A comprehensive study of batch construction strategies for recurrent neural networks in MXNet

5 May 2017

Papers citing "A comprehensive study of batch construction strategies for recurrent neural networks in MXNet"

2 / 2 papers shown

Title
Training and Inference Efficiency of Encoder-Decoder Speech Models Piotr .Zelasko Kunal Dhawan Daniel Galvez Krishna C. Puvvada Ankita Pasad Nithin Rao Koluguri Ke Hu Vitaly Lavrukhin Jagadeesh Balam Boris Ginsburg 41 0 0 07 Mar 2025
On Batching Variable Size Inputs for Training End-to-End Speech Enhancement Systems Philippe Gonzalez T. S. Alstrøm Tobias May 24 9 0 25 Jan 2023