Utilization of Multiple Units in Human And Machine Recognition of Continuous Speech---- Perceptual Evidence And A Proposal For An Asr System
Abstract
The ultimate goal of automatic speech recognition (ASR) is obviously to replicate the human capability of speech processing by machine. Research of ASR will thus profit very much from investigations into the human processes of speech perception/comprehension. Few studies, however, seem to have been made along this line. The present paper summarizes a series of psycholinguistic experiments conducted to elucidate certain aspects of human speech perception, especially in relation to the units of processing. On the bases of these experiments, we propose a new system for continuous speech recognition utilizing multiple units.
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.
