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