Modification of Earley’s Algorithm for Speech Recognition
This paper describes an adaptation of Earley’s algorithm for the recognition of spoken sentences. Earley’s algorithm is one of the most efficient parsing algorithms for written sentences. The modifications and extensions of Earley’s algorithm required by the variability and ambiguity of the speech signal concern the scoring of word and sentence hypotheses and the application of a beam search or pruning technique.
Unable to display preview. Download preview PDF.
- /Ear 70/.
- /Fu 82/.
- /Gra 76/.S. L. Graham, M. A. Harrison, W. L. Ruzzo: ‘On-Line Context- Free Language Recognition in less than Cubic Time’, Proc. of the 8. Annual ACM Symposium on Theory of Computing, 1976.Google Scholar
- /Lyo 74/.
- /Nak 87/.S. Nakagawa, ‘Spoken Sentence Recognition by Time-Synchronous Parsing Algorithm of Context-Free Grammar’, Proc. of the Int. Conf. on Acoustics, Speech, and Signal Processing, Dallas, TX, April 1987, pp. 20.9.1–4.Google Scholar
- /Ney 82/.H. Ney, ‘Dynamic Programming as a Technique for Pattern Recognition’, Proc. 6th Int. Conf. on Pattern Recognition, Muenchen, S. 1119–1125, 1982.Google Scholar
- /Ney 87/.H. Ney, ‘Dynamic Programming Speech Recognition using a Context-Free Grammar’, Proc. of the Int. Conf. on Acoustics, Speech, and Signal Processing, Dallas, TX, 1987, pp. 3.2.1–4.Google Scholar