Phonetic word verification

Abstract:  Abstract Analytic phonetic processing in speech recognition usually results in segmentation and labelling and is followed by lexical matching based on sequences of phonetic labels. Segmentation and labelling are impaired by coarticulation effects and imperfect syllabication. Matching is complicated by missed, extraneous, and mislabelled segments. This paper describes an approach to phonetic-based analysis which minimizes the difficulties just mentioned. Phonetic word verification permits an evaluation of phonetic similarity of incoming speech with prestored lexical entries. The comparison is based on acoustic parameter values (rather than segment labels). This allows the evaluation to be phone-specific and context-dependent, thus accommodating naturally for coarticulation effects. It also permits scores for each phone to be gradient at the acoustic level, avoiding the difficulties of missed and extraneous phonetic segments. Because the approach is predictive (top-down), syllable-internal phonetic analysis can be performed where syllabication is imperfect. Finally, the approach naturally accommodates powerful transitional and durational constraints.