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

• Ground truth for auditory salience can be built up by thresholding polling data.
• The optimum threshold of the polling data is derived based on its statistical model.
• As the threshold increases, the equal error rate for salience detection decreases.
• We model salience detect process with a linear filter on perceptual loudness.
• The derived salience filter looks an onset detector rather than contrast detector.

Auditory salience describes how much a particular auditory event attracts human attention. Previous attempts at automatic detection of salient audio events have been hampered by the challenge of defining ground truth. In this paper ground truth for auditory salience is built up from annotations by human subjects of a large corpus of meeting room recordings. Following statistical purification of the data, an optimal auditory salience filter with linear discrimination is derived from the purified data. An automatic auditory salience detector based on optimal filtering of the Bark-frequency loudness performs with 32% equal error rate. Expanding the feature vector to include other common feature sets does not improve performance. Consistent with intuition, the optimal filter looks like an onset detector in the time domain.