Search

An automatic categorization of the speakers according to their sex improves the performance of an automatic detector of voice pathologies. This is grounded on findings demonstrating perceptual, acoustical and anatomical differences in males’ and females’ voices. In particular, this paper follows two objectives: 1) to design a system which automatically discriminates the sex of a speaker when using normophonic and pathological speech, 2) to study the influence that this sex detector has on the accuracy of a further voice pathology detector. The parameterization of the automatic sex detector relies on MFCC applied to speech; and MFCC applied to glottal waveforms plus parameters modeling the vocal tract. The glottal waveforms are extracted from speech via iterative lattice inverse filters. Regarding the pathology detector, a MFCC parameterization is applied to speech signals. Classification, in both sex and pathology detectors, is carried out using state of the art techniques based on universal background models. Experiments are performed in the Saarbrücken database, employing the sustained phonation of vowel /a/. Results indicate that the sex of the speaker may be discriminated automatically using normophonic and pathological speech, obtaining accuracy up to 95%. Moreover, including the a-priori information about the sex of the speaker produces an absolute performance improvement in EER of about 2% on pathology detection tasks. RESUMEN. Una categorización automática de los hablantes de acuerdo con su sexo mejora el rendimiento de un detector automático de patologías de voz. Esto se fundamenta en hallazgos que demuestran diferencias perceptuales, acústicas y anatómicas en voces masculinas y femeninas. En particular, este trabajo persigue dos objetivos: 1) diseñar un sistema que discrimine automáticamente el sexo de hablantes utilizando habla normofónica y patológica, 2) estudiar la influencia que este detector de sexo tiene sobre el acierto de un posterior detector de patologías de voz. La parametrización del detector automático de sexo se basa en MFCC aplicados sobre señales de voz; y MFCC aplicados a formas de onda glotal junto a parámetros que modelan el tracto vocal. Las formas de onda glotal se extraen de la voz a través de un filtrado inverso iterativo en celosía. En cuanto al detector de patologías, una parametrización MFCC se aplica a señales de voz. La clasificación, tanto en los detectores de sexo como de patología, se lleva a cabo con técnicas del estado del arte basadas en modelos de base universal. Experimentos son realizados sobre la base de datos Saarbrücken empleando la fonación sostenida de la vocal /a/. Los resultados indican que el sexo del hablante puede ser discriminado automáticamente utilizando habla normofónica y patológica, obteniendo una precisión de hasta un 95%. Por otra parte, al incluir información a priori sobre el sexo del hablante se produce una mejora de alrededor del 2% de rendimiento absoluto en EER, en tareas de detección de patología.

Systems that automatically detect voice pathologies are usually trained with recordings belonging to population of all ages. However such an approach might be inadequate because of the acoustic variations in the voice caused by the natural aging process. In top of that, elder voices present some perturbations in quality similar to those related to voice disorders, which make the detection of pathologies more troublesome. With this in mind, the study of methodologies which automatically incorporate information about speakers’ age, aiming at a simplification in the detection of voice disorders is of interest. In this respect, the present paper introduces an age detector trained with normal and pathological voice, constituting a first step towards the study of age-dependent pathology detectors. The proposed system employs sustained vowels of the Saarbrucken database from which two age groups are examinated: adults and elders. Mel frequency cepstral coefficients for characterization, and Gaussian mixture models for classification are utilized. In addition, fusion of vowels at score level is considered to improve detection performance. Results suggest that age might be effectively recognized using normal and pathological voices when using sustained vowels as acoustical material, opening up possibilities for the design of automatic age-dependent voice pathology detection systems.

Estimates of the value-of-life have relied heavily on labor market studies of compensating wages. These studies typically involve least squares regressions using cross-sectional data. The dependent variable is log of wages and the independent variables are years of schooling, age, age squared, and so on. The key independent variable is a measure of the death rate on the job. Most studies have found a strong partial correlation between log-wages and the death rate and most authors have interpreted this correlation as evidence that the labor market is generating compensating wages for hazardous work. Some economists have used the coefficient from this correlation to estimate a statistical value-of-life. I n t h i s p a p e r , w e f i r s t m e n t i o n s o m e e v i d e n c e t h a t c o r r e l a t i o n s b e t w e e n wages and death rates are fragile. We then discuss a study (Leigh, 1991) that did not find strong wage-death rate correlations using unique data on occupations. Third, we argue that the correlations found in prior literature are more likely the result of historical inter-industry differentials than the result of a compensating wage paid for dangerous work. The fourth part of the paper offers some explanations for why compensating wages fail to appear for the lion's share of jobs in the labor market but do appear for the handful of jobs that are undeniably hazardous. We offer a comment on the academic importance of forensic economists in the fifth part of the paper. A summary concludes our paper. I. Fragile Estimates Ted Miller (1990) reviewed 27 studies and Kip Viscusi (1992) reviewed 30 studies on compensating wages for job-related deaths, most of which found positive and statistically significant estimated coefficients on death rate variables. Virtually all of Miller’s studies were on Viscusi’s list. However, in several of these studies, the estimated coefficients for the death rate variables were either statistically insignificant or significant but close to zero (Dickens, 1984; Dorsey, 1983; Leigh and Folsom, 1984; Leigh, 1987; Moore and Viscusi, 1988; Thaler and Rosen, 1975; Viscusi, 1979; Kniesner and Leeth, 1991). More importantly, these two reviews are incomplete since they do not include at least two prior studies or three subsequent studies that failed to find statisti

The efficient use of spectrum has become an active research area, due to its scarcity and underutilization. In a spectrum sharing scenario as Cognitive Radio (CR), the vacancy of licensed frequency bands could be detected by a secondary user through spectrum sensing techniques. Usually, this sensing approaches are performed with a priori knowledge of the channel features. In the present work, a blind spectrum sensing approach based on Independent Component Analysis and Singular Spectrum Analysis is proposed. The approach is tested and compared with other outcomes. Results show that the proposed scheme is capable of detect most of the sources with low time consumption, which is a remarkable aspect for online applications with demanding time issues.