English

Investigations on End-to-End Audiovisual Fusion

Computer Vision and Pattern Recognition 2018-05-01 v1 Neural and Evolutionary Computing

Abstract

Audiovisual speech recognition (AVSR) is a method to alleviate the adverse effect of noise in the acoustic signal. Leveraging recent developments in deep neural network-based speech recognition, we present an AVSR neural network architecture which is trained end-to-end, without the need to separately model the process of decision fusion as in conventional (e.g. HMM-based) systems. The fusion system outperforms single-modality recognition under all noise conditions. Investigation of the saliency of the input features shows that the neural network automatically adapts to different noise levels in the acoustic signal.

Keywords

Cite

@article{arxiv.1804.11127,
  title  = {Investigations on End-to-End Audiovisual Fusion},
  author = {Michael Wand and Ngoc Thang Vu and Juergen Schmidhuber},
  journal= {arXiv preprint arXiv:1804.11127},
  year   = {2018}
}

Comments

Published at ICASSP 2018