Year: 1987
Type: conference-paper
Abstract: In this paper we present results of our analysis of isolated utterances of Hindi (an Indian language) stop consonants and propese a recognition method for the same.Standard techniques which use fixed strategies for isola ted ward speech recogni tion fail to work for this confusable vocabulary set, since they do not focus on the primarily distinguishing parts of the ut terance which contain linguistically important information.The duration of the consonantal part being small, their features are submerged by the dominant vowel part of the utterance.The studies on consonants wi th different manners of production suggest that processing may be confined to different regions to enhance the recognition performance.An improved performance is obtained by using a hierarchical approach for recogni tion along wi th the use of appropriate knowledge for processing different regions of an utterance.
Authors: R. Sundar, S. Raman, B. Yegnanarayana
Institution: Indian Institute of Technology Madras
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W89496786
