# Cosine-Distance Virtual Adversarial Training for Semi-Supervised Speaker-Discriminative Acoustic Embeddings

arXiv: https://arxiv.org/abs/2008.03756 · HTML: https://mlsanity.com/paper/2008.03756/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2020.

## Built on by (most cited first, 3 of 3)

- [ReconVAT: A Semi-Supervised Automatic Music Transcription Framework for Low-Resource Real-World Data](https://mlsanity.com/paper/2107.04954/) (2021)
- [Graph-based Label Propagation for Semi-Supervised Speaker Identification](https://mlsanity.com/paper/2106.08207/) (2021)
- [Enhancing Audio Augmentation Methods with Consistency Learning](https://mlsanity.com/paper/2102.05151/) (2021)

## Abstract (arXiv)

In this paper, we propose a semi-supervised learning (SSL) technique for training deep neural networks (DNNs) to generate speaker-discriminative acoustic embeddings (speaker embeddings). Obtaining large amounts of speaker recognition train-ing data can be difficult for desired target domains, especially under privacy constraints. The proposed technique reduces requirements for labelled data by leveraging unlabelled data. The technique is a variant of virtual adversarial training (VAT) [1] in the form of a loss that is defined as the robustness of the speaker embedding against input perturbations, as measured by the cosine-distance. Thus, we term the technique cosine-distance virtual adversarial training (CD-VAT). In comparison to many existing SSL techniques, the unlabelled data does not have to come from the same set of classes (here speakers) as the labelled data. The effectiveness of CD-VAT is shown on the 2750+ hour VoxCeleb data set, where on a speaker verification task it achieves a reduction in equal error rate (EER) of 11.1% relative to a purely supervised baseline. This is 32.5% of the improvement that would be achieved from supervised training if the speaker labels for the unlabelled data were available.