clinical Utility.

It is pertinent to have a Tuning Fork Hearing Test that stand-alone can detect severities (Mild, Moderate, Severe and Profound) and the types of hearing losses (Conductive, Sensorineural, and Mixed). A novel 3-Step Tuning Fork Hearing Test (3-STFHT) was attempted for the first time that could detect both the types and the severities of hearing losses. The study was aimed to describe the method of the 3-STFHT and evaluate its clinical utility and reliability. Research Design: Hospital-based observational study of a diagnostic tool. Settings: Otorhinolaryngology Department of a tertiary care medical college hospital. Subjects: 108 adult patients (216 ears) who required hearing evaluation. Main Outcome measures: Sensitivity and specificity of novel 3-STFHT were assessed by comparing its results with the reports of pure tone audiometry in detecting the type and severity of hearing loss. The new 3-STFHT was found very effective (100% sensitivity and specificity) in detecting conductive and profound sensorineural hearing losses. The sensitivity in detecting sensorineural hearing loss was found 97%-100%. The sensitivity was observed relatively low (92%) at detecting mixed hearing loss. The overall sensitivity and specificity of the 3-STFHT in detecting the types of hearing losses was found 97% and 86% respectively. The novel 3-STFHT, which is simple and convenient, was found very effective in detecting the types and severity of hearing losses. The 3-STFHT can be an important tool in otorhinolaryngology practice and in primary care setting for detecting and screening the types and severities of hearing losses. Supplementary Information: The online version contains supplementary material available at 10.1007/s12070-022-03095-0.

Clinical Evaluation of 'Computer-Aided Diagnosis InNeuro-Otology (CADINO)' in Terms of Usefulness, Functionality and Effectiveness.

Computer-based medical diagnosis expert systems are considered both accurate and educationally helpful in most cases. Dizziness and vertigo are among the most common complaints however E.N.T. surgeons and neuro-otologists are not available in the peripheral areas. Computer-Aided Diagnosis In NeurOtology (CADINO) can be of immense value for these unprivileged dizzy patients of remote and rural areas. The study aimed to document the strength, weaknesses and capabilities of CADINO in terms of accuracy, educational usefulness, functionality and effectiveness. Design Hospital-based observational study of a diagnostic tool. Settings Otorhinolaryngology Department of a tertiary care medical college hospital. This prospective study was conducted in 70 patients, 24 simulated cases and 6 case reports from journals. The study included even the feedback of the clinicians before and after consultation. Eleven ENT residents, 14 ENT surgeons [8 teachers and 6 consultants] participated in the study. The overall diagnostic accuracy of the CADINO was found 86%. While in the patients, CADINO accuracy was found 84% approximately similar to faculties/consultants (80%) but it was significantly better than that of residents (57%). Most of the clinicians (84%), rated the CADINO consultation as being educationally helpful, and useful for patient management. CADINO was found very effective and convenient as it could be operated in the OPD simultaneously while evaluating the dizzy patients. CADINO provided accurate diagnostic suggestions. It was found improving patient safety and quality of care by enhancing knowledge and cognitive skills of the clinicians.

Dietary Risk Factors in Upper Aero-Digestive Tract Cancers.

The Upper AeroDigestive Tract (UADT) cancers are most common, invasive and have high morbidity. The two leading risk factors, smoking and alcohol, are well known but there is a long list of other risk factors which are not that well talked about. The aim of this study was to ascertain the dietary factors which could be important in their prevention.The PubMed and Google Scholar databases were searched for relevant studies from January 2001 to November 2021. Refined grains were found directly related to the risk of UADT cancer while the whole grain cereals were found protective. Significant inverse associations were observed for the highest compared to the lowest tertile of whole grains and yellow/orange vegetables. Stricter adherence to the Mediterranean diet was seen associated with a substantial and significant decrease in UADT cancer risk. A significant inverse association was also found between yoghurt intake and UADT cancer risk. Consumption of three or more cups of coffee per day was found to have a significant inverse association with UADT cancer. Carcinogenicity of cannabis consumption was observed for regular cannabis smokers (> 1 per day for years). The current study concludes that the protective dietary factors have substantial activity in the prevention of UADT cancer. Nevertheless, basic research is required in investigating the role of these dietary factors and valid biomarkers will be important for chemoprevention studies. The basic research on risk factors on the basis of current knowledge would ultimately lead to the better prevention of UADT cancer.

Audio Augmentation for Non-Native Children's Speech Recognition through Discriminative Learning.

Automatic speech recognition (ASR) in children is a rapidly evolving field, as children become more accustomed to interacting with virtual assistants, such as Amazon Echo, Cortana, and other smart speakers, and it has advanced the human-computer interaction in recent generations. Furthermore, non-native children are observed to exhibit a diverse range of reading errors during second language (L2) acquisition, such as lexical disfluency, hesitations, intra-word switching, and word repetitions, which are not yet addressed, resulting in ASR's struggle to recognize non-native children's speech. The main objective of this study is to develop a non-native children's speech recognition system on top of feature-space discriminative models, such as feature-space maximum mutual information (fMMI) and boosted feature-space maximum mutual information (fbMMI). Harnessing the collaborative power of speed perturbation-based data augmentation on the original children's speech corpora yields an effective performance. The corpus focuses on different speaking styles of children, together with read speech and spontaneous speech, in order to investigate the impact of non-native children's L2 speaking proficiency on speech recognition systems. The experiments revealed that feature-space MMI models with steadily increasing speed perturbation factors outperform traditional ASR baseline models.

Otorhinolaryngology Malignancies in Children: A Case Series.

BACKGROUND AND OBJECTIVES: Ear, nose and throat (E.N.T.) malignancies in children are rare and can have different characteristics than those occurring among adults. Early diagnosis and treatment can improve the survival rates. The aim of this study was to determine the incidence of different E.N.T. malignant tumours in children and the way they presented so that they could be diagnosed early and managed efficiently in time. The other object of the study was to highlight the clinical, pathological, diagnostic and therapeutic features of E.N.T. malignancies in children which were of paramount importance in their effective management. MATERIAL AND METHODS: This hospital-based observational study reports on the incidence of different E.N.T. malignancies in children seen over a period of 5 years in the Department of E.N.T. in a tertiary care medical college hospital. We studied 25 patients in this case series of paediatric E.N.T. malignancies. RESULTS: E.N.T. malignancies accounted for approximately 20% of all paediatric malignancies. We observed 17 (68%) cases of carcinoma while mesenchymal malignancies were seen in 8 (32%) cases. Mesenchymal tumours included rhabdomyosarcoma, fibrosarcoma, and neuroblastoma etc. The nasopharynx and laryngopharynx were two of the commonest sites. Other less common sites were the parotid gland, nose and paranasal sinuses, tongue, oesophagus and larynx. CONCLUSION: The E.N.T. malignancies in children are rare and constitutes 20% of all paediatric malignancies. Carcinoma was found more common (68%) than the sarcoma (32%). The nasopharynx and laryngopharynx were found to be the most common sites. They usually present with features that are common in benign illnesses thereby masking the serious nature of the disease. However, the awareness about these tumours and complete examination and early imaging studies and biopsy in suspected children can secure early diagnosis. Radiation therapy is commonly used either alone or with chemotherapy. Radiotherapy can also be given either before or after surgical excision. The pathological nature of the tumour and the time taken to start definite treatment determines the prognosis.

A Simple, Objective, and Mathematical Grading Scale for the Assessment of Facial Nerve Palsy.

OBJECTIVES: It is imperative to acquire a simple, objective, and mathematical method for the assessment of facial nerve palsy which can be universally accepted and implemented. A grading scale which is convenient, continuous and economical was attempted for the first time for global and region-specific assessment of facial nerve palsy. STUDY DESIGN: Hospital-based observational study. SETTING: Medical college hospital. PATIENTS: Ten normal subjects and 51 patients with facial paralysis. INTERVENTIONS: Patients with facial nerve palsy were graded according to the revised version of House-Brackmann grading system (HBGS-2) and a newly proposed grading system. MAIN OUTCOME MEASURES: The results of the present study were compared with the HBGS-2. Data were analyzed using SPSS-17 (IBM Corporation, New York) for descriptive statistics, normality test, Wilcoxon signed-rank test, and Mann-Whitney U test. RESULTS: The mean time spent on recording measurements was 288 seconds. For the new method and HBGS-2, the modes were graded 3 and 4, corresponding to incomplete facial paralysis. The Kolmogorov-Smirnov normality and Wilcoxon signed rank tests were found significant. In Mann-Whitney U test, probability value indicated that grades of new scale were similar to grades of HBGS-2. CONCLUSION: The proposed simple, objective and mathematical (SOM) method of grading facial nerve palsy is convenient and provides global and regional continuous percentage that can monitor the progress and classify the patients with facial paralysis into six-point grades based on severity. This system was having substantial compatibility with HBGS-2 grading. For further validity, multi-center study with a larger sample of patients would be required.

Development of an Experimental System "Computer-Aided Diagnosis in Neurotology (CADINO)" for Vertigo.

Computer-based medical diagnosis expert systems, when used by clinicians, familiar with the limitations of the system, were found both accurate and educationally helpful. Vertigo is one of the most common complaints of the patients and the specialists who manage these patients are not easily available. Diagnostic expert system can help clinicians including general practitioners in providing reasonable diagnostic suggestions while dealing with patients with vertigo/dizziness when the specialist doctors are not available. To provide an understanding about the method of making an expert system "Computer-Aided Diagnosis in Neurotology (CADINO)" for dizzy patients and highlight its potential uses. CADINO, developed during this original research project, is an expert computer program which is capable of making diagnoses in patients with vertigo. CADINO includes more than 100 causes of vertigo. It was developed in Microsoft Office using hyperlinks. CADINO has the potential of making diagnoses in patients with vertigo. It differs from most other programs for computer-assisted diagnosis in the generality of its approach and knowledge base. Specific deficiencies of CADINO include its inability to explain its thinking. CADINO can broaden the clinicians' scope and awareness regarding the findings which are important for making the differential diagnoses in patients with vertigo/dizziness. Though the CADINO on its face value seems to improve patient safety and quality of care by enhancing knowledge and cognitive skills of the clinicians, yet it remains a research tool and will need clinical evaluation in terms of diagnostic accuracy.

Introduction of Directly Observed Procedural Skills (DOPS) as a Part of Competency-Based Medical Education in Otorhinolaryngology.

The Directly Observed Procedural/Practical Skill (DOPS) is a relatively new but reliable tool for formative assessment. The lack of desired awareness regarding DOPS among the Otorhinolayngologists of India made us to conduct this study. The aim of the study was introduction of DOPS in Oto-rhino-laryngology Department. The objectives of the study were: (1) To prepare lists of Oto-rhino-laryngology procedures for DOPS, (2) To conduct Orientation program of DOPS for the participants, (3) To prepare a structured list of items for the rating scale, (4) To facilitate and conduct DOPS encounters of different Oto-rhino-laryngology procedures. The study was conducted in a tertiary care medical college hospital from April 2018 to August 2018. Thirty-three trainees and 5 trainers participated. The 421 DOPS encounters involved 41 Oto-rhino-laryngology procedures. For checking the association between average time and clinical settings and Oto-rhino-laryngology procedures and DOPS encounters, the nonparametric test χ2 test was employed. Male trainees (63.63%) outnumbered female trainees. Mostly trainees (91%) were aged 22-25 years. Approximately half (49%) of the Oto-rhino-laryngology procedures (20/41) and 9/10th (86.22%) of DOPS encounters (363/421) were conducted in OPD. The average time taken to complete the E.N.T. procedures and DOPS encounters was 15 min or less in the majority (91% and 98%) of the Oto-rhino-laryngology procedures (38/41) and DOPS encounters (414/421). DOPS was introduced as a learning tool in the Oto-rhino-laryngology Department of our medical college. For assessing the "competency level" of trainees for E.N.T. procedures, DOPS is a high quality instrument as it tests the candidate at the "does" level.

Why Cannot We have an Etiological Classification for the Patients with Granular Myringitis?

Though granular myringitis (GM) is not a very rare disease it does not have any classification. Its exact etiology is not known. The granulations on tympanic membrane also occur in association with other lesions of external auditory canal (EAC) and middle ear. The aims of this study were to know the etiological factors of GM and classify the disease according to its etiological factors and associated disorders of EAC and middle ear. Data were retrieved from the search of four electronic databases: PubMed, EMBASE, Cochrane Library, and Google scholar. Relevant articles were also sought by a hand search review of reference books. The databases were searched using the key words otitis externa, external otitis, granular myringitis, granular otitis externa and myringitis. Data were extracted using a pre-defined data-extraction form. The following data were recorded (1) etiological and predisposing conditions; (2) pathological features; (3) associated disorders of external and middle ear. The study proposes the etiological classification of GM. It suggests two major groups: primary and secondary. The primary GM is basically idiopathic and these patients do no have evidences of any other types of otitis media and otitis externa. In the secondary GM the cause is obvious and the patients usually have associated otitis media and/or lesions of external ear canal. Author speculates that habit of self ear cleaning/scratching is a specific etiological factor in cases of primary GM but more studies are required to confirm this theory.

Teflon Implants Versus Titanium Implants in Stapes Surgery.

Otosclerosis is the most common cause of bilateral gradually progressive conductive hearing loss with normal tympanic membrane and Eustachian tube. Otosclerosis surgical treatment is one of the most gratifying operations in Otorhinolaryngology. It is not only the surgical techniques but also the prosthesis which are evolving in the attempt of providing best hearing results. Teflon piston is the most commonly employed prosthesis in stapes surgery. Titanium pistons are relatively the new development in the evolution of stapes prosthesis. The aim of this review article is to know and compare the surgical technicalities and postoperative outcomes including hearing improvement after the use of Teflon and titanium stapes piston. The adverse reactions occurred during follow-up were taken into consideration. The data in this article are supported by a Medline search. The use of both the prosthesis gave good results in cases of otosclerosis. The placement of titanium soft clip design was found easier than the earlier àWengen design of clip piston.