Hostname: page-component-745bb68f8f-5r2nc Total loading time: 0 Render date: 2025-02-06T22:01:51.833Z Has data issue: false hasContentIssue false
  • English
  • Français

Recognition of continuous speech requires top-down processing

Published online by Cambridge University Press:  10 October 2000

Kenneth N. Stevens
Kenneth N. Stevens
Affiliation:
Department of Electrical Engineering and Computer Science and Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, MA 02139 stevens@speech.mit.edu
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

The proposition that feedback is never necessary in speech recognition is examined for utterances consisting of sequences of words. In running speech the features near word boundaries are often modified according to language-dependent rules. Application of these rules during word recognition requires top-down processing. Because isolated words are not usually modified by rules, their recognition could be achieved by bottom-up processing only.

Type
Brief Report
Information
Behavioral and Brain Sciences , Volume 23 , Issue 3 , June 2000 , pp. 348
Copyright
© 2000 Cambridge University Press