Follow
Macro-block dropout for improved regularization in training end-to-end speech recognition models. (arXiv:2212.14149v1 [cs.LG]) http://arxiv.org/abs/2212.14149
Macro-block dropout for improved regularization in training end-to-end speech recognition models. (arXiv:2212.14149v1 [cs.LG]) http://arxiv.org/abs/2212.14149