Discriminative feature extraction for speech recognition using continuous output codes

• المؤلفون الرئيسيون: Dehzangi, Omid, Ma, Bin, Chng, Eng Siong, Li, Haizhou
• مؤلفون آخرون: School of Computer Engineering
• التنسيق: مقال
• اللغة: English
• منشور في: 2013
• الموضوعات: DRNTU::Engineering::Computer science and engineering
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/105600; http://hdl.handle.net/10220/17340
• المؤسسة: Nanyang Technological University

Feature transformation techniques have been widely investigated to reduce feature redundancy and to introduce additional discriminative information with the aim to improve the performance of automatic speech recognition (ASR). In this paper, we propose a novel method to obtain discriminative feature...