Towards the recovery of targets from coarticulated speech for automatic speech recognition

Abstract

An HMM-based ASR system tested on phoneme recognition of TIMIT (accuracy 74.2%) shows substitution errors covering all distinctive-feature dimensions of vowels: front/back, tense/lax, and high/low. These vowel-to-vowel errors account for about 30% of all substitution errors. These types of errors may be addressed by recovering vowel targets (and, as a by-product, coarticulation functions) during ASR. The current work models observed trajectories using a linear combination of target vectors, one vector per phoneme. A sigmoid function (with parameters for slope and position) models the evolution of the trajectory. In accordance with the Locus theory, if duration is sufficiently short and the rate of change is sufficiently slow, the targets may not be reached. Current data indicate that in clearly articulated speech, the vowel target is often reached, while in conversational speech, the vowel target is often not reached. This difference between speaking styles may explain the difficulty that current ASR systems have in recognizing conversational speech: by not always reaching the vowel target, the observed values for a phoneme have higher variance and increased overlap with other phonemes. By recovering the target values, variance of phonemes within the feature space may be reduced, thereby improving classification accuracy. [Work supported by NSF Grant IIS-0915754.]