paper-with-me

홈 › Papers

Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR

2026-07-06 · Qu Yang, Cakra Wardhana, Tim Ng arxiv

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.

📄 PDF Abstract BibTeX arXiv:2607.05224

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Recognition

Similar Papers 제목 키워드 기반

ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models

2026-02-21 · Zefang Liu, Chenyang Zhu, Sangwoo Cho, Shi-Xiong Zhang arxiv

Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, …

Speech Recognition

RefineLoc: Iterative Refinement for Weakly-Supervised Action Localization

2019-03-30 · Alejandro Pardo, Humam Alwassel, Fabian Caba Heilbron, Ali Thabet 외

Video action detectors are usually trained using datasets with fully-supervised temporal annotations. Building such datasets is an expensive task. To alleviate this problem, recent methods have tried to leverage weak lab…

Action LocalizationTemporal Action LocalizationTemporal LocalizationWeakly Supervised Action Localization+1

Divide and Ensemble: Progressively Learning for the Unknown

2023-10-09 · Hu Zhang, Xin Shen, Heming Du, Huiqiang Chen 외

In the wheat nutrient deficiencies classification challenge, we present the DividE and EnseMble (DEEM) method for progressive test data predictions. We find that (1) test images are provided in the challenge; (2) samples…

Foundation Model-guided Iteratively Prompting and Pseudo-Labeling for Partially Labeled Medical Image Segmentation

2026-04-01 · Qiaochu Zhao, Wei Wei, David Horowitz, Richard Bakst 외 arxiv

Automated medical image segmentation has achieved remarkable progress with fully labeled data. However, site-specific clinical priorities and the high cost of manual annotation often yield scans with only a subset of org…

Medical Image Segmentation

ElimPCL: Eliminating Noise Accumulation with Progressive Curriculum Labeling for Source-Free Domain Adaptation

2025-03-31 · Jie Cheng, Hao Zheng, Meiguang Zheng, Lei Wang 외

Source-Free Domain Adaptation (SFDA) aims to train a target model without source data, and the key is to generate pseudo-labels using a pre-trained source model. However, we observe that the source model often produces h…

Domain AdaptationSource-Free Domain Adaptation