Follow
Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation. (arXiv:2301.13003v2 [cs.CL] UPDATED)
Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation. (arXiv:2301.13003v2 [cs.CL] UPDATED)