caa a22 4500 477034500 CHVBK 20180405111301.0 cr unu---uuuuu 170330e19960601xx s 000 0 eng 10.1007/BF00571681 doi (NATIONALLICENCE)springer-10.1007/BF00571681 Text-dependent speaker identification based on input/output HMMs: An empirical study [Elektronische Daten] [Ke Chen, Dahong Xie, Huisheng Chi] In this paper, we explore theInput/Output HMM (IOHMM) architecture for a substantial problem, that of text-dependent speaker identification. For subnetworks modeled with generalized linear models, we extend the IRLS algorithm to the M-step of the corresponding EM algorithm. Experimental results show that the improved EM algorithm yields significantly faster training than the original one. In comparison with the multilayer perceptron, the dynamic programming technique and hidden Markov models, we empirically demonstrate that the IOHMM architecture is a promising way to text-dependent speaker identification. Kluwer Academic Publishers, 1996 speaker identification nationallicence input/output HMM nationallicence EM algorithm nationallicence temporal processing nationallicence Chen Ke National Laboratory of Machine Perception, Peking University, 100871, Beijing, China aut Xie Dahong National Laboratory of Machine Perception, Peking University, 100871, Beijing, China aut Chi Huisheng National Laboratory of Machine Perception, Peking University, 100871, Beijing, China aut Neural Processing Letters Kluwer Academic Publishers 3/2(1996-06-01), 81-89 1370-4621 3:2<81 1996 3 11063 https://doi.org/10.1007/BF00571681 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF00571681 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Chen Ke National Laboratory of Machine Perception, Peking University, 100871, Beijing, China aut NATIONALLICENCE 700 1- Xie Dahong National Laboratory of Machine Perception, Peking University, 100871, Beijing, China aut NATIONALLICENCE 700 1- Chi Huisheng National Laboratory of Machine Perception, Peking University, 100871, Beijing, China aut NATIONALLICENCE 773 0- Neural Processing Letters Kluwer Academic Publishers 3/2(1996-06-01), 81-89 1370-4621 3:2<81 1996 3 11063 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer