Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR
Abstract
Code-switching (CS), alternating languages within the same utterance, poses significant challenges for automatic speech recognition (ASR) due to limited CS training data. This paper applies an iterative pseudo-labeling training approach to CS-ASR for the first time, demonstrating its effectiveness in leveraging unlabeled data to improve CS-ASR performance. The approach comprises three phases: pseudo-label generation, two-stage bilingual model training, and iterative improvements. It begins by generating pseudo-labels from a large unlabeled corpus, creating a semi-supervised dataset. This dataset supports a two-stage training framework where the model is pre-trained and then fine-tuned on supervised CS data. Iterative refinements further enhance the model's accuracy in handling complex CS scenarios. Our approach significantly advances CS-ASR systems, achieving notable Mix Error Rate (MER) reductions on SEAME's devman (6.35%) and devsge (8.29%) subsets.
Cite
@article{arxiv.2607.05224,
title = {Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR},
author = {Qu Yang and Cakra Wardhana and Tim Ng},
journal= {arXiv preprint arXiv:2607.05224},
year = {2026}
}