# Adversarial Data Augmentation for Robust Speaker Verification

arXiv: https://arxiv.org/abs/2402.02699 · HTML: https://mlsanity.com/paper/2402.02699/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 17 of 17)

- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [Attentive Statistics Pooling for Deep Speaker Embedding](https://mlsanity.com/paper/1803.10963/) (2018)
- [Speaker Recognition Based on Deep Learning: An Overview](https://mlsanity.com/paper/2012.00931/) (2020)
- [CN-CELEB: a challenging Chinese speaker recognition dataset](https://mlsanity.com/paper/1911.01799/) (2019)
- [THCHS-30 : A Free Chinese Speech Corpus](https://mlsanity.com/paper/1512.01882/) (2015)
- [Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition](https://mlsanity.com/paper/1906.07317/) (2019)
- [Augmentation adversarial training for self-supervised speaker recognition](https://mlsanity.com/paper/2007.12085/) (2020)
- [The 2021 NIST Speaker Recognition Evaluation](https://mlsanity.com/paper/2204.10242/) (2022)
- [VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challenge](https://mlsanity.com/paper/2302.10248/) (2023)
- [Deep Speaker Feature Learning for Text-independent Speaker Verification](https://mlsanity.com/paper/1705.03670/) (2017)
- [Build a SRE Challenge System: Lessons from VoxSRC 2022 and CNSRC 2022](https://mlsanity.com/paper/2211.00815/) (2022)
- [Data augmentation versus noise compensation for x- vector speaker recognition systems in noisy environments](https://mlsanity.com/paper/2006.15903/) (2020)
- [Adversarial Training for Multi-domain Speaker Recognition](https://mlsanity.com/paper/2011.08623/) (2020)
- [Spot keywords from very noisy and mixed speech](https://mlsanity.com/paper/2305.17706/) (2023)

## Built on by (most cited first, 1 of 1)

- [Automatic Speech Recognition using Advanced Deep Learning Approaches: A survey](https://mlsanity.com/paper/2403.01255/) (2024)

## Abstract (arXiv)

Data augmentation (DA) has gained widespread popularity in deep speaker models due to its ease of implementation and significant effectiveness. It enriches training data by simulating real-life acoustic variations, enabling deep neural networks to learn speaker-related representations while disregarding irrelevant acoustic variations, thereby improving robustness and generalization. However, a potential issue with the vanilla DA is augmentation residual, i.e., unwanted distortion caused by different types of augmentation. To address this problem, this paper proposes a novel approach called adversarial data augmentation (A-DA) which combines DA with adversarial learning. Specifically, it involves an additional augmentation classifier to categorize various augmentation types used in data augmentation. This adversarial learning empowers the network to generate speaker embeddings that can deceive the augmentation classifier, making the learned speaker embeddings more robust in the face of augmentation variations. Experiments conducted on VoxCeleb and CN-Celeb datasets demonstrate that our proposed A-DA outperforms standard DA in both augmentation matched and mismatched test conditions, showcasing its superior robustness and generalization against acoustic variations.