conferenceObject info:eu-repo/semantics/acceptedVersion © IEEE All rights reserved ABSTRACT It is well-known that for speaker recognition task, genderdependent acoustic modeling performs better than genderindependent modeling. The practice is to use the gender ground-truth and to train gender-dependent models. However, such information is not necessarily available, especially if speakers are remotely enrolled. A way to overcome this is to use a gender classification system, which introduces an

more »

... dditional layer of uncertainty. To date, such uncertainty has not been studied. We implement two gender classifier systems and test them with two different corpora and speaker verification systems. We find that estimated gender information can improve speaker verification accuracy over genderindependent methods. Our detailed analysis suggests that gender estimation should have a sufficiently high accuracy to yield improvements in speaker verification performance.