# Delving into VoxCeleb: environment invariant speaker recognition

arXiv: https://arxiv.org/abs/1910.11238 · HTML: https://mlsanity.com/paper/1910.11238/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2019.

## Built on by (most cited first, 13 of 13)

- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning](https://mlsanity.com/paper/2207.05506/) (2022)
- [Multi-View Self-Attention Based Transformer for Speaker Recognition](https://mlsanity.com/paper/2110.05036/) (2021)
- [In search of strong embedding extractors for speaker diarisation](https://mlsanity.com/paper/2210.14682/) (2022)
- [Synthetic Speech Source Tracing using Metric Learning](https://mlsanity.com/paper/2506.02590/) (2025)
- [Whose Emotion Matters? Speaking Activity Localisation without Prior Knowledge](https://mlsanity.com/paper/2211.15377/) (2022)
- [Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification](https://mlsanity.com/paper/2306.03664/) (2023)
- [Additive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representations](https://mlsanity.com/paper/2404.14913/) (2024)
- [A Study on Bias and Fairness In Deep Speaker Recognition](https://mlsanity.com/paper/2303.08026/) (2023)
- [Advancing the dimensionality reduction of speaker embeddings for speaker diarisation: disentangling noise and informing speech activity](https://mlsanity.com/paper/2110.03380/) (2021)
- [Macro-block dropout for improved regularization in training end-to-end speech recognition models](https://mlsanity.com/paper/2212.14149/) (2022)
- [Adaptive Multimodal Person Recognition: A Robust Framework for Handling Missing Modalities](https://mlsanity.com/paper/2512.14961/) (2025)
- [Self-Supervised Learning for Speaker Recognition: A study and review](https://mlsanity.com/paper/2602.10829/) (2026)

## Abstract (arXiv)

Research in speaker recognition has recently seen significant progress due to the application of neural network models and the availability of new large-scale datasets. There has been a plethora of work in search for more powerful architectures or loss functions suitable for the task, but these works do not consider what information is learnt by the models, apart from being able to predict the given labels. In this work, we introduce an environment adversarial training framework in which the network can effectively learn speaker-discriminative and environment-invariant embeddings without explicit domain shift during training. We achieve this by utilising the previously unused `video' information in the VoxCeleb dataset. The environment adversarial training allows the network to generalise better to unseen conditions. The method is evaluated on both speaker identification and verification tasks using the VoxCeleb dataset, on which we demonstrate significant performance improvements over baselines.