A comparative study of two search strategies for connected word recognition: dynamic programming and heuristic search
- 1 May 1992
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 14 (5) , 586-595
- https://doi.org/10.1109/34.134063
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
This publication has 6 references indexed in Scilit:
- A data-driven organization of the dynamic programming beam search for continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A 10000-word continuous-speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Structural methods in automatic speech recognitionProceedings of the IEEE, 1985
- The use of a one-stage dynamic programming algorithm for connected word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984
- An adaptive, ordered, graph search technique for dynamic time warping for isolated word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1982
- Design of a linguistic statistical decoder for the recognition of continuous speechIEEE Transactions on Information Theory, 1975