Adaptive blind source separator for ultra-wide bandwidth signal tracking
Described is a system for adaptive blind source separation. A time-series of data points from one or more mixtures of source signals is continuously passed through adaptable filters, where each filter has a corresponding output signal. An error of each output signal is determined, and a filter state of each filter is determined using the error signals. A set of filter center frequencies are adapted using the set of error signals and the filter states, resulting in new filter center frequencies. The set of filter center frequencies are updated with the new filter center frequencies. Finally, separated source signals are extracted from the mixture of signals.
1. A system for blind source separation, the system comprising:
one or more processors and a non-transitory computer-readable medium having executable instructions encoded thereon such that when executed, the one or more processors perform operations of:
continuously passing a time-series of data points from one or more mixtures of source signals through a plurality of adaptable filters having center frequencies, resulting in a plurality of output signals, each filter in the plurality of adaptable filters having a corresponding output signal;
determining an error of each output signal, resulting in a set of error signals;
determining a filter state of each filter using the error signals, resulting in a set of filter states;
adapting a set of filter center frequencies with a filter center frequency adapter by receiving and using both the set of error signals and the set of filter states, resulting in new filter center frequencies;
updating the set of filter center frequencies with the new filter center frequencies; and
extracting separated source signals from the mixture of signals.
2. The system as set forth in claim 1 , wherein the plurality of filters are low-order adaptable infinite impulse (IIR) filters.
3. The system as set forth in claim 1 , wherein the error is a negative power of the output signal, and wherein the separated source signals are extracted by minimizing the negative power of each filter's output signal.
4. The system as set forth in claim 1 , wherein, as the one or more mixtures of source signals is passed through each filter, each filter adapts such that its filter center frequency converges on a filter center frequency of a separated source signal.
5. The system as set forth in claim 1 , wherein the filter center frequency adapter prevents more than one filter from extracting any given source signal at the same time.
6. The system as set forth in claim 1 , wherein the filter center frequency adapter integrates a plurality of adaptation methods that operate together or alone to select new filter center frequencies, wherein an adaptation method in the plurality of adaptation methods is selected based on a filter's state.
7. A computer program product for blind source separation, the computer program product comprising:
a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions by one or more processors, the one or more processors perform operations of:
continuously passing a time-series of data points from one or more mixtures of source signals through a plurality of adaptable filters having center frequencies, resulting in a plurality of output signals, each filter in the plurality of adaptable filters having a corresponding output signal;
determining an error of each output signal, resulting in a set of error signals;
determining a filter state of each filter using the error signals, resulting in a set of filter states;
adapting a set of filter center frequencies with a filter center frequency adapter by receiving and using both the set of error signals and the set of filter states, resulting in new filter center frequencies;
updating the set of filter center frequencies with the new filter center frequencies; and
extracting separated source signals from the mixture of signals.
8. The computer program product as set forth in claim 7 , wherein the plurality of filters are low-order adaptable infinite impulse (IIR) filters.
9. The computer program product as set forth in claim 7 , wherein the error is a negative power of the output signal, and wherein the separated source signals are extracted by minimizing the negative power of each filter's output signal.
10. The computer program product as set forth in claim 7 , wherein, as the one or more mixtures of source signals is passed through each filter, each filter adapts such that its filter center frequency converges on a filter center frequency of a separated source signal.
11. The computer program product as set forth in claim 7 , wherein the filter center frequency adapter prevents more than one filter from extracting any given source signal at the same time.
12. The computer program product as set forth in claim 7 , wherein the filter center frequency adapter integrates a plurality of adaptation methods that operate together or alone to select new filter center frequencies, wherein an adaptation method in the plurality of adaptation methods is selected based on a filter's state.
13. A computer implemented method for blind source separation, the method comprising an act of:
causing one or more processors to execute instructions encoded on a non-transitory computer-readable medium, such that upon execution, the one or more processors perform operations of:
continuously passing a time-series of data points from one or more mixtures of source signals through a plurality of adaptable filters having center frequencies, resulting in a plurality of output signals, each filter in the plurality of adaptable filters having a corresponding output signal;
determining an error of each output signal, resulting in a set of error signals;
determining a filter state of each filter using the error signals, resulting in a set of filter states;
adapting a set of filter center frequencies with a filter center frequency adapter by receiving and using both the set of error signals and the set of filter states, resulting in new filter center frequencies;
updating the set of filter center frequencies with the new filter center frequencies; and
extracting separated source signals from the mixture of signals.
14. The method as set forth in claim 13 , wherein the plurality of filