Quality enhancement of compressed vibrotactile signals using recurrent neural networks and residual learning

Andreas Noll, Ayten Gurbuz, Basak Gulecyuz, Kai Cui, Eckehard Steinbach

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

We present a neural network-based compression artifact removal technique for vibrotactile signals. The proposed decoder-side quality enhancement approach is based on recurrent neural networks (RNNs) and the principle of residual learning. We use a total of 8 nonlinear RNN layers trained to first estimate the difference between the original and the compressed signal. The estimated difference signal is then added to the compressed signal, followed by further linear processing steps to construct the enhanced signal. With our approach, we are able to enhance signals at almost all compression ratios by up to 1:25 dB. For the signals in our data set, rougly 86% are enhanced in their quality. Through an ablation study, we show that every block of our network is functioning as intended and contributes to the compression artifact removal. Additionally, we show that the chosen network parameters maximize performance.

Original languageEnglish
Article number9428501
Pages (from-to)316-321
Number of pages6
JournalIEEE Transactions on Haptics
Volume14
Issue number2
DOIs
StatePublished - 1 Apr 2021

Keywords

  • Machine learning
  • Quality enhancement
  • RNN, residual learning
  • Tactile signal compression

Fingerprint

Dive into the research topics of 'Quality enhancement of compressed vibrotactile signals using recurrent neural networks and residual learning'. Together they form a unique fingerprint.

Cite this