An efficient speech recognition system in adverse conditions using the nonparametric regression |
| |
| Authors: | Abderrahmane Amrouche Mohamed Debyeche Abdelmalik Taleb-Ahmed Jean Michel Rouvaen Mustapha CE Yagoub |
| |
| Affiliation: | 1. Faculty of Electronics and Computer Sciences, USTHB, P.O. Box 32, Bab Ezzouar, Algiers 16 111, Algeria;2. LAMIH (UMR CNRS 8530), Valenciennes University, P.O. Box 304, Le Mont Houy 59 313, France;3. OAE-IEMN (UMR CNRS 8520), Valenciennes University, P.O. Box 304, Le Mont Houy 59 313, France;4. SITE, University of Ottawa, 800 King Edward, Ottawa, ON, Canada K1N 6N5;1. Instituto Politécnico Nacional, ESIME-Culhuacan, Santa Ana 1000, 04430 D.F., Mexico;2. Universidad Autónoma Metropolitana Iztapalapa, San Rafael Atlixco 186, 09340 D.F., Mexico;1. Institute of Modern Optics, Department of Physics, Harbin Institute of Technology, Harbin 150001, China;2. Key Laboratory of Micro-optics and Photonic Technology of Heilongjiang Province, Department of Physics, Harbin Institute of Technology, Harbin 150001, China;1. ITER-India, Institute for Plasma Research, Bhat, Gandhinagar 382428, India;2. Institute for Plasma Research, Bhat, Gandhinagar 382428, India;1. School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, People’s Republic of China;2. The Key Laboratory for Special Fiber and Fiber Sensor of Hebei Province, Yanshan University, Qinhuangdao 066004, People’s Republic of China;1. Laboratoire Signal et Communication, Ecole Nationale Polytechnique, 10, Av. Hassen Badi, P.O. Box 182, 16200 El-Harrach, Algeria;2. Signal Processing Group, Institute of Telecommunications, Technische Universität Darmstadt, Merckstr. 25, 64283 Darmstadt, Germany |
| |
| Abstract: | General Regression Neural Networks (GRNN) have been applied to phoneme identification and isolated word recognition in clean speech. In this paper, the authors extended this approach to Arabic spoken word recognition in adverse conditions. In fact, noise robustness is one of the most challenging problems in Automatic Speech Recognition (ASR) and most of the existing recognition methods, which have shown to be highly efficient under noise-free conditions, fail drastically in noisy environments. The proposed system was tested for Arabic digit recognition at different Signal-to-Noise Ratio (SNR) levels and under four noisy conditions: multispeakers babble background, car production hall (factory), military vehicle (leopard tank) and fighter jet cockpit (buccaneer) issued from NOISEX-92 database. The proposed scheme was successfully compared to the similar recognizers based on the Multilayer Perceptrons (MLP), the Elman Recurrent Neural Network (RNN) and the discrete Hidden Markov Model (HMM). The experimental results showed that the use of nonparametric regression with an appropriate smoothing factor (spread) improved the generalization power of the neural network and the global performance of the speech recognizer in noisy environments. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
