Generation of robust phonetic set and decision tree for Mandarin using chi-square testing

A phonetic representation of a language is used to describe the corresponding pronunciation and synthesize the acoustic model of any vocabulary. A phonetic representation with smaller phonetic units such as SAMPA-C for Mandarin Chinese and decision trees for parameter sharing are broadly applied to deal with the problem of large numbers of recognition units. However, the confusable phonetic representation in SAMPA-C generally degrades the recognition performance. In this paper, a statistical method based on chi-square testing is used to investigate the phonetic unit characteristics that are confusing and develop a more reliable phonetic set, named modified SAMPA-C. A corresponding question set for the modified SAMPA-C and a two-level splitting criterion are also proposed to effectively and efficiently construct the decision trees. Experiments using continuous Mandarin telephone speech recognition were conducted. Experimental results show that an encouraging improvement in recognition performance can be obtained. The proposed approaches represent a good compromise between the demands of accurate acoustic modeling and the limitations imposed by insufficient training data.