Lookup NU author(s): Musab Al-Kaltakchi,
Dr Wai Lok Woo,
Professor Satnam Dlay,
Professor Jonathon Chambers
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
© 2017, The Author(s). In this study, a speaker identification system is considered consisting of a feature extraction stage which utilizes both power normalized cepstral coefficients (PNCCs) and Mel frequency cepstral coefficients (MFCC). Normalization is applied by employing cepstral mean and variance normalization (CMVN) and feature warping (FW), together with acoustic modeling using a Gaussian mixture model-universal background model (GMM-UBM). The main contributions are comprehensive evaluations of the effect of both additive white Gaussian noise (AWGN) and non-stationary noise (NSN) (with and without a G.712 type handset) upon identification performance. In particular, three NSN types with varying signal to noise ratios (SNRs) were tested corresponding to street traffic, a bus interior, and a crowded talking environment. The performance evaluation also considered the effect of late fusion techniques based on score fusion, namely, mean, maximum, and linear weighted sum fusion. The databases employed were TIMIT, SITW, and NIST 2008; and 120 speakers were selected from each database to yield 3600 speech utterances. As recommendations from the study, mean fusion is found to yield overall best performance in terms of speaker identification accuracy (SIA) with noisy speech, whereas linear weighted sum fusion is overall best for original database recordings.
Author(s): Al-Kaltakchi MTS, Woo WL, Dlay S, Chambers JA
Publication type: Article
Publication status: Published
Journal: EURASIP Journal on Advances in Signal Processing
Online publication date: 02/12/2017
Acceptance date: 13/11/2017
ISSN (print): 1687-6172
ISSN (electronic): 1687-6180
Publisher: Springer International Publishing
Altmetrics provided by Altmetric