content type paperpublished August 2026
Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR
AuthorsQu Yang†**, Cakra Wardhana, Tim Ng
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.
- † National University of Singapore
- ** Work done while at Apple
Related readings and updates.
Cross-lingual Knowledge Transfer and Iterative Pseudo-labeling for Low-Resource Speech Recognition with Transducers
June 16, 2023research area Speech and Natural Language Processing
Voice technology has become ubiquitous recently. However, the accuracy, and hence experience, in different languages varies significantly, which makes the technology not equally inclusive. The availability of data for different languages is one of the key factors affecting accuracy, especially in training of all-neural end-to-end automatic speech recognition systems.
Cross-lingual knowledge transfer and iterative pseudo-labeling are two…
Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data
May 12, 2023research area Speech and Natural Language Processingconference ACL
Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool. In this work, we investigate and use pseudo-labeling for a recently proposed novel setup: joint transcription and translation of speech, which suffers from an absence of sufficient parallel data resources. We…
Discover opportunities in Machine Learning.
Our research in machine learning breaks new ground every day.