10.1371/journal.pone.0158520.g008 Md. Atiqul Islam Md. Atiqul Islam Wissam A. Jassim Wissam A. Jassim Ng Siew Cheok Ng Siew Cheok Muhammad Shamsul Arefeen Zilany Muhammad Shamsul Arefeen Zilany Text-dependent speaker identification performance of the proposed and existing methods using the UM database. Public Library of Science 2016 2- D neurograms Gamma-tone frequency cepstral coefficients Mel-frequency cepstral coefficients Auditory Periphery Speaker identification speaker identification system speech processing applications Robust Speaker Identification System speaker identification methods Gaussian mixture model-universal background model classification technique performance response speech signals text-dependent speaker databases 2016-07-08 16:59:16 Figure https://plos.figshare.com/articles/figure/Text-dependent_speaker_identification_performance_of_the_proposed_and_existing_methods_using_the_UM_database_/3908937 <p>Two cases of frequency bands were considered: left panels show the performance of the SI systems using features from the narrowband frequencies (<1 kHz), and the right panels represent performances for the wideband frequencies. Results are shown as a function of SNR with three different types of noise (A: white Gaussian noise, B: pink noise, and C: street noise). Speech samples from 39 speakers were used for evaluation and comparison of the performance of different methods.</p>