Automatic gender identification
Alireza Afshordi Dibazar, Jim‐Shih Liaw, Theodore W. Berger · The Journal of the Acoustical Society of America · 2001
In this paper, a new automatic gender identification method is proposed as a part of an Automatic Speaker Recognition (ASR) system. The short time raw speech signal (180–450 ms) was filtered by the nine-order Butterworth low pass filter and decomposed to different frequency bands by the wavelet filter bank analyzer. The energy of the 120 sub-bands was used as a feature vector and applied to a standard classifier. This classifier was trained by the gradient descent method with 1594 utterances spoken by various males and females. The system was tested with different 2542 utterances giving 99.2% correct classification rate. The high performance and simplicity of implementation are the characteristics of this system in comparison to the other methods. [Work supported by DARPA.]