The SPIB noise dataset [39] was used in the simulation, including (1) destroyer engine room noise, (2) factory noise, (3) tank noise, (4) military vehicle noise.
One of the Japanese destroyers——developed engine trouble and turned back.
Recognition performance improves the most in destroyer-engine noise. .
Figure 11 SNR-dependent speaker recognition performance in destroyer-engine noise and average condition.
Figure 7 gives the recognition performance of two systems in destroyer-engine noise at a SNR of 0 dB.
Figure 8 The DET curves for two kinds of reconstruction methods in destroyer-engine noise at a SNR of 0 dB.
(e) The improved recognition performance is 6.04%, 6.97%, 8.99%, 5.63%, and 11.37% in babble, factory1, pink, white, and destroyer-engine noise, respectively.
In order to evaluate the validity of the proposed reconstruction method in various noise types, this paper conducts recognition experiments in babble, factory1, pink, white, and destroyer-engine noise.
Figure 7 The DET curves for two recognition systems in destroyer-engine noise at a SNR of 0 dB. Figure 8 shows that the recognition performance of the latter system improves when reconstruction is applied to process the corrupted features, and the recognition accuracy of the latter system using 2-sub-band reconstruction method is improved 5.65% more than full-band reconstruction method.
Mr. Bender blames his stint in the engine room of a Navy destroyer decades ago for his cancer, which typically shows up many years after exposure to asbestos.
