0:00:15i don't
0:00:18i'm going to percent for about the speaker recognition in formant frequencies in linguistic units
0:00:24and the motivation is the wavelet use of the formant frequencies applied in linguistic constraints
0:00:30in four and six but there's a need to validate these formant based speaker discrimination
0:00:37of formant frequencies from the standard benchmark by nist sre
0:00:44so you know previous work we present an approach to in which we extract i-vectors
0:00:51from the segments belonging to a specific and linguistic constraints
0:00:59based on formant frequencies and we use the score a cosine scoring and score normalization
0:01:05and not clear is understanding of the to obtain a wellcalibrated slant ranges better linguistic
0:01:14i in this work for a sequence as existing we replace a cosine scoring
0:01:22and score normalization and calibration steps
0:01:26with a covariance model
0:01:28and based on the same linguistically constraining formation i-vectors
0:01:34and be used in a improve discrimination which is not surprising
0:01:39but the thing is that we obtain a scores with low below countries you're a
0:01:45the constraint so we can be used directly as like radios
0:01:50a million the an additional information from score school
0:01:55like right yes
0:01:57bizarre the results when combining several of these linguistic constraints
0:02:03on nist sre two thousand and six
0:02:08decide there is also just remind that
0:02:11it and the results are using a and formant frequencies
0:02:17that's this summer i u one two normal at a site would be of course
0:02:20that's ser mean of stardom or think