The recognition of pathological voice is considered a difficult task for speech analysis.Moreover,otolaryngologists needed to rely on oral communication with patients to discover traces of voice pathologies like dysph...The recognition of pathological voice is considered a difficult task for speech analysis.Moreover,otolaryngologists needed to rely on oral communication with patients to discover traces of voice pathologies like dysphonia that are caused by voice alteration of vocal folds and their accuracy is between 60%–70%.To enhance detection accuracy and reduce processing speed of dysphonia detection,a novel approach is proposed in this paper.We have leveraged Linear Discriminant Analysis(LDA)to train multiple Machine Learning(ML)models for dysphonia detection.Several ML models are utilized like Support Vector Machine(SVM),Logistic Regression,and K-nearest neighbor(K-NN)to predict the voice pathologies based on features like Mel-Frequency Cepstral Coefficients(MFCC),Fundamental Frequency(F0),Shimmer(%),Jitter(%),and Harmonic to Noise Ratio(HNR).The experiments were performed using Saarbrucken Voice Data-base(SVD)and a privately collected dataset.The K-fold cross-validation approach was incorporated to increase the robustness and stability of the ML models.According to the experimental results,our proposed approach has a 70%increase in processing speed over Principal Component Analysis(PCA)and performs remarkably well with a recognition accuracy of 95.24%on the SVD dataset surpassing the previous best accuracy of 82.37%.In the case of the private dataset,our proposed method achieved an accuracy rate of 93.37%.It can be an effective non-invasive method to detect dysphonia.展开更多
A 35-year-old female patient with spasmodic dysphonia underwent massage and vocal training. Chinese manipulation was administered to Tiantu （CV 22） and Lianquan （CV 23）, the convergent acupoints of the conception ...A 35-year-old female patient with spasmodic dysphonia underwent massage and vocal training. Chinese manipulation was administered to Tiantu （CV 22） and Lianquan （CV 23）, the convergent acupoints of the conception meridian and Yin link vessel, Yamen （GV 15） and Fengfu （GV 16）, the convergent acupoints of Du meridian and Yang link vessel, as well as large intestine channel of hand Yangming Hegu （LI 4）, by gently pressing and rubbing for stimulation. In addition, throat muscle massage therapy and vocal training were performed. Results were evaluated using acoustic measurements in combination with a single statistical method. A comprehensive treatment combining vocal training and face-neck massage was shown to relieve dystonia of facial-cervical muscles in patients, as well as improve voice quality while providing a safe treatment method.展开更多
Objectives: This study aims to analyze the impact of age and sex on botulinum neurotoxin (BoNT-A) dosing and outcomes in adductor spasmodic dysphonia (AdSD).Methods: A database review of all spasmodic dysphonia patien...Objectives: This study aims to analyze the impact of age and sex on botulinum neurotoxin (BoNT-A) dosing and outcomes in adductor spasmodic dysphonia (AdSD).Methods: A database review of all spasmodic dysphonia patients treated with BoNT from 1989 to 2018 at the Mayo Clinic in Arizona was performed. Only patients who had received ≥4 injections of BoNT-A for AdSD were included. Patients were divided into two cohorts to analyze age, with an age of first treatment cutoff of 60 years. Patients were divided into male and female cohorts to analyze sex.Results: The final analysis included 398 patients. The mean dose of BoNT-A per treatment was significantly higher in the younger cohort (4.4 vs. 3.9 units,p = 0.048). The mean maximal benefit was similar (72% vs. 70%,p = 0.48);however, the mean length of benefit was significantly shorter in younger patients (3.0 vs. 3.6 months,p < 0.01). The mean BoNT-A dose was significantly higher in the female cohort (4.2 vs. 3.6 units,p = 0.02). The mean maximal benefit was similar (69% vs. 75%,p = 0.58), as was the mean length of benefit (3.2 vs. 3.5 months,p = 0.11).Conclusions: This study suggests that age and sex influence BoNT-A dosing and outcomes in AdSD.展开更多
Laryngeal tuberculosis is a rare entity. We consider the case of a woman of 62 who presented a one-year evolving chronic dysphonia chart associated with cough, febricula and general health damage. The nasofibroscopy s...Laryngeal tuberculosis is a rare entity. We consider the case of a woman of 62 who presented a one-year evolving chronic dysphonia chart associated with cough, febricula and general health damage. The nasofibroscopy showed a budding ulcerous lesion of the larynx a priori evoking a granulomatous lesion or cancer. The BAAR spits were strongly positive and the radiographic pictures of the thorax, typically evoked a pulmonary tuberculosis. Seeing the excellent therapeutic response to TB treatment in 4 months period, the bifocal tuberculosis diagnostic was confirmed.展开更多
Laryngeal tuberculosis is a rare form of extrapulmonary tuberculosis, often complicating pulmonary tuberculosis that may be unrecognized. Its clinical presentation is nonspecific, often pointing to cancer. We report t...Laryngeal tuberculosis is a rare form of extrapulmonary tuberculosis, often complicating pulmonary tuberculosis that may be unrecognized. Its clinical presentation is nonspecific, often pointing to cancer. We report the case of a 77-year-old woman, with no reported pathological history. She also has no alcohol or tobacco intoxication, who presented with chronic dysphonia evolving for 2 months, associated with an altered general condition. The examination of the larynx by direct laryngoscopy and anatomical pathology study of the biopsies led to the diagnosis of laryngeal tuberculosis. A search for secondary sites revealed a concomitant pulmonary infection. The evolution was favorable under standard anti-tuberculosis treatment, with complete voice recovery and improved performance status. Laryngeal tuberculosis should be suspected in patients living in endemic areas and suffering from chronic dysphonia, even if they are not alcoholics or smokers.展开更多
