Improvements on hierarchical language identification based on automatic language clustering

Hierarchical language identification (HLID) is a novel framework for combining multiple features or primary systems in language identification. In this paper, several key components of HLID are investigated and developed. Crossing likelihood ratio and Kullback-Leibler distance measures are introduced for faster and more accurate clustering. A novel feature selection scheme based on fusion is proposed to incorporate multiple features at each classification level. Further, a phone recognizer followed by language model (PRLM) system is introduced in addition to the other three acoustic systems to provide phonetic information. These proposed techniques improve the performance of HLID system to an EER of 6.3% on the NIST LRE 2003 30s task.