persoDA: Personalized Data Augmentation for Personalized ASR
Pablo Peso Parada, Spyros Fontalis, Md Asif Jalal, Karthikeyan Saravanan, Anastasios Drosou, Mete Ozay, Gil Ho Lee, Jungin Lee
Abstract
Data augmentation (DA) is ubiquitously used in training of Automatic Speech Recognition (ASR) models. DA offers increased data variability, robustness and generalization against different acoustic distortions. Recently, personalization of ASR models on mobile devices has been shown to improve Word Error Rate (WER). This paper evaluates data augmentation in this context and proposes persoDA; a DA method driven by user’s data utilized to personalize ASR [1] –[3]. persoDA aims to augment training with data specifically tuned towards acoustic characteristics of the end-user, as opposed to standard augmentation based on Multi-Condition Training (MCT) that applies random reverberation and noises. Our evaluation with an ASR conformer-based baseline trained on Librispeech and per-sonalized for VOICES [4] shows that persoDA achieves a 13.9% relative WER reduction over using standard data augmentation (using random noise & reverberation). Furthermore, persoDA shows 16% to 20% faster convergence over MCT.
BibTeX
@inproceedings{icassp2025_persodapersonali,
title = {persoDA: Personalized Data Augmentation for Personalized ASR},
author = {Pablo Peso Parada and Spyros Fontalis and Md Asif Jalal and Karthikeyan Saravanan and Anastasios Drosou and Mete Ozay and Gil Ho Lee and Jungin Lee and Seokyeong Jung},
booktitle = {ICASSP 2025},
year = {2025}
}