VoxCeleb1: Speaker Age-Group Classification using Probabilistic Neural Network

The international arab journal of information technology

article

Ameer Badr¹  Alia Abdul-Hassan¹ 

[1] Department of Computer Science, University of Technology

关键词: Speaker age-group recognition;    features fusion;    SSC;    F0;    jitter and shimmer;   

DOI  :  10.34028/iajit/19/6/2

学科分类：计算机科学（综合）

来源: Zarqa University

【 摘 要 】

The human voice speech includes essentially paralinguistic information used in many applications forvoice recognition. Classifying speakers according to their age-group has been considered as a valuable tool in variousapplications, as issuing different levels of permission for different age-groups. In the presented research, an automatic systemto classify speaker age-group without depending on the text is proposed. The Fundamental Frequency (F0), Jitter, Shimmer, andSpectral Sub-Band Centroids (SSCs) are used as a feature, while the Probabilistic Neural Network (PNN) is utilized as aclassifier for the purpose of classifying the speaker utterances into eight age-groups. Experiments are carried out on VoxCeleb1dataset to demonstrate the proposed system's performance, which is considered as the first effort of its kind. The suggestedsystem has an overall accuracy of roughly 90.25%, and the findings reveal that it is clearly superior to a variety of base- classifiers in terms of overall accuracy.

【 授权许可】

Unknown