# Centroid-based deep metric learning for speaker recognition

arXiv: https://arxiv.org/abs/1902.02375 · HTML: https://mlsanity.com/paper/1902.02375/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2019.

## Built on by (most cited first, 20 of 20)

- [On the Unreasonable Effectiveness of Centroids in Image Retrieval](https://mlsanity.com/paper/2104.13643/) (2021)
- [A Closer Look at Prototype Classifier for Few-shot Image Classification](https://mlsanity.com/paper/2110.05076/) (2021)
- [Deepfake audio detection by speaker verification](https://mlsanity.com/paper/2209.14098/) (2022)
- [N-pad : Neighboring Pixel-based Industrial Anomaly Detection](https://mlsanity.com/paper/2210.08768/) (2022)
- [Feature Generation for Long-tail Classification](https://mlsanity.com/paper/2111.05956/) (2021)
- [Online Deterministic Annealing for Classification and Clustering](https://mlsanity.com/paper/2102.05836/) (2021)
- [Sports Re-ID: Improving Re-Identification Of Players In Broadcast Videos Of Team Sports](https://mlsanity.com/paper/2206.02373/) (2022)
- [Domain Agnostic Few-shot Learning for Speaker Verification](https://mlsanity.com/paper/2206.13700/) (2022)
- [Real Additive Margin Softmax for Speaker Verification](https://mlsanity.com/paper/2110.09116/) (2021)
- [Speaker attribution with voice profiles by graph-based semi-supervised learning](https://mlsanity.com/paper/2102.03634/) (2021)
- [Training speaker recognition systems with limited data](https://mlsanity.com/paper/2203.14688/) (2022)
- [Automatic Evaluation of Speaker Similarity](https://mlsanity.com/paper/2207.00344/) (2022)
- [Prototypical Contrastive Learning For Improved Few-Shot Audio Classification](https://mlsanity.com/paper/2509.10074/) (2025)
- [Semi Supervised Learning For Few-shot Audio Classification By Episodic Triplet Mining](https://mlsanity.com/paper/2102.08074/) (2021)
- [Prototype-based Personalized Pruning](https://mlsanity.com/paper/2103.15564/) (2021)
- [Improved Relation Networks for End-to-End Speaker Verification and Identification](https://mlsanity.com/paper/2203.17218/) (2022)
- [Lexical semantics enhanced neural word embeddings](https://mlsanity.com/paper/2210.00754/) (2022)
- [Toward Improving Synthetic Audio Spoofing Detection Robustness via Meta-Learning and Disentangled Training With Adversarial Examples](https://mlsanity.com/paper/2408.13341/) (2024)
- [Meta-Learning Framework for End-to-End Imposter Identification in Unseen Speaker Recognition](https://mlsanity.com/paper/2306.00952/) (2023)
- [Person Re-Identification via Generalized Class Prototypes](https://mlsanity.com/paper/2510.17043/) (2025)

## Abstract (arXiv)

Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker recognition task. However, there is still a significant performance gap between recognizing speakers in the training set and unseen speakers. The latter case corresponds to the few-shot learning task, where a trained model is evaluated on unseen classes. Here, we optimize a speaker embedding model with prototypical network loss (PNL), a state-of-the-art approach for the few-shot image classification task. The resulting embedding model outperforms the state-of-the-art triplet loss based models in both speaker verification and identification tasks, for both seen and unseen speakers.