Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Iliescu, Dan Andrei"'
We address the problem of human-in-the-loop control for generating prosody in the context of text-to-speech synthesis. Controlling prosody is challenging because existing generative models lack an efficient interface through which users can modify th
Externí odkaz:
http://arxiv.org/abs/2303.09446
Many real-world datasets can be divided into groups according to certain salient features (e.g. grouping images by subject, grouping text by font, etc.). Often, machine learning tasks require that these features be represented separately from those m
Externí odkaz:
http://arxiv.org/abs/2202.07285
The choice of a loss function is an important factor when training neural networks for image restoration problems, such as single image super resolution. The loss function should encourage natural and perceptually pleasing results. A popular choice f
Externí odkaz:
http://arxiv.org/abs/2103.14616
Autor:
Webb, Andrew M., Reynolds, Charles, Chen, Wenlin, Reeve, Henry, Iliescu, Dan-Andrei, Lujan, Mikel, Brown, Gavin
End-to-End training (E2E) is becoming more and more popular to train complex Deep Network architectures. An interesting question is whether this trend will continue-are there any clear failure cases for E2E training? We study this question in depth,
Externí odkaz:
http://arxiv.org/abs/1902.04422
We address the problem of human-in-the-loop control for generating highly-structured data. This task is challenging because existing generative models lack an efficient interface through which users can modify the output. Users have the option to eit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dace1155b349413f921944f3ee92ad98
http://arxiv.org/abs/2303.09446
http://arxiv.org/abs/2303.09446