On Acoustic Versus Abstract Units of Representation
Abstract
Postulating the existence of abstract representational units appears useful in speech research. For instance, such units can be used to partition a large lexicon for word-candidate hypothesization [8] [4], or to specify phonetic deletion and modification sites. However, since such linguistic representations have at best an indirect realization in the physical signal. it has proven difficult to build classfiers for these units. Therefore, recognition systems generally use less abstract units such as spectral templates. We argue that the difficulty of classifying abstract units docs not preclude using these units in recognition. In particular, constraint-based systems provide a mechanism for exploiting abstract linguistic knowledge m the acoustic level.
Downloads
Published
How to Cite
Issue
Section
License
Copyright on articles is held by the author(s). The corresponding author has the right to grant on behalf of all authors and does grant on behalf of all authors, a worldwide exclusive licence (or non-exclusive license for government employees) to the Publishers and its licensees in perpetuity, in all forms, formats and media (whether known now or created in the future)
i) to publish, reproduce, distribute, display and store the Contribution;
ii) to translate the Contribution into other languages, create adaptations, reprints, include within collections and create summaries, extracts and/or, abstracts of the Contribution;
iii) to exploit all subsidiary rights in the Contribution,
iv) to provide the inclusion of electronic links from the Contribution to third party material where-ever it may be located;
v) to licence any third party to do any or all of the above.
