Search Results for author: Geng-Shen Fu

Found 3 papers, 0 papers with code

Max-Pooling Loss Training of Long Short-Term Memory Networks for Small-Footprint Keyword Spotting

no code implementations5 May 2017 Ming Sun, Anirudh Raju, George Tucker, Sankaran Panchapagesan, Geng-Shen Fu, Arindam Mandal, Spyros Matsoukas, Nikko Strom, Shiv Vitaladevuni

Finally, the max-pooling loss trained LSTM initialized with a cross-entropy pre-trained network shows the best performance, which yields $67. 6\%$ relative reduction compared to baseline feed-forward DNN in Area Under the Curve (AUC) measure.

Small-Footprint Keyword Spotting

Independent Component Analysis by Entropy Maximization with Kernels

no code implementations22 Oct 2016 Zois Boukouvalas, Rami Mowakeaa, Geng-Shen Fu, Tulay Adali

ICA algorithms cast in the ML framework often deviate from its theoretical optimality properties due to poor estimation of the source PDF.

Independent Vector Analysis: Identification Conditions and Performance Bounds

no code implementations29 Mar 2013 Matthew Anderson, Geng-Shen Fu, Ronald Phlypo, Tülay Adalı

Thus, we provide the additional conditions for when the arbitrary ordering of the sources within each dataset is common.

Cannot find the paper you are looking for? You can Submit a new open access paper.