Flexible and self-adaptive classification of received audio measurements in a network environment
AssigneeInternational Business Machines Corporation
InventorsMandis S. Beigi, Seraphin B. Calo, Dinesh C. Verma, Shiqiang Wang, David A. Wood
Life of this patent
Estimating the term…
Abstract
A domain description is received, by a processor, the domain description identifying a domain associated with a sensor input. The domain description is formatted according to a hierarchical naming structure. A training data set is selected from a plurality of training data sets based upon the received domain description and sensor input. A combination of a subset of classifiers for classifying the sensor input is selected from a set of classifiers based upon the selected training data set.
Claims20
A method comprising:
- receiving, by a processor, a domain description from an audio monitoring device, the domain description identifying a domain associated with a sensor input of the audio monitoring device, wherein the domain description is formatted according to a hierarchical naming structure;
- receiving the sensor input from the audio monitoring device, the sensor input including at least one audio sample monitored by the audio monitoring device in the domain;
- selecting a training data set from a plurality of training data sets based upon the received domain description and sensor input;
- determining a combination of a subset of classifiers for classifying the sensor input from a set of classifiers based upon the selected training data set, wherein the determining further includes determining a combination of a subset of audio feature extractors from a set of audio feature extractors and a subset of audio classifiers from a set of audio classifiers based upon the selected training data set;
- and
- sending an indication of the determined combination to the audio monitoring device, wherein the audio monitoring device is configured to monitor for audio signals within the domain using the determined combination of the subset of audio feature extractors and the subset of audio classifiers.
(canceled)
(canceled)
(canceled)
A computer usable program product comprising one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices, the stored program instructions comprising:
- program instructions to receive, by a processor, a domain description from an audio monitoring device, the domain description identifying a domain associated with a sensor input of the audio monitoring device, wherein the domain description is formatted according to a hierarchical naming structure;
- program instructions to receive the sensor input from the audio monitoring device, the sensor input including at least one audio sample monitored by the audio monitoring device in the domain;
- program instructions to select a training data set from a plurality of training data sets based upon the received domain description and sensor input;
- program instructions to determine a combination of a subset of classifiers for classifying the sensor input from a set of classifiers based upon the selected training data set, wherein the determining further includes determining a combination of a subset of audio feature extractors from a set of audio feature extractors and a subset of audio classifiers from a set of audio classifiers based upon the selected training data set;
- and
- program instructions to send an indication of the determined combination to the audio monitoring device, wherein the audio monitoring device is configured to monitor for audio signals within the domain using the determined combination of the subset of audio feature extractors and the subset of audio classifiers.
(canceled)
(canceled)
(canceled)
A computer system comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:
- program instructions to receive, by a processor, a domain description from an audio monitoring device, the domain description identifying a domain associated with a sensor input of the audio monitoring device, wherein the domain description is formatted according to a hierarchical naming structure;
- program instructions to receive the sensor input from the audio monitoring device, the sensor input including at least one audio sample monitored by the audio monitoring device in the domain;
- program instructions to select a training data set from a plurality of training data sets based upon the received domain description and sensor input;
- program instructions to determine a combination of a subset of classifiers for classifying the sensor input from a set of classifiers based upon the selected training data set, wherein the determining further includes determining a combination of a subset of audio feature extractors from a set of audio feature extractors and a subset of audio classifiers from a set of audio classifiers based upon the selected training data set;
- and
- program instructions to send an indication of the determined combination to the audio monitoring device, wherein the audio monitoring device is configured to monitor for audio signals within the domain using the determined combination of the subset of audio feature extractors and the subset of audio classifiers.
(canceled)
Dependencies are inferred from the claim text.