The application of fuzzy mathematics to adaptive speech recognition

This paper discusses speaker-independent isolated word recognition using fuzzy set theory. In the case of a small training sample set, a second-level fuzzy clustering method (clustering algorithm based on a fuzzy equivalent relation combined with the fuzzy ISODATA algorithm) is presented for obtaini...

Full description

Saved in:
Bibliographic Details
Main Authors: Wang Shouyong, Xu Zhongyuan
Format: Conference Proceeding
Language:English
Subjects:
Clustering algorithms
Clustering methods
Fuzzy set theory
Fuzzy sets
Mathematics
Radar theory
Speech recognition
Symmetric matrices
Vectors
Vocabulary
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper discusses speaker-independent isolated word recognition using fuzzy set theory. In the case of a small training sample set, a second-level fuzzy clustering method (clustering algorithm based on a fuzzy equivalent relation combined with the fuzzy ISODATA algorithm) is presented for obtaining initial reference templates. In the course of recognition, the self-updating algorithm of the reference templates and weighted vector is used.< >
DOI:10.1109/ICPR.1992.202033