Abstract: The conversion of brain activity into text using electroencephalography (EEG) has gained significant traction in recent years. Many researchers are working to develop new models to decode ...
Course project extending DCoND with: (i) a skip-diphone auxiliary head (z_{t-2} → z_t), and (ii) a temporal smoothness loss on marginalized phoneme probabilities. See docs/proposal.pdf for full ...
Abstract: Autoregressive generative models have shown their superiority in the fields of vision and language, such as high accuracy, high fidelity, and strong stability. Most existing methods are ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results