文摘The recognition of pathological voice is considered a difficult task for speech analysis.Moreover,otolaryngologists needed to rely on oral communication with patients to discover traces of voice pathologies like dysphonia that are caused by voice alteration of vocal folds and their accuracy is between 60%–70%.To enhance detection accuracy and reduce processing speed of dysphonia detection,a novel approach is proposed in this paper.We have leveraged Linear Discriminant Analysis(LDA)to train multiple Machine Learning(ML)models for dysphonia detection.Several ML models are utilized like Support Vector Machine(SVM),Logistic Regression,and K-nearest neighbor(K-NN)to predict the voice pathologies based on features like Mel-Frequency Cepstral Coefficients(MFCC),Fundamental Frequency(F0),Shimmer(%),Jitter(%),and Harmonic to Noise Ratio(HNR).The experiments were performed using Saarbrucken Voice Data-base(SVD)and a privately collected dataset.The K-fold cross-validation approach was incorporated to increase the robustness and stability of the ML models.According to the experimental results,our proposed approach has a 70%increase in processing speed over Principal Component Analysis(PCA)and performs remarkably well with a recognition accuracy of 95.24%on the SVD dataset surpassing the previous best accuracy of 82.37%.In the case of the private dataset,our proposed method achieved an accuracy rate of 93.37%.It can be an effective non-invasive method to detect dysphonia.
基金the Third Phase College Education High Land Construction Project of Shanghai Munici-pality,the Fourth Phase Characteristic Speciality Construction Project in High Education Institutes by the Ministry of Education,No. TS11404
文摘A 35-year-old female patient with spasmodic dysphonia underwent massage and vocal training. Chinese manipulation was administered to Tiantu （CV 22） and Lianquan （CV 23）, the convergent acupoints of the conception meridian and Yin link vessel, Yamen （GV 15） and Fengfu （GV 16）, the convergent acupoints of Du meridian and Yang link vessel, as well as large intestine channel of hand Yangming Hegu （LI 4）, by gently pressing and rubbing for stimulation. In addition, throat muscle massage therapy and vocal training were performed. Results were evaluated using acoustic measurements in combination with a single statistical method. A comprehensive treatment combining vocal training and face-neck massage was shown to relieve dystonia of facial-cervical muscles in patients, as well as improve voice quality while providing a safe treatment method.
文摘Objectives: This study aims to analyze the impact of age and sex on botulinum neurotoxin (BoNT-A) dosing and outcomes in adductor spasmodic dysphonia (AdSD).Methods: A database review of all spasmodic dysphonia patients treated with BoNT from 1989 to 2018 at the Mayo Clinic in Arizona was performed. Only patients who had received ≥4 injections of BoNT-A for AdSD were included. Patients were divided into two cohorts to analyze age, with an age of first treatment cutoff of 60 years. Patients were divided into male and female cohorts to analyze sex.Results: The final analysis included 398 patients. The mean dose of BoNT-A per treatment was significantly higher in the younger cohort (4.4 vs. 3.9 units,p = 0.048). The mean maximal benefit was similar (72% vs. 70%,p = 0.48);however, the mean length of benefit was significantly shorter in younger patients (3.0 vs. 3.6 months,p < 0.01). The mean BoNT-A dose was significantly higher in the female cohort (4.2 vs. 3.6 units,p = 0.02). The mean maximal benefit was similar (69% vs. 75%,p = 0.58), as was the mean length of benefit (3.2 vs. 3.5 months,p = 0.11).Conclusions: This study suggests that age and sex influence BoNT-A dosing and outcomes in AdSD.
文摘Laryngeal tuberculosis is a rare entity. We consider the case of a woman of 62 who presented a one-year evolving chronic dysphonia chart associated with cough, febricula and general health damage. The nasofibroscopy showed a budding ulcerous lesion of the larynx a priori evoking a granulomatous lesion or cancer. The BAAR spits were strongly positive and the radiographic pictures of the thorax, typically evoked a pulmonary tuberculosis. Seeing the excellent therapeutic response to TB treatment in 4 months period, the bifocal tuberculosis diagnostic was confirmed.
文摘Laryngeal tuberculosis is a rare form of extrapulmonary tuberculosis, often complicating pulmonary tuberculosis that may be unrecognized. Its clinical presentation is nonspecific, often pointing to cancer. We report the case of a 77-year-old woman, with no reported pathological history. She also has no alcohol or tobacco intoxication, who presented with chronic dysphonia evolving for 2 months, associated with an altered general condition. The examination of the larynx by direct laryngoscopy and anatomical pathology study of the biopsies led to the diagnosis of laryngeal tuberculosis. A search for secondary sites revealed a concomitant pulmonary infection. The evolution was favorable under standard anti-tuberculosis treatment, with complete voice recovery and improved performance status. Laryngeal tuberculosis should be suspected in patients living in endemic areas and suffering from chronic dysphonia, even if they are not alcoholics or smokers.
