1. INTRODUCTION
Automatic word boundary detection, a topic that has been investigated for several decades, is still an active area of research due to its impact in diverse applications and, the challenging nature of the problem. Initial applications have included detection of the exact word boundaries to assess speech recognition performance and to make recognizers faster. Other, applications of word boundary detection include detecting regions of out of vocabulary (OOV) words and detecting exact boundaries for unknown named entities in speech. Word boundary information can also be helpful for rich transcription of speech such as in detecting emphatic (prominent) words [1].