@inproceedings{eb7c8b784e60468395688c5785e315be,
title = "Robust speaker verification using Population-based Data Augmentation",
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.",
keywords = "Robust speaker verification, data augmentation, hyper-parameter optimization, population-based learning",
author = "Weiwei Lin and Mak, {Man Wai}",
note = "Funding Information: This work was supported by the RGC of Hong Kong SAR, Grant No. PolyU 152137/17E and National Natural Science Foundation of China (NSFC), Grant No. 61971371. Publisher Copyright: {\textcopyright} 2022 IEEE",
year = "2022",
month = may,
doi = "10.1109/ICASSP43922.2022.9746956",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "IEEE",
pages = "7642--7646",
booktitle = "2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings",
address = "United States",
}