TY - JOUR
T1 - Evaluation of a speaker identification system with and without fusion using three databases in the presence of noise and handset effects
AU - Al-Kaltakchi, Musab T. S.
AU - Woo, Wai L.
AU - Dlay, Satnam
AU - Chambers, Jonathon A.
PY - 2017/12/2
Y1 - 2017/12/2
N2 - 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.
AB - 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.
KW - Speaker identification system
KW - TIMIT
KW - SITW 2016 and NIST2008 databases
KW - Noise and handset effects
U2 - 10.1186/s13634-017-0515-7
DO - 10.1186/s13634-017-0515-7
M3 - Article
SN - 1687-6180
VL - 2017
JO - Eurasip Journal on Advances in Signal Processing
JF - Eurasip Journal on Advances in Signal Processing
M1 - 80
ER -