# Few Shot Speaker Recognition using Deep Neural Networks

arXiv: https://arxiv.org/abs/1904.08775 · HTML: https://mlsanity.com/paper/1904.08775/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2019.

## Built on by (most cited first, 8 of 8)

- [Learning from Few Examples: A Summary of Approaches to Few-Shot Learning](https://mlsanity.com/paper/2203.04291/) (2022)
- [Large Language Models Vote: Prompting for Rare Disease Identification](https://mlsanity.com/paper/2308.12890/) (2023)
- [Domain Agnostic Few-shot Learning for Speaker Verification](https://mlsanity.com/paper/2206.13700/) (2022)
- [Fusion of Embeddings Networks for Robust Combination of Text Dependent and Independent Speaker Recognition](https://mlsanity.com/paper/2106.10169/) (2021)
- [Meta-Learning in Audio and Speech Processing: An End to End Comprehensive Review](https://mlsanity.com/paper/2408.10330/) (2024)
- [Semi Supervised Learning For Few-shot Audio Classification By Episodic Triplet Mining](https://mlsanity.com/paper/2102.08074/) (2021)
- [A Multi-tasking Model of Speaker-Keyword Classification for Keeping Human in the Loop of Drone-assisted Inspection](https://mlsanity.com/paper/2207.04027/) (2022)
- [Text-Independent Speaker Identification Using Audio Looping With Margin Based Loss Functions](https://mlsanity.com/paper/2509.22838/) (2025)

## Abstract (arXiv)

The recent advances in deep learning are mostly driven by availability of large amount of training data. However, availability of such data is not always possible for specific tasks such as speaker recognition where collection of large amount of data is not possible in practical scenarios. Therefore, in this paper, we propose to identify speakers by learning from only a few training examples. To achieve this, we use a deep neural network with prototypical loss where the input to the network is a spectrogram. For output, we project the class feature vectors into a common embedding space, followed by classification. Further, we show the effectiveness of capsule net in a few shot learning setting. To this end, we utilize an auto-encoder to learn generalized feature embeddings from class-specific embeddings obtained from capsule network. We provide exhaustive experiments on publicly available datasets and competitive baselines, demonstrating the superiority and generalization ability of the proposed few shot learning pipelines.