Saved in:
Bibliographic Details
Main Authors: Choi, Jeong-Hwan, Seong, Ju-Seok, Jeoung, Ye-Rin, Chang, Joon-Hyuk
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.04512
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Adaptive S-norm (AS-norm) calibrates automatic speaker verification (ASV) scores by normalizing them utilize the scores of impostors which are similar to the input speaker. However, AS-norm does not involve any learning process, limiting its ability to provide appropriate regularization strength for various evaluation utterances. To address this limitation, we propose a trainable AS-norm (TAS-norm) that leverages learnable impostor embeddings (LIEs), which are used to compose the cohort. These LIEs are initialized to represent each speaker in a training dataset consisting of impostor speakers. Subsequently, LIEs are fine-tuned by simulating an ASV evaluation. We utilize a margin penalty during top-scoring IEs selection in fine-tuning to prevent non-impostor speakers from being selected. In our experiments with ECAPA-TDNN, the proposed TAS-norm observed 4.11% and 10.62% relative improvement in equal error rate and minimum detection cost function, respectively, on VoxCeleb1-O trial compared with standard AS-norm without using proposed LIEs. We further validated the effectiveness of the TAS-norm on additional ASV datasets comprising Persian and Chinese, demonstrating its robustness across different languages.