Syllable Network for Phonemic Decoding of Speech
Abstract
The decoding of speech into phonemes for large vocabulary speech recognition is made more reliable by restricting phoneme sequences to those which compose valid syllables. To apply this restriction when decoding a sequence of phonemes, we use a syllable network representing the valid syllables in Webster’s 7th Collegiate dictionary. Since major allophonic variants of a phoneme are determined by the phoneme's position within the syllable (e.g., prevocalic vs. postvocalic /r /), the syllable network can be used to represent allophonic variation by employing distinct allophone models of a phoneme in different positions within the network. A preliminary experiment using the syllable network in large vocabulary recognition to select appropriate Markov models for allophones shows promising results.
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.
