In order to examine the stability and patterning of speech movement sequences, movements of the lip were recorded as subjects produced a phrase at normal, fast, and slow rates. Three methods of analysis were employed. First, a new index of spatiotemporal stability was derived by summing the standard deviations computed across amplitude- and time-normalized displacement records. This index indicated that normal and fast rates of speech production result in more stable movement execution compared to slow rates. In the second analysis, the relative time of occurrence of the peak velocity of the three middle opening movements of the utterance was measured. For each of the three peaks, the preservation of relative timing was assessed by applying Genter's (1987) slope test. The results clearly indicate that the relative timing of these events does not remain constant across changes in speech rate. The relative timing of the middle opening gestures shifted, becoming later as utterance duration increased. In a third analysis, pattern recognition techniques were applied to the normalized displacement waveforms. A classification algorithm was highly successful in sorting waveforms into normal, fast, and slow rate conditions. These findings were interpreted to suggest that, within a subject, three distinct patterns or movement templates exist, one for each rate of production. Speech rate appears to be a global parameter, one that affects the entire command sequence for the utterance.
We present a study on the use of lexical stress classication to aid in the recognition of phonetically similar words. In this study, w e use a simple pattern recognition approach t o determine which syllable is lexically stressed for phonetically similar word pairs (e.g., PERfect, perFECT) extracted from continuously spoken sentences. We use a combination of two features from the acoustic correlates of lexical stress, and assume multivariate Gaussian distributions to form a Bayesian classier. The features used are normalized energy and duration of the vowel for each syllable of the word. We e v aluate several normalization methods. Two sets of sentences were designed for this study. F or the pilot experiment, the classication accuracy on words from the natural sentence set was 89.9% and on words from the control sentence set was 100%. To improve the performance, three-feature classiers, which included two normalized energy features and one normalized duration feature, were developed. The classication accuracy on words from the natural sentence set was 97.23%.
We present a probabilistic error correction technique to be used with an average magnitude dierence function (AMDF) based pitch detector. This error correction routine provides a v ery simple method to correct errors in pitch period estimation. Used in conjunction with the computationally ecient AMDF, the result is a fast and accurate pitch detector. In performance tests on the CSTR (Center for Speech Technology Research) database, probabilistic error correction reduced the gross error rate from 6.07% to 3.29%.
We present a probabilistic error correction technique to be used with an average magnitude dierence function (AMDF) based pitch detector. This error correction routine provides a v ery simple method to correct errors in pitch period estimation. Used in conjunction with the computationally ecient AMDF, the result is a fast and accurate pitch detector. In performance tests on the CSTR (Center for Speech Technology Research) database, probabilistic error correction reduced the gross error rate from 6.07% to 3.29%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.