Lip reading with Hahn Convolutional Neural Networks

作者：

Highlights：

• This work proposes a new architecture called Hahn Convolutional Neural Network.

• The complexity is reduced enormously by minimizing number of parameters and layers.

• The experiments are conducted on AVLetters, OuluVS2 and BBC LRW datasets.

• The classification results are 59,23% on AVLetters, 93,72% on OuluVS2, 46,6% on BBC LRW.

摘要

•This work proposes a new architecture called Hahn Convolutional Neural Network.•The complexity is reduced enormously by minimizing number of parameters and layers.•The experiments are conducted on AVLetters, OuluVS2 and BBC LRW datasets.•The classification results are 59,23% on AVLetters, 93,72% on OuluVS2, 46,6% on BBC LRW.

论文关键词：Visual speech recognition,Lipreading,Laryngectomy,Hahn moments,Convolutional Neural Networks

论文评审过程：Received 23 December 2017, Revised 8 February 2019, Accepted 22 April 2019, Available online 29 April 2019, Version of Record 14 June 2019.

论文官网地址：https://doi.org/10.1016/j.imavis.2019.04.010