S
Saira Karim
Researcher at National University of Computer and Emerging Sciences
Publications - 10
Citations - 35
Saira Karim is an academic researcher from National University of Computer and Emerging Sciences. The author has contributed to research in topics: Computer science & Complete bipartite graph. The author has an hindex of 1, co-authored 5 publications receiving 10 citations.
Papers
More filters
Journal ArticleDOI
Generative adversarial networks for speech processing: A review
Aamir Wali,Zareen Alamgir,Saira Karim,Ather Fawaz,Mubariz Barkat Ali,Muhammad Adan,Malik Mujtaba +6 more
TL;DR: A comprehensive review of the novel and emerging GAN-based speech frameworks and algorithms that have revolutionized speech processing and categorized speech GANs based on application areas: speech synthesis, speech enhancement & conversion, and data augmentation in automatic speech recognition and emotion speech recognition systems.
Journal ArticleDOI
Generating bracelets with fixed content
TL;DR: The algorithm can be applied to efficiently list all non-isomorphic unicyclic graphs with n vertices to generate bracelets with fixed content in constant amortized time.
Journal ArticleDOI
Federated recommenders: methods, challenges and future
TL;DR: This research summarizes the current limitations, highlights the areas that need improvements, and presents future paths for the development of robust federated recommenders that can handle the challenges of federated learning and, at the same time, generate high-quality recommendations.
Book ChapterDOI
On fast enumeration of pseudo bicliques
TL;DR: This paper introduces various enhancements to their algorithm based on the structure of pseudo bicliques and underlying bipartite graph, to show that these improvements significantly reduce the running time of the algorithm.
Mining Dense Structures by Enumerating Weighted and Multi-level Pseudo-Bicliques
TL;DR: The weighted density based model of pseudo-biclique is considered, which better fits the real-world situations and give much more flexibility to researchers and an algorithm based on reverse search to generate all weighted pseudo- bicliques in a given graph is proposed.