no code implementations • 1 Jun 2020 • Kazi Nazmul Haque, Rajib Rana, Björn W. Schuller
Hence, with the extensive experimental results, we have demonstrated that by harnessing the power of the high-fidelity audio generation, the proposed GAAE model can learn powerful representation from unlabelled dataset leveraging a fewer percentage of labelled data as supervision/guidance.
no code implementations • 5 Mar 2020 • Kazi Nazmul Haque, Rajib Rana, John H. L. Hansen, Björn Schuller
However, the model can become redundant if it is intended for a specific task.
no code implementations • 18 Apr 2019 • Kazi Nazmul Haque, Siddique Latif, Rajib Rana
Learning disentangled representation from any unlabelled data is a non-trivial problem.
no code implementations • 16 Jan 2018 • Kazi Nazmul Haque, Mohammad Abu Yousuf, Rajib Rana
In the proposed model, the encoder reads an image and catches the abstraction of that image in a vector, where decoder takes that vector as well as the corrupted image to reconstruct a clean image.