Whisper-SLU: Extending a pretrained speech-to-text transformer for low resource spoken language understanding KU Leuven
In recent years, transformers have become a fundamental part of machine learning research and have demonstrated impressive results in various fields. However, they require significant resources for training. This paper proposes extending the Whisper transformer-based model with dedicated modules for low resource spoken language understanding tasks, including named entity recognition and intent recognition. The authors borrow techniques from ...