Introduction and Review of Auditory Saliency
That was clearly salient. But that sound was easy. What, in general, makes a sound salient? How do we model and predict saliency? Saliency is just the first part of auditory scene analysis. A sound must be salient, in some fashion, before we can separate it out into its own sound object.
Visual saliency is well established, due to a number of eye-tracking studies that show what people look at first. The visual saliency models have been translated, with more or less success, into auditory models. But there is definitely a lack of hard data to drive these auditory saliency models. At this Friday’s seminar I’ll review the literature of auditory saliency, play lots of sounds, and lead a discussion about what makes a sound salient, and how we might measure it. This is based on material I presented at an Interspeech tutorial last month.
Who: Malcolm Slaney (Google and Stanford)
What: Auditory Saliency
When: Friday October 7th at 10:30AM
Where: CCRMA Seminar Room
Why: Because we want to know what the brain thinks is important
Bring your favorite auditory saliency detector to CCRMA on Friday morning.