Kwon, Soonil Narayanan, Shrikanth 2024-01-21T01:35:03Z 2024-01-21T01:35:03Z 2021-08-31 2007-01-01 0167-8655 https://pubs.kist.re.kr/handle/201004/134752 A new method for speaker identification that selectively uses feature vectors for robust decision-making is described. Experimental results, with short speech segments ranging from 0.25 to 2 s, showed that our method consistently outperforms other approaches yielding relative improvements of 20-51% and 15-30% over baseline GMM and the LDA-GMM systems, respectively. (c) 2006 Elsevier B.V. All rights reserved. English ELSEVIER Robust speaker identification based on selective use of feature vectors Article 10.1016/j.patrec.2006.06.009 1 PATTERN RECOGNITION LETTERS, v.28, no.1, pp.85 - 89 PATTERN RECOGNITION LETTERS 28 1 85 89 scie scopus 000242552900010 2-s2.0-33750470047 Computer Science, Artificial Intelligence Computer Science Article short-segment speaker identification speaker model construction feature vector selection linear discriminant analysis (LDA)