Aural classification of impulsive-source active sonar echoes

Pitton, J.W.; Philips, Scott; Atlas, Les; Ballas, James A.; Brock, Derek; McClimens, Brian; Miller, Maxwell

doi:10.1121/1.4786679

Cited by 5 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Not only does this allow for correlating with the entire space, but it also removes any error induced by the MDS analysis. We also observe that the listener similarity matrix 8 is a perceptual equivalent to matrices used in kernel methods for regression and classification such as kernel-based PCA [ 1] and Support Vector Machines [ 12].…”

Section: B Kernel Matchingmentioning

confidence: 94%

“…Since the auditory system relies on time-frequency-like decomposition, and sonar echoes are transient in nature, we demonstrate this approach using features ofthe form (2) gh(x) = h(t, f)Sx (t, f) t,f where S, (t, f) is the envelope of the output of a PattersonHoldsworth auditory filter bank [10] and h(t, f) is a timefrequency weighting function. For this class of signal features, it can be shown that the optimal weighting function according to Equation 1 is…”

Section: New Feature Identificationmentioning

confidence: 99%

“…One common example is the radial basis kernel which takes the form features using kernel-based PCA or be used directly to classify signals using a Support Vector Machine. 1 K(x,y)= e-(5) This kernel is defined by distance measure d(x, y) between data vectors. In contrast, we have a set of numeric similarity measures obtained from human subjects rather than a functional distance measure.…”

Section: B Kernel Matchingmentioning

confidence: 99%

“…Their initial understanding of the sonar classification problem ranged from truly naive to detailed technical understanding of sonar signal processing. Previous experiments showed that all subjects were able to perform target/clutter discrimination significantly above chance [1].…”

Section: Introductionmentioning

confidence: 98%

See 3 more Smart Citations

Perceptual Feature Identification for Active Sonar Echoes

2006

Self Cite

View full text Add to dashboard Cite

This paper presents a novel method of using psychoacoustic information from human listening experiments to generate useful features for automated signal classification or regression. The design and analysis of a similarity experiment using active sonar transient echoes is summarized and two methods are presented for feature identification based on the results of the listening experiment. These methods not only identify novel features but also provide a visual insight into perceptually significant signal attributes. The approach presented is based on perceptual similarity measures collected during formal listening experiments but is applicable to any perceptual similarity experiment (e.g. visual).

show abstract

Section: B Kernel Matchingmentioning

confidence: 94%

Section: New Feature Identificationmentioning

confidence: 99%

Section: B Kernel Matchingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

See 2 more Smart Citations

Perceptual Feature Identification for Active Sonar Echoes

2006

Self Cite

View full text Add to dashboard Cite

show abstract

“…There is anecdotal evidence and mounting experimental evidence 3,4 to suggest that when auditioned ͑i.e., auralized or listened to͒ by a human operator explosive-source echoes from man-made metallic objects sound very different than similar echoes from naturally occurring objects. This paper describes the development of an automatic classifier for explosive-source active sonar based upon the specific aural cues or perceptual signal features employed in the human auditory system.…”

Section: Introductionmentioning

confidence: 98%

Perception-based automatic classification of impulsive-source active sonar echoes

Young

Hines

2007

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

Impulsive-source active sonar systems are often plagued by false alarm echoes resulting from the presence of naturally occurring clutter objects in the environment. Sonar performance could be improved by a technique for discriminating between echoes from true targets and echoes from clutter. Motivated by anecdotal evidence that target echoes sound very different than clutter echoes when auditioned by a human operator, this paper describes the implementation of an automatic classifier for impulsive-source active sonar echoes that is based on perceptual signal features that have been previously identified in the musical acoustics literature as underlying timbre. Perceptual signal features found in this paper to be particularly useful to the problem of active sonar classification include: the centroid and peak value of the perceptual loudness function, as well as several features based on subband attack and decay times. This paper uses subsets of these perceptual signal features to train and test an automatic classifier capable of discriminating between target and clutter echoes with an equal error rate of roughly 10%; the area under the receiver operating characteristic curve corresponding to this classifier is found to be 0.975.

show abstract

Similarity-Based Perceptual Feature Identification for Active Sonar Signal Classification

Philips

Pitton

2008

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

In many aural (acoustic) signal processing tasks, humans are known to perform better than automated classification systems. For such applications, it may be beneficial to identify how humans relate different sounds to one another and incorporate that information into an automatic classification system. This paper presents a method for using psychoacoustic information from a human listening experiment to generate a novel kernel function that can be used to improve automated signal classification. We have conducted a similarity-based listening experiment on a series of impulsive-source sonar echoes. In this experiment, humans were asked to rate perceived similarity between pairings of target and clutter echoes. These ratings combine to form a similarity matrix that reflects the underlying distance measure humans use when judging these echoes. This similarity matrix is a perceptual equivalent to the similarity matrix used in modern kernel methods used in automatic classification systems (e.g. Support Vector Machine). By fitting an appropriate distance metric to the results of the perceptual experiment we can identify novel, perceptually-inspired, kernel functions. This paper presents a series of new approaches for the identification of a perceptual kernel function. We then compare the classification performance between these perceptual kernels and more standard kernel functions.

show abstract

Aural classification of impulsive-source active sonar echoes

Cited by 5 publications

References 0 publications

Perceptual Feature Identification for Active Sonar Echoes

Perceptual Feature Identification for Active Sonar Echoes

Perception-based automatic classification of impulsive-source active sonar echoes

Similarity-Based Perceptual Feature Identification for Active Sonar Signal Classification

Contact Info

Product

Resources

About