Text-independent speaker recognition from a large linguistically unconstrained time-spaced data base

A very large data base consisting of over 36 h of unconstrained extemporaneous speech, from 17 speakers, recorded over a period of more than three months, has been analyzed to determine the effectiveness of long-term average features for speaker recognition. Results are shown to be strongly dependent on the voiced speech averaging interval Lε. Monotonic increases in the probability of correct identification and monotonic decreases in the equal error probability for speaker verification were obtained as Lεincreased, even with substantial time periods between successive sessions. For Lεcorresponding to approximately 39 s of speech, text-independent results (no linguistic constraints embedded into the data base) of 98.05 percent for speaker identification and 4.25 percent for equal error speaker verification were obtained.