# Deep Speaker Verification: Do We Need End to End?

## TL;DR

This paper compares end-to-end and feature learning approaches for speaker verification, finding that feature learning outperforms end-to-end methods on a large-scale dataset, highlighting the importance of approach selection.

## Contribution

The study provides a direct comparison between end-to-end and feature learning methods for speaker verification, demonstrating the superiority of feature learning in their experimental setup.

## Key findings

- Feature learning outperforms end-to-end on Fisher dataset
- Deep neural networks significantly improve speaker verification
- Results support using feature learning with available data and resources

## Abstract

End-to-end learning treats the entire system as a whole adaptable black box, which, if sufficient data are available, may learn a system that works very well for the target task. This principle has recently been applied to several prototype research on speaker verification (SV), where the feature learning and classifier are learned together with an objective function that is consistent with the evaluation metric. An opposite approach to end-to-end is feature learning, which firstly trains a feature learning model, and then constructs a back-end classifier separately to perform SV. Recently, both approaches achieved significant performance gains on SV, mainly attributed to the smart utilization of deep neural networks. However, the two approaches have not been carefully compared, and their respective advantages have not been well discussed. In this paper, we compare the end-to-end and feature learning approaches on a text-independent SV task. Our experiments on a dataset sampled from the Fisher database and involving 5,000 speakers demonstrated that the feature learning approach outperformed the end-to-end approach. This is a strong support for the feature learning approach, at least with data and computation resources similar to ours.