 |
International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (MAVEBA 1999)Florence, Italy |
 |
|
International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (MAVEBA 1999)Florence, Italy |
|
Voice registers are widely affected when voice diseases appear. These diseases have to be
diagnosed and
treated during an early stage. Detection of voice diseases may be carried out by means of acoustic
analysis of voice register. Many algorithms to calculate acoustic parameters have been developed and
have been demonstrated that there is a great correlation between parameter deviations and
impairments
presence.
The effectiveness and importance of the acoustic analysis of
pathological voices have been proven by
many experimental researches which demonstrate that acoustic parameters of pathological voices are
deviated from the mean. So, voice registers can be vector quantified in order to classify
into healthy and
impaired voices.
It is well known that male and female voices have different acoustic
properties. Due to this fact, we may
think that feature gender has to be kept in mind as a new feature in order to detect voice
impairment from
the voice register alone.
The aim of this paper is to study the influence of the feature
gender to carry out classification and
automatic detection of voice diseases.
Bibliographic reference. Godino-Llorente, Juan I. / Aguilera-Navarro, Santiago / Palazuelos-Cagigas, Sira E. / Martin-Sánchez, José L. (1999): "Does it affect feature "sex" on automatic detection of impaired voices?", In MAVEBA-1999, 48-53.