Aplicaciones clínicas del análisis acústico de la voz / Clinical applications of acoustic voice analysis

El análisis acústico de la voz es un método de evaluación vocal objetivo y no invasivo, utilizado con fines diagnósticos, terapéuticos e investigativos. Utiliza registros acústicos obtenidos directamente de la voz del paciente mediante el uso de un micrófono profesional. Existe una gran variedad de programas y métodos de graficación disponibles, que favorecen la versatilidad y especificidad del proceso. Esta revisión muestra los métodos de graficación de la voz más utilizados.

The acoustic voice analysis is an objective and non invasive vocal assessment method, used for voice diagnosis, therapy and research. It uses acoustic records obtained from the patient's voice using professional microphones. There is a variety of softwares and graphing programs available that allows process versatility and specificity. This review presents the most utilized methods of voice graphing.

Usefulness of Cepstral Peak Prominence (CPP) in Unilateral Vocal Fold Paralysis Dysphonia Evaluation

BACKGROUND AND OBJECTIVES: The purpose of this study was to compare the usefulness of Cepstral peak prominence (CPP) with parameter of Multiple Dimensional Voice Program (MDVP) in evaluating unilateral vocal fold paraylsis patients with subjective voice impairment. MATERIALS AND METHODS: From July 2014 to August 2016, 37 patients with unilateral vocal fold paralysis who had been diagnosed with unilateral vocal fold paralysis and had received two or more voice tests before and after the diagnosis were evaluated for maximum phonation time (MPT), MDVP and CPP. Respectively. Voice tests were performed with short vowel /a/ and paragraph reading. RESULTS: The CPP-a (CPP with vowel /a/) and CPP-s (CPP with paragraph reading) of the Cepstrum were statistically negatively correlated with G, R, B, and A before the voice therapy. Jitter, Shimmer, and NHR of MDVP were positively correlated with G, R, B. Jitter, Shimmer, and NHR of the MDVP were significantly correlated with the Cepstrum index. G, B, A and CPP-a and CPP-s showed a statistically significant negative correlation and a somewhat higher correlation coefficient between 0.5 and 0.78. On the other hand, in MDVP index, there was a positive correlation with G and B only with Jitter of 0.4. CONCLUSION: CPP can be an important evaluation tool in the evaluation of speech in the unilateral vocal cord paralysis when speech energy changes or the cycle is not constant during speech.

Determinación del Tamaño Óptimo de Modelos HMM-GMM para Clasificación de las Señales Bioacústicas / Determining optimal size of HMM-GMM models to classify bio-acoustic signal

Resumen Este artículo está relacionado con el análisis y la propuesta de una arquitectura HMM-GMM para clasificación de señales HS y LS, haciendo un énfasis en el tamaño del modelo. Actualmente, las enfermedades respiratorias y cardiovasculares son un problema a nivel mundial y con una alta mortandad, esto podría ser disminuido mediante un diagnóstico temprano y objetivo; las herramientas digitales y el empleo de reconocimiento de patrones ampliarían las perspectivas de aplicación. Particularmente, aquí se demuestra que los modelos HMM-GMM son eficientes para consultorios de atención primaria, así mismo los extractores de características tales como MFCC y Cuantiles mejoran la tarea de clasificación. Si bien la visualización con siluetas, dendrogramas y algoritmos tales como BIC no son concluyentes cuando se aplican GMM's, no obstante sí fue el punto de partida para dimensionar el tamaño del modelo, disminuyendo la cantidad de experimentos con distintos tamaños del mismo. Adicionalmente, se constata que la estructura de señales normales HS y LS cambian cuando hay patologías y permite la clasificación aplicando MFCC o Cuantiles. Además, se observa que con una gran cantidad de datos se podrían obtener modelos más robustos y adaptados, pero esto no es una limitante para el cálculo de los modelos.

Abstract This paper demonstrates the analysis and proposed HMM-GMM models architecture to classify heart and lung sounds (HS and LS) signals emphasizing the model size optimization. Respiratory and cardiovascular diseases continue to represent one of the major worldwide healthcare problems associated with a liigli mortality rate, wliicli can be reduced by an early and effective diagnosis; in this context, the use of digital tools utilizing signal pattern recognition allows efficient screening for abnormalities and their quantitative assessment. In particular, the HMM-GMM models demonstrated their efficiency in normal and traditionally noisy environments in light of very low intensities of these auscultation signals used as diagnostic indicators. Furthermore, applied MFCC and Quantiles feature extractors improve overall classification. While characterization with silhouettes, dendrograms and algorithms such as BIC was inconclusive when GMM was applied, however they were useful as a starting point in the determination of a size of the model as it allowed a reduction in the number of iterations considering different model size. In addition one can note that application of MFCC or Quantiles allowed differentiating the characteristics of normal HS and LS from those associated with pathological conditions. Furthermore, it was observed that a large amount of data leads to more robust and adapted models, but does not limit the calculation demand. Overall, this approach may enhance efficiency and precision of the diagnostic screening for abnormal auscultation indicators.

Analysis of Acoustic Parameters to Objectively Reflect the Change of Voice Quality before and after Surgery in Benign Vocal Fold Mucosal Disorders / 대한이비인후과학회지

BACKGROUND AND OBJECTIVES: The aim of this study was to compare between preoperative and postoperative voices by subjective auditory perceptual evaluation and objective acoustic analysis. The study also analyzed the acoustic parameters that best reflected the auditory perceptual characteristics in laryngeal microsurgery. SUBJECTS AND METHOD: The records of 49 patients who had been diagnosed as benign vocal fold mucosal diseases and had undergone laryngeal microsurgery were retrospectively analyzed. Preoperative and postoperative voices were assessed by auditory perceptual evaluation using the GRBAS Scale and acoustic analysis using Multi-Dimensional Voice Program (MDVP) and Analysis of Dysphonia in Speech and Voice (ADSV). Correlation between auditory perceptual characteristics and acoustic parameters was analyzed. RESULTS: Auditory perceptual evaluation showed that the patients' voices were improved after the operation. Several acoustic parameters of MDVP related to short-term and long-term variability showed significant improvement. Also, there were significant differences in several cepstral/spectral parameters of ADSV after operation. In the correlation analysis, the overall grade (G) of the GRBAS Scale showed highest correlation with the cepstral spectral index of dysphonia (CSID) (r=-0.700). The roughness (R) of GRBAS Scale was correlated with the smoothed amplitude perturbation quotient of long-term variability of MDVP (r=0.468), breathiness (B) with cepstral peak prominence (r=-0.703) and strain (S) with CSID (r=0.650) (p<0.01). CONCLUSION: Our results showed that the acoustic parameters were related to the long-term variability of MDVP, and the parameters of cepstrum/spectrum were useful for the objective assessment of voice quality in patients who received laryngeal microsurgery. These parameters were also useful for the quantification of voice quality and abnormality of phonation.

AN ANALYSIS OF THE MICROSTRUCTURE CHARACTERISTICS IN HUMAN KIDNEY WITH ULTRASONIC BACKSCATTERING / 药物分析学报

Objective To investigate the microstructure characteristics in human kidney with the WD cepstrum of ultrasonic backscattering. Methods By using this method, an analysis of the backscattering signals of normal and pathological human kidney in vitro was made and the mean spacing of the scatterers of biological soft tissues was estimated, then compared the means of this new approach with the means of the AR cepstrum. Results The results show that the mean spacings of the scatterers of the two different kidney tissues are noticeably different, which reveals the fact that the WD cepstrum works more effective than the AR cepstrum in showing the features of the microstructure of soft tissues. Conclusion The WD cepstrum is an effective mean to analyze the ultrasonic scattering signals and determine the features of the mean spacing of the scatterers of soft tissues. This method provides more available clinical diagnosis and improves the results of mean spacing of the scatterers of soft tissues.