Code-switching (CS), alternating languages within the same utterance, poses significant challenges for automatic speech ...

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.Source: Apple Machine Learning Researchhttps://machinelearning.apple.com/research/progressive-refinement-pseudo-labeling#MachineLearning