@misc{verma2021attention, title={Attention is All You Need? Good Embeddings with Statistics are enough:Large Scale Audio Understanding without Transformers/ Convolutions/ BERTs/ Mixers/ Attention/ RNNs or ....}, author={Prateek Verma}, year={2021}, eprint={2110.03183}, archivePrefix={arXiv}, primaryClass={cs.SD}, url={https://arxiv.org/abs/2110.03183} }