Improving faster-than-real-time human acoustic event detection by saliency-maximized audio visualization
- 1 March 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 2277-2280
Abstract
We propose a saliency-maximized audio spectrogram as a representation that lets human analysts quickly search for and detect events in audio recordings. By rendering target events as visually salient patterns, this representation minimizes the time and effort needed to examine a recording. In particular, we propose a transformation of a conventional spectrogram that maximizes the mutual information between the spectrograms of isolated target events and the estimated saliency of the overall visual representation. When subjects are shown spectrograms that are saliency-maximized, they perform significantly better in a 1/10-real-time acoustic event detection task.Keywords
This publication has 7 references indexed in Scilit:
- A Salience‐based Quality Metric for VisualizationComputer Graphics Forum, 2010
- Real-world acoustic event detectionPattern Recognition Letters, 2010
- Unleashing the killer corpus: experiences in creating the multi-everything AMI Meeting CorpusLanguage Resources and Evaluation, 2007
- Detection and Localization of Magazine Insertion Clicks in Various Environmental NoisesMilitary Psychology, 2007
- Modeling attention to salient proto-objectsNeural Networks, 2006
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- SpeechSkimmerACM Transactions on Computer-Human Interaction, 1997