The authors describe two efficient enhancements for speaker-independent connected-spoken-word spotting. The first enhancement, LESS COST, uses phoneme concatenation to reduce the cost of computing the pairwise local distances between reference and input pattern points. The second enhancement, coarse DP refinement, reduces the cost of dynamic time warping for only a small error rate penalty. A preliminary experiment that confirmed these techniques is described.
|Number of pages
|ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
|Published - 1986
ASJC Scopus subject areas
- Signal Processing
- Electrical and Electronic Engineering