Feature Adaptation Using Linear Spectro-Temporal Transform for Robust Speech Recognition

• المؤلفون الرئيسيون: Nguyen, Duc Hoang Ha, Xiao, Xiong, Chng, Eng Siong, Li, Haizhou
• مؤلفون آخرون: School of Computer Science and Engineering
• التنسيق: مقال
• اللغة: English
• منشور في: 2016
• الموضوعات: Feature adaptation; Temporal filtering
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/84664; http://hdl.handle.net/10220/41916
• المؤسسة: Nanyang Technological University

Spectral information represents short-term speech information within a frame of a few tens of milliseconds, while temporal information captures the evolution of speech statistics over consecutive frames. Motivated by the findings that human speech comprehension relies on the integrity of both the sp...