Title :
A comparative study of two search strategies for connected word recognition: dynamic programming and heuristic search
Author_Institution :
Philips Res. Lab., Aachen, Germany
fDate :
5/1/1992 12:00:00 AM
Abstract :
A most successful approach to recognizing continuous speech is to model the recognition problem as one of finding an optimal path through a finite state network. A comparison of two search strategies for finding the optimal path, dynamic programming and heuristic search, is presented. The comparison is based on theoretical considerations and experimental tests on a digit string task
Keywords :
dynamic programming; graph theory; heuristic programming; search problems; speech recognition; connected word recognition; continuous speech; dynamic programming; finite state network; heuristic search; optimal path; Artificial intelligence; Automata; Costs; Dynamic programming; Maximum likelihood decoding; Pattern recognition; Signal processing; Signal processing algorithms; Speech recognition; Testing;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
