Noise robust speaker verification using GMM-UBM multi-condition training

In this paper, two model based approaches are applied to make GMM-UBM based speaker verification task noise robust. In the first approach, speaker model adaptation is implemented based on the noise condition observed during verification. In the second approach, multi-condition training is adopted in which multiple speaker models are trained using multiple noisy speech samples. In both approaches a range of signal to noise ratios are considered. The performance of the systems in clean and environmental noise conditions is tested for both target trials and impostor trials. For test utterance corrupted by additive noise, test results show that multi-condition based noise compensation approach achieve from 1.34to 4.8percentage improvement for GMM-UBM.