Research Journal of Biological Sciences
ISSN: Online 1993-6087ISSN: Print 1815-8846
Abstract
Gender and age evaluation for speech usages is very significant. One among the uses is that it can enhance person-machine communication, e.g., the announcements can be focused founded on the gender and the age of the individual on the receiver. It can assist in recognizing illegal case suspects or reduce the amount of suspects. In this essay, the estimation of gender and age was carried out using an education algorithm, including contrasting the behavior of the mechanism. Moreover, the dataset incorporated real-life experiences, such that the mechanism is compliant to real world uses. Shifted Delta Cepstral (SDC) is mined by means of Mel Frequency Cepstral Coefficients (MFCC) and the benefit of SDC is that it is further strong under loud information. From the trials, an amalgamation of MFCC and pitch was employed to get even superior acknowledgment rates.
How to cite this article:
Romany F. Mansour and Abdul Samad A. Marghilani. Estimating Age and Gender for Speaker through Distorted Voices Based on Fused Model.
DOI: https://doi.org/10.36478/rjbsci.2016.67.74
URL: https://www.makhillpublications.co/view-article/1815-8846/rjbsci.2016.67.74