A genetic classification method for speaker recognition |
| |
| Affiliation: | 1. School of Energy, Power and Mechanical Engineering, North China Electric Power University, Beijing 102206, China;2. IMDEA Energy Institute, Ramon de la Sagra 3, 28935 Móstoles, Spain;3. China Datang Corporation Renewable Power Co., Limited, Beijing 100053, China;1. The University of Birmingham, School of Engineering, Edgbaston, Birmingham, B15-2TT, UK;2. The University of Mosul, Mechanical Engineering Department, Ninawa, Iraq;1. Environmental Engineering Department, Faculty of Engineering, Al-Hussein Bin Talal University, Ma''an, P.O. Box 20, Jordan;2. Petroleum and Chemical Engineering Department, College of Engineering, Sultan Qaboos University, Muscat, Oman;3. Department of Mechanical Engineering, Faculty of Engineering, Al-Hussein Bin Talal University, Ma''an, P.O. Box 20, Jordan;1. Department of Mechanical Engineering, Amirkabir University of Technology, Tehran, Iran;2. Department of Mechanical and Aeronautical Engineering, University of Pretoria, Pretoria, South Africa;1. CMT-Motores Térmicos, Universitat Politècnica de València, Camí de Vera s/n, 46022, Valencia, Spain;2. Propulsion Systems Research Lab, General Motors Global Research and Development, United States |
| |
| Abstract: | Gaussian mixture model (GMM) has been widely used for modeling speakers. In speaker identification, one major problem is how to generate a set of GMMs for identification purposes based upon the training data. Due to the hill-climbing characteristic of the maximum likelihood (ML) method, any arbitrary estimate of the initial model parameters will usually lead to a sub-optimal model in practice. To resolve this problem, this paper proposes a hybrid training method based on genetic algorithm (GA). It utilizes the global searching capability of GA and combines the effectiveness of the ML method. Experimental results based on TI46 and TIMIT showed that this hybrid GA could obtain more optimized GMMs and better results than the simple GA and the traditional ML method. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
