Optimizing model training for speech recognition

• المؤلف الرئيسي: Chak, Hui Ping
• مؤلفون آخرون: Lee Bu Sung
• التنسيق: Final Year Project
• اللغة: English
• منشور في: 2010
• الموضوعات: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
• الوصول للمادة أونلاين: http://hdl.handle.net/10356/40059

Modern speech recognition systems are generally based on statistical models which output a sequence of symbols or quantities. These models can be trained automatically and are simple and computationally feasible to use. To reduce long computational time, the model training can be distributed to many...