oboVox Far Field Speaker Recognition: A Novel Data Augmentation Approach with Pretrained Models

TL;DR

This paper introduces a novel noise-based data augmentation method for far-field speaker recognition, leveraging pre-trained models like ResNet to improve accuracy and robustness in challenging acoustic environments.

Contribution

The study proposes a new noise augmentation technique that aligns test and enrollment data sources, demonstrating its effectiveness with pre-trained models, especially ResNet, in far-field speaker recognition.

Findings

ResNet achieved a DCF of 0.84 and EER of 13.44 before augmentation.

Augmentation improved ResNet performance to 0.75 DCF and 12.79 EER.

ResNet outperformed ECPA, Mel-spectrogram, Payonnet, and Titanet large models.

Abstract

In this study, we address the challenge of speaker recognition using a novel data augmentation technique of adding noise to enrollment files. This technique efficiently aligns the sources of test and enrollment files, enhancing comparability. Various pre-trained models were employed, with the resnet model achieving the highest DCF of 0.84 and an EER of 13.44. The augmentation technique notably improved these results to 0.75 DCF and 12.79 EER for the resnet model. Comparative analysis revealed the superiority of resnet over models such as ECPA, Mel-spectrogram, Payonnet, and Titanet large. Results, along with different augmentation schemes, contribute to the success of RoboVox far-field speaker recognition in this paper