Data selection with kurtosis and nasality features for speaker recognition
Howard Lei, Nikki Mirghafori · 2011
We propose new data selection approaches based on speaker discriminability features, including kurtosis and a set of nasal-ity features which exploit spectral properties of nasal speech sounds. Data selected based on the speaker discriminability fea-tures are used to implement end-to-end speaker recognition sys-tems, which produce significant improvements when combined with the baseline system (which uses the speech-only data re-gions determined by a speech/non-speech detector), where the optimal combination of systems produces roughly a 24 % im-provement over the baseline. Results suggest that focusing the modeling power on data regions selected via the kurtosis and nasality speaker discriminability features, part of which are of-ten discarded in the speech/non-speech detection process, can improvement speaker recognition. Index Terms: speaker recognition, kurtosis, nasality features, data selection