Comparing Self-Supervised Pre-Training and Semi-Supervised Training for Speech Recognition in Languages with Weak Language Models

This paper investigates the potential of improving a hybrid automatic speech recognition model trained on 10 hours of transcribed data with 200 hours of untranscribed data in low-resource languages. First, we compare baseline methods of cross-lingual transfer with MFCC features and features extracted with the multilingual self-supervised model XLSR-53. Subsequently, we compare two approaches that can leverage the untranscribed data: semi-supervised training with LF-MMI and continued self-supervised pre-training of XLSR-53. Our results on well-resourced English broadcast data derived from MGB show that both methods achieve 18% and 27% relative improvements compared to the baseline, respectively. On the low-resource South African Soap Opera dataset, the relative improvement with semi-supervised training is only 3% due to the inherently weak language model. However, continued pre-training achieves 8.6% relative improvement because it does not rely on any external information.