Phrase Errors Research Articles

Some experiments with a linguistic processor for continuous speech recognition

The linguistic processor of a system for the recognition of fluently spoken Japanese is described. Input to the processor is a phoneme lattice in which scores are given for each of 27 phonemes for each segment. Phrases composed of words from a 112 word vocabulary are recognized by an error correcting parser which tolerates both classification and segmentation errors in the phoneme lattice by means of a Substitution-Insertion-Deletion Mechanism (SID). Some phrase errors are corrected at the sentence level by means of a Cartesian Product Sorting Algorithm. The processor has been tested on a total of 80 sentences from four male speakers. The sentences comprised 496 phrases with an average of 25 phonemes per phrase. The phoneme lattices had a 70 percent accuracy on phonemes with roughly equal numbers of segmentation and classification errors. Under these conditions 77 percent phrase accuracy was observed.

Some experiments with a linguistic processor for continuous speech recognition

The linguistic processor of a system for the recognition of fluently spoken Japanese is described. Input to the processor is a phoneme lattice [R. Nakatsu and M. Kohda, Rev. ECL 26, 1505–1520 (1978)] in which scores are given for each of 27 phonemes for each segment. Phrases composed of words from a 112-word vocabulary are recognized by an error correcting parser which tolerates both classification and segmentation errors in the phoneme lattice by means of a Substitution-Insertion-Deletion Mechanism (SID) [L. R. Bahl and F. Jelinek, IEEE Trans. Inform. Theory IT-21, 401–411 (1975)]. Some phrase errors are corrected at the entrance level by means of a Cartesian Product Sorting Algorithm. [A. V. Aho et al., Proc. 14th CISS (1980)]. The processor has been tested on a total of 80 sentences from four male speakers. The sentences comprised 496 phrases with an average of 25 phonemes per phrase. The phoneme lattices had a 70% accuracy on phonemes with roughly equal numbers of segmentation and classification errors. Under these conditions 77% phrase accuracy was observed.