Attention based temporal filtering of sensory signals for data redundancy reduction

Sofoklis Kakouros, Okko Räsänen, Unto K. Laine

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

2 Citations (Scopus)

Abstract

Since modern computational devices are required to store and process increasing amounts of data generated from various sources, efficient algorithms for identification of significant information in the data are becoming essential. Sensory recordings are one example where automatic and continuous storing and processing of large amounts of data is needed. Therefore, algorithms that can alleviate the computational load of the devices and reduce their storage requirements by removing uninformative data are important. In this work we propose a method for data reduction based on theories of human attention. The method detects temporally salient events based on the context in which they occur and retains only those sections of the input signal. The algorithm is tested as a pre-processing stage in a weakly supervised keyword learning experiment where it is shown to significantly improve the quality of the codebooks used in the pattern discovery process.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
Pages3188-3192
Number of pages5
DOIs
Publication statusPublished - 18 Oct 2013
MoE publication typeA4 Conference publication
EventIEEE International Conference on Acoustics, Speech, and Signal Processing - Vancouver, Canada
Duration: 26 May 201331 May 2013
Conference number: 38

Conference

ConferenceIEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated titleICASSP
Country/TerritoryCanada
CityVancouver
Period26/05/201331/05/2013

Keywords

  • attention modeling
  • data compression
  • data redundancy reduction
  • machine learning

Fingerprint

Dive into the research topics of 'Attention based temporal filtering of sensory signals for data redundancy reduction'. Together they form a unique fingerprint.

Cite this