A noise robust i-vector extractor using vector taylor series for speaker recognition
ICASSP, pp. 6788-6791, 2013.
i-vectorapproximation theoryclean speech segmentsvector taylor seriesseries (mathematics)More(20+)
We propose a novel approach for noise-robust speaker recognition, where the model of distortions caused by additive and convolutive noises is integrated into the i-vector extraction framework. The model is based on a vector taylor series (VTS) approximation widely successful in noise robust speech recognition. The model allows for extract...More
Full Text (Upload PDF)
PPT (Upload PPT)