Entity · paper

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

paperactiveprovisionalprogressive-refinement-an-iterative-pseudo-labeling-approach-for-mandarin-english-code-switching-asr-46202f8b·1 events·first seen 41h ago

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

Co-occurring entities

SEAME

More like this (12)

Learning to Hear Hesitation: Continual Learning for Disfluency-Aware ASR language-adaptive switch LLM-based code change labeling pipeline On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners Posterior Refinement: Fast Language Generation via Any-Order Flow Maps Scaling LLM Reasoning from Minimal Labels: A Semi-Supervised Framework with a Lightweight Verifier Leveraging Audio-LLMs to Filter Speech-to-Speech Training Data Grammar-Constrained Decoding Adaptive Turn-Taking for Real-time Multi-Party Voice Agents Language-Critique Imitation Learning from Suboptimal Demonstrations FlowEdit: Associative Memory for Lifelong Pronunciation Adaptation in Flow-Matching TTS Soft Label Supervision

Recent events (1)

3arXiv · cs.CL·41h ago·source ↗

Iterative pseudo-labeling approach improves Mandarin-English code-switching ASR

A new arXiv preprint introduces a three-phase iterative pseudo-labeling framework for code-switching automatic speech recognition (ASR), applied here to Mandarin-English mixing. The method generates pseudo-labels from unlabeled corpora, trains a bilingual model in two stages, and iteratively refines it, achieving Mix Error Rate reductions of 6.35% and 8.29% on the SEAME benchmark's devman and devsge subsets. This is the first application of iterative pseudo-labeling to code-switching ASR, addressing the chronic data scarcity problem in this domain.

Evaluation and Benchmarking SEAME Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR