4 papers
SPARCLE: SPeaker-aware Aligned Representations via Contrastive Language Embeddings
Priyam Mazumdar, Yurii Halychanskyi, Steven Guo +2
Recent advances in speech synthesis have shifted from phoneme representations to direct grapheme modeling. While phonemes address the one-to-many mapping between text and acoustics…
Training Next Generation AI Users and Developers at NCSA
Daniel S. Katz, Volodymyr Kindratenko, Olena Kindratenko +1
This article focuses on training work carried out in artificial intelligence (AI) at the National Center for Supercomputing Applications (NCSA) at the University of Illinois Urbana…
Self-Supervised Masked Digital Elevation Models Encoding for Low-Resource Downstream Tasks
Priyam Mazumdar, Aiman Soliman, Volodymyr Kindratenko +2
The lack of quality labeled data is one of the main bottlenecks for training Deep Learning models. As the task increases in complexity, there is a higher penalty for overfitting an…
Integrated dataset for air travel and reported Zika virus cases in Colombia (Data and Resources Paper)
Aiman Soliman, Priyam Mazumdar, Aaron Hoyle-Katz +2
This open-access dataset provides consistent records of air travel volumes between 205 airport catchments in Colombia and the associated number of reported human cases of Zika viru…