Preliminary Thoughts on “phonologization” within an Exemplar-based Speech Processing System
نویسنده
چکیده
This paper discusses a particular problem attendant upon the hypothesis that phonological patterns emerge directly from considerations of phonetic functionality: the problem is that phonological patterns frequently display stability across tokens and contexts, where direct phonetic conditioning would predict variation. I suggest that this stabilization might emerge from an exemplar-based speech processing system, which, in essence, enforces the notion of analogical pattern extension.
منابع مشابه
Computing phonological generalization over real speech exemplars
Though it has attracted growing attention from phonologists and phoneticians, Exemplar Theory (e.g. Bybee 2001) has hitherto lacked an explicit production model that can apply to speech signals. An adequate model must be able to generalize; but this presents the problem of how to generate an output that generalizes over a collection of unique, variable-length signals. Rather than resorting to a...
متن کاملPreliminary Thoughts on “phonologisation” within an Exemplar-based Speech Processing System
This paper discusses a particular problem attendant upon the hypothesis that phonological patterns emerge directly from considerations of phonetic functionality, and tentatively explores a possible solution. The problem is that many sound patterns display a certain stability, across tokens and contexts, which is difficult to account for in terms of purely phonetic considerations; moreover, thes...
متن کاملImproving Exemplar-based Image Completion methods using Selecting the Optimal Patch
Image completion is one of the subjects in image and video processing which deals with restoration of and filling in damaged regions of images using correct regions. Exemplar-based image completion methods give more pleasant results than pixel-based approaches. In this paper, a new algorithm is proposed to find the most suitable patch in order to fill in the damaged parts. This patch selection ...
متن کاملAn analysis of sparseness and regularization in exemplar-based methods for speech classification
The use of exemplar-based techniques for both speech classification and recognition tasks has become increasingly popular in recent years. However, the notion of why sparseness is important for exemplar-based speech processing has been relatively unexplored. In addition, little analysis has been done in speech processing on the appropriateness of different types of sparsity regularization const...
متن کاملReducing over-smoothness in HMM-based speech synthesis using exemplar-based voice conversion
Speech synthesis has been applied in many kinds of practical applications. Currently, state-of-the-art speech synthesis uses statistical methods based on hidden Markov model (HMM). Speech synthesized by statistical methods can be considered over-smooth caused by the averaging in statistical processing. In the literature, there have been many studies attempting to solve over-smoothness in speech...
متن کامل