Robust Speaker Verification Using Population-Based Data Augmentation
Lists
Only you see this
Abstract
Speaker recognition under environments with a low signal-to-noise ratio (SNR) and high reverberation level has always been challenging. Data augmentation can be applied to simulate the adverse environments that a speaker recognition system may encounter. Typically, the augmentation parameters are manually set. Recently, automatic hyper-parameter optimization using population-based learning has shown promising results. This paper proposes a population-based searching strategy for optimizing the augmentation parameters. We refer to the resulting augmentation as population-based augmentation (PBA). Instead of finding a fixed set of hyper-parameters, PBA learns a scheduler for setting the hyper-parameters. This strategy offers a considerable computation advantage over the grid search. We obtained high-performance augmentation policies using a population of six networks only. With PBA, we achieved an EER of 3.98% on the VOiCES19 evaluation set.
BibTeX
@inproceedings{lin2022robust,
author = {Weiwei Lin and Man-Wai Mak},
title = {{Robust Speaker Verification Using Population-Based Data Augmentation}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2022},
url = {https://openreview.net/forum?id=QQMa2kNrPsp},
}Loading related content...