Automatic detection of auditory salience with optimized linear filters derived from human annotation

Auditory salience using natural soundscapes

“…19 The current dataset supports this intuitive notion. Figure 5(a) (inset) shows a significant increase in loudness preceding an event, calculated as the average loudness within 0.5 s before an event minus the average loudness between 2.0 and 1.5 s before the event [tð232Þ ¼ 11:6; p ( 0:001].…”

“…The first comparison uses the Kayser et al model 15 which calculates salience using a center-surround mechanism based on models of visual salience. The second is a model by Kim et al, 19 which calculates salient periods using a linear salience filter and linear discriminant analysis on loudness. The third is a model by Kaya et al, 18 which detects deviants in acoustic features using a predictive tracking model using a Kalman filter.…”

“…A complementary approach favored in other studies used annotation where listeners are asked to mark timing of salient events in a continuous recording. 19 This paradigm puts less emphasis on a choice of events determined by an experimenter, and adopts a more stimulusdriven approach that polls responses across subjects to determine salience. Still, this approach presents its own limitation in terms of controlling top-down and cognitive factors since listeners are presented with a single scene whose context might bias their judgment of stimulus-driven salience.…”

“…15,17,18 A few studies incorporated more rich natural scenes using recordings from the BU Radio News Corpus 23 and the AMI Corpus. 19 Still, both of the latter databases consist of scenes with relatively homogeneous compositions, both in terms of audio class (mostly speech interspersed with other sounds) and density (mostly sparse with rare instances of overlapping sound objects). The lack of a diverse and realistic selection of natural soundscapes in the literature results in a narrow view of what drives salience in audition.…”

“…Salience judgments are determined by the scenes themselves with no prearranged placement of specific events or salience ground truth. Moreover, employing two competing scenes in a dichotic setting disperses effects of top-down attention and allows salient events to attract listeners' attention in a stimulus-driven fashion; hence expanding on the previously used annotation paradigm used by Kim et al 19 Still, studying salience using these sustained natural scenes comes with many limitations and challenges. First, it is impossible to fully nullify the effects of voluntary attention in this paradigm.…”