Search Results for author:
Found 1 papers, 0 papers with code
Orthogonality Constrained Multi-Head Attention For Keyword Spotting
Augmenting regularization terms which penalize positional and contextual non-orthogonality between the attention heads encourages to output different representations from separate subsequences, which in turn enables leveraging structured information without explicit sequence models such as hidden Markov models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
