# Domain Agnostic Few-shot Learning for Speaker Verification

arXiv: https://arxiv.org/abs/2206.13700 · HTML: https://mlsanity.com/paper/2206.13700/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 28 Jun 2022.

## Builds on (most cited first, 23 of 23)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [Episodic Training for Domain Generalization](https://mlsanity.com/paper/1902.00113/) (2019)
- [Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation](https://mlsanity.com/paper/2001.08735/) (2020)
- [Domain Generalization Using a Mixture of Multiple Latent Domains](https://mlsanity.com/paper/1911.07661/) (2019)
- [In defence of metric learning for speaker recognition](https://mlsanity.com/paper/2003.11982/) (2020)
- [End-to-End Text-Dependent Speaker Verification](https://mlsanity.com/paper/1509.08062/) (2015)
- [Large Margin Softmax Loss for Speaker Verification](https://mlsanity.com/paper/1904.03479/) (2019)
- [CN-Celeb: multi-genre speaker recognition](https://mlsanity.com/paper/2012.12468/) (2020)
- [Centroid-based deep metric learning for speaker recognition](https://mlsanity.com/paper/1902.02375/) (2019)
- [Few Shot Speaker Recognition using Deep Neural Networks](https://mlsanity.com/paper/1904.08775/) (2019)
- [Angular Softmax Loss for End-to-end Speaker Verification](https://mlsanity.com/paper/1806.03464/) (2018)
- [Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization](https://mlsanity.com/paper/2111.06531/) (2021)
- [An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network](https://mlsanity.com/paper/1908.02612/) (2019)
- [Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learning](https://mlsanity.com/paper/2005.11900/) (2020)
- [End-to-end losses based on speaker basis vectors and all-speaker hard negative mining for speaker verification](https://mlsanity.com/paper/1902.02455/) (2019)
- [Triplet Based Embedding Distance and Similarity Learning for Text-independent Speaker Verification](https://mlsanity.com/paper/1908.02283/) (2019)
- [Arbitrary Style Transfer using Graph Instance Normalization](https://mlsanity.com/paper/2010.02560/) (2020)

## Built on by (most cited first, 4 of 4)

- [Progressive Random Convolutions for Single Domain Generalization](https://mlsanity.com/paper/2304.00424/) (2023)
- [Adaptive Domain Generalization via Online Disagreement Minimization](https://mlsanity.com/paper/2208.01996/) (2022)
- [Constrained Maximum Cross-Domain Likelihood for Domain Generalization](https://mlsanity.com/paper/2210.04155/) (2022)
- [L-Proto: Language-Aware Episodic Prototypical Training for Multilingual Speaker Verification](https://mlsanity.com/paper/2606.17416/) (2026)

## Abstract (arXiv)

Deep learning models for verification systems often fail to generalize to new users and new environments, even though they learn highly discriminative features. To address this problem, we propose a few-shot domain generalization framework that learns to tackle distribution shift for new users and new domains. Our framework consists of domain-specific and domain-aggregation networks, which are the experts on specific and combined domains, respectively. By using these networks, we generate episodes that mimic the presence of both novel users and novel domains in the training phase to eventually produce better generalization. To save memory, we reduce the number of domain-specific networks by clustering similar domains together. Upon extensive evaluation on artificially generated noise domains, we can explicitly show generalization ability of our framework. In addition, we apply our proposed methods to the existing competitive architecture on the standard benchmark, which shows further performance improvements.