Saved in:
Bibliographic Details
Main Authors: Bian, Wesley, Lin, Xiaofeng, Cheng, Guang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.20534
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918217972187136
author Bian, Wesley
Lin, Xiaofeng
Cheng, Guang
author_facet Bian, Wesley
Lin, Xiaofeng
Cheng, Guang
contents Modern machine learning models for audio tasks often exhibit superior performance on English and other well-resourced languages, primarily due to the abundance of available training data. This disparity leads to an unfair performance gap for low-resource languages, where data collection is both challenging and costly. In this work, we introduce a novel data augmentation technique for speech corpora designed to mitigate this gap. Through comprehensive experiments, we demonstrate that our method significantly improves the performance of automatic speech recognition systems on low-resource languages. Furthermore, we show that our approach outperforms existing augmentation strategies, offering a practical solution for enhancing speech technology in underrepresented linguistic communities.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20534
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bridging the Language Gap: Synthetic Voice Diversity via Latent Mixup for Equitable Speech Recognition
Bian, Wesley
Lin, Xiaofeng
Cheng, Guang
Computation and Language
Modern machine learning models for audio tasks often exhibit superior performance on English and other well-resourced languages, primarily due to the abundance of available training data. This disparity leads to an unfair performance gap for low-resource languages, where data collection is both challenging and costly. In this work, we introduce a novel data augmentation technique for speech corpora designed to mitigate this gap. Through comprehensive experiments, we demonstrate that our method significantly improves the performance of automatic speech recognition systems on low-resource languages. Furthermore, we show that our approach outperforms existing augmentation strategies, offering a practical solution for enhancing speech technology in underrepresented linguistic communities.
title Bridging the Language Gap: Synthetic Voice Diversity via Latent Mixup for Equitable Speech Recognition
topic Computation and Language
url https://arxiv.org/abs/2511.20534