29 October 1993 Explicit noise hypotheses in speech recognition
Author Affiliations +
Abstract
Noise is typically present in the input signal for perception problems. Noise arises in speech recognition due to both background sounds, and unintentional derivations from the intended utterance on the part of the speaker. The task of speech recognition is to correctly identify the words (or meaning) carried by the speech signal. Thus the speech recognizer must be able to successfully handle noise. We describe here a method of explicitly identifying and labeling noise elements in a speech signal. NOISE hypotheses are generated, and considered for acceptance, as part of an abductive inference strategy for speech processing. An abductive problem solver is able to treat noise within a unified inferential framework, treating noise hypotheses similarly to other hypotheses, weighing the explanatory alternatives in a context-sensitive manner, and with no need to resort to indirect methods to achieve noise tolerance.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Richard K. Fox, Richard K. Fox, John R. Josephson, John R. Josephson, } "Explicit noise hypotheses in speech recognition", Proc. SPIE 2032, Neural and Stochastic Methods in Image and Signal Processing II, (29 October 1993); doi: 10.1117/12.162043; https://doi.org/10.1117/12.162043
PROCEEDINGS
11 PAGES


SHARE
Back to Top