A segmental k-means training procedure for connected word recognition based on whole word reference patterns.

Algorithms for recognizing strings of connected words from whole word patterns (either templates or statistical models) have advanced to the point of high efficiency and accuracy. Although the computation rate of these connected word recognition algorithms remains high, advances in VLSI hardware make even the most ambitious connected word recognition tasks practical with todays technology. The greatest impediment to the successful utilization of connected word recognizers is the difficulty in extracting reliable, robust whole word reference patterns. In the past, connected word recognizers have relied on either isolated word reference patterns (which are trivially obtained), or reference patterns derived from limited context strings of words (e.g. the middle digit from strings of 3 digits).