Search Results for author:
Found 2 papers, 1 papers with code
Indirectly Parameterized Concrete Autoencoders
Feature selection is a crucial task in settings where data is high-dimensional or acquiring the full set of features is costly.
End-to-End Whisper to Natural Speech Conversion using Modified Transformer Network
We introduce whisper-to-natural-speech conversion using sequence-to-sequence approach by proposing enhanced transformer architecture, which uses both parallel and non-parallel data.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
