A Speech Recognition System for Improving English Pronunciation of Mandarin Speakers

CS-TR-01-14

Author: Mengjie Zhang
Source: GZipped PostScript (62kb); Adobe PDF (363kb)


To improve the English pronunciation of Mandarin speakers, this paper describes an approach to the use of machine learning techniques for single English word recognition and pronunciation measure problems. After briefly presenting a simple pronunciation improvement system for user typed/selected English words, we mainly describe the design of an automatic speech recognition system based on pronounced words from Mandarin speakers.

[Up to Computer Science Technical Report Archive: Home Page]