System and method for tagging signals of interest in time variant data
Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for tagging a known signal of interest. Initially, the system classifies the data from an input signal using a short-term classifier, wherein there are at least two classifications available, a first classification of the data as having no identified outputs and a second classification of the data as at least one potential signal of interest, wherein the short-term classifier also bypasses data that is known to be of no interest. After the short-term classifier classifies the inputs, it collapses the input data that is classified as having no identified outputs. This allows the short-term classifier to create time-variant data. Finally, the system will tag a known signal of interest in the time-variant data that was classified as having at least one potential signal of interest. Therefore, a system for tagging a known signal of interest is described.
1. A method comprising:
classifying, via a processor, a first data from input signal data as having no signal of interest, to yield a first classification;
classifying a second data from the input signal data as having a potential signal of interest, to yield a second classification;
collapsing a portion of the input signal data, based on the first classification, to yield a third data; and
tagging a segment of the third data, based on the second classification, as having a known signal of interest.
2. The method of claim 1 , wherein the collapsing further comprises one of ignoring a portion of the input signal data and removing a portion of the input signal data.
3. The method of claim 1 , wherein having no signal of interest comprises one of having no identified outputs and having a known signal of no interest.
4. The method of claim 3 , wherein the known signal of no interest comprises one of a door slam, a paper rattle, air conditioning, an airplane engine, a dial tone, and a speaker of no interest.
5. The method of claim 1 , wherein the third data is a time-variant data.
6. The method of claim 1 , wherein the potential signal of interest is a signal with no output for a predetermined amount of time.
7. The method of claim 1 , wherein the third data is smoothed prior to the tagging but after the collapsing.
8. The method of claim 1 , wherein the tagging further comprises determining a number of matches identified within the third data based on known signals of interest.
9. A system comprising:
a processor; and
a computer-readable storage device having instructions stored which when executed by the processor, cause the processor to perform operations comprising:
classifying a first data from input signal data as having no signal of interest, to yield a first classification;
classifying a second data from the input signal data as having a potential signal of interest, to yield a second classification;
collapsing a portion of the input signal data, based on the first classification, to yield a third data; and
tagging a segment of the third data, based on the second classification, as having a known signal of interest.
10. The system of claim 9 , wherein the collapsing further comprises one of ignoring a portion of the input signal data and removing a portion of the input signal data.
11. The system of claim 9 , wherein having no signal of interest comprises one of having no identified outputs and having a known signal of no interest.
12. The system of claim 9 , wherein the third data is a time-variant data.
13. The system of claim 9 , wherein the third data is smoothed prior to the tagging but after the collapsing.
14. The system of claim 9 , wherein the tagging further comprises determining a number of matches identified within the third data based on known signals of interest.
15. A computer-readable storage device having instructions stored which, when executed by a processor, cause the processor to perform operations comprising:
classifying a first data from input signal data as having no signal of interest, to yield a first classification;
classifying a second data from the input signal data as having a potential signal of interest, to yield a second classification;
collapsing a portion of the input signal data, based on the first classification, to yield a third data; and
tagging a segment of the third data, based on the second classification, as having a known signal of interest.
16. The computer-readable storage device of claim 15 , wherein the collapsing further comprises one of ignoring a portion of the input signal data and removing a portion of the input signal data.
17. The computer-readable storage device of claim 15 , wherein having no signal of interest comprises one of having no identified outputs and having a known signal of no interest.
18. The computer-readable storage device of claim 17 , wherein the known signal of no interest comprises one of a door slam, a paper rattle, air conditioning, an airplane engine, a dial tone, and a speaker of no interest.
19. The computer-readable storage device of claim 15 , wherein the third data is a time-variant data.
20. The computer-readable storage device of claim 15 , wherein the potential signal of interest is a signal with no output for a predetermined amount of time.