Low-resource Language Discrimination Towards Chinese Dialects with Transfer learning and Data Augmentation

2026-06-16

AI Summary

This study addresses the challenge of scarce labeled data in low-resource Chinese dialect identification by proposing the CDDTLDA framework, which integrates transfer learning with lightweight speech data augmentation techniques—including speech rate, pitch, and noise perturbations. The approach first pretrains an automatic speech recognition (ASR) model on a high-resource source dialect and then employs a self-attention mechanism to extract cross-dialect shared semantic features, which are subsequently fine-tuned on the target low-resource dialect. Experimental results demonstrate that the proposed framework significantly outperforms current state-of-the-art methods on two benchmark Chinese dialect datasets, effectively enhancing dialect identification performance under low-resource conditions.

Abstract

Chinese dialects discrimination is a challenging natural language processing task due to scarce annotation resource. In this article, we develop a novel Chinese dialects discrimination framework with transfer learning and data augmentation (CDDTLDA) in order to overcome the shortage of resources. To be more specific, we first use a relatively larger Chinese dialects corpus to train a source-side automatic speech recognition (ASR) model. Then, we adopt a simple but effective data augmentation method (i.e., speed, pitch, and noise disturbance) to augment the target-side low-resource Chinese dialects, and fine-tune another target ASR model based on the previous source-side ASR model. Meanwhile, the potential common semantic features between source-side and target-side ASR models can be captured by using self-attention mechanism. Finally, we extract the hidden semantic representation in the target ASR model to conduct Chinese dialects discrimination. Our extensive experimental results demonstrate that our model significantly outperforms state-of-the-art methods on two benchmark Chinese dialects corpora.

Problem

• Chinese dialects discrimination
• low-resource
• natural language processing
• annotation scarcity

Innovation

• transfer learning
• data augmentation
• Chinese dialects discrimination
• automatic speech recognition
• self-attention mechanism