# Trainable Adaptive Score Normalization for Automatic Speaker Verification

arXiv: https://arxiv.org/abs/2504.04512 · HTML: https://mlsanity.com/paper/2504.04512/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Speaker recognition and diarization, one of 11 directions in Speech and audio language models.
- Builds on 16 of its 47 references that are in the map.
- First posted on arXiv 6 Apr 2025.

## Placed in

- Speech and audio language models / [Speaker recognition and diarization](https://mlsanity.com/speech/speaker-recognition-and-diarization/)

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [In defence of metric learning for speaker recognition](https://mlsanity.com/paper/2003.11982/) (2020)
- [Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit](https://mlsanity.com/paper/2210.17016/) (2022)
- [CN-CELEB: a challenging Chinese speaker recognition dataset](https://mlsanity.com/paper/1911.01799/) (2019)
- [CN-Celeb: multi-genre speaker recognition](https://mlsanity.com/paper/2012.12468/) (2020)
- [Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective](https://mlsanity.com/paper/2302.01425/) (2023)
- [A Multi Purpose and Large Scale Speech Corpus in Persian and English for Speaker and Speech Recognition: the DeepMine Database](https://mlsanity.com/paper/1912.03627/) (2019)
- [Cross-Lingual Speaker Verification with Domain-Balanced Hard Prototype Mining and Language-Dependent Score Normalization](https://mlsanity.com/paper/2007.07689/) (2020)
- [NeXt-TDNN: Modernizing Multi-Scale Temporal Convolution Backbone for Speaker Verification](https://mlsanity.com/paper/2312.08603/) (2023)
- [The SpeakIn Speaker Verification System for Far-Field Speaker Verification Challenge 2022](https://mlsanity.com/paper/2209.11625/) (2022)
- [Team HYU ASML ROBOVOX SP Cup 2024 System Description](https://mlsanity.com/paper/2407.11365/) (2024)

## Abstract (arXiv)

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.