MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition. (arXiv:2212.00500v1 [cs.MM]) Show more
http://arxiv.org/abs/2212.00500 #arXiv #NLProc
QOTO: Question Others to Teach Ourselves An inclusive, Academic Freedom, instance All cultures welcome. Hate speech and harassment strictly forbidden.
