期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2015
卷号：6
期号：2
页码：1643-1647
出版社：TechScience Publications
摘要：Deep Neural Network Hidden Markov Models, or DNN-HMMs, are recently very promising acoustic models achieving good speech recognition results over Gaussian mixture model based HMMs (GMM-HMMs).The accurate methods to profile different characteristics of a speaker from recorded voice patterns, which facilitate to identify him/her or at least narrow down the number of suspects. Here they propose a new gender and age group recognition approach based on Hidden Markov Model (HMM). First, an acoustic model is trained for all speakers in a training database including male and female speakers of different age. Finally, Supervised HMM is applied to detect the gender and age group of unseen test speakers. Designing a new HMM-based approach for speaker, gender and age estimation, which improves the accuracy of the state-of-the-art speaker age estimation methods with statistical significance. Analyzing the effect of major factors influencing the automatic gender and age estimation systems.
