# Text-Independent Speaker Verification Using 3D Convolutional Neural Networks

## TL;DR

This paper introduces a 3D-CNN based approach for text-independent speaker verification, which directly creates robust speaker models from utterances, outperforming traditional averaging methods like d-vector systems.

## Contribution

The paper proposes a novel 3D-CNN architecture for direct speaker model creation, improving robustness and performance over existing d-vector methods.

## Key findings

- Significantly outperforms traditional d-vector systems.
- Captures speaker-related information more effectively.
- Provides an alternative one-shot speaker modeling approach.

## Abstract

In this paper, a novel method using 3D Convolutional Neural Network (3D-CNN) architecture has been proposed for speaker verification in the text-independent setting. One of the main challenges is the creation of the speaker models. Most of the previously-reported approaches create speaker models based on averaging the extracted features from utterances of the speaker, which is known as the d-vector system. In our paper, we propose an adaptive feature learning by utilizing the 3D-CNNs for direct speaker model creation in which, for both development and enrollment phases, an identical number of spoken utterances per speaker is fed to the network for representing the speakers' utterances and creation of the speaker model. This leads to simultaneously capturing the speaker-related information and building a more robust system to cope with within-speaker variation. We demonstrate that the proposed method significantly outperforms the traditional d-vector verification system. Moreover, the proposed system can also be an alternative to the traditional d-vector system which is a one-shot speaker modeling system by utilizing 3D-CNNs.