Title :
Speaker-independent word recognition using sex-dependent clustering
Author :
Diller, Timothy C. ; Siebenand, J. ; Siebenand, John F.
Author_Institution :
Sperry Univac, St. Paul, Minnesota
Abstract :
In the absence of perfect speaker normalization techniques, speaker-independent recognition using spectral pattern matching is improved significantly by using multiple lexical patterns for each word
Keywords :
Aggregates; Clustering algorithms; Costs; Delay; Oral communication; Pattern matching; Pattern recognition; Performance analysis; Speech analysis; Testing;
Conference_Titel :
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '81.
DOI :
10.1109/ICASSP.1981.1171137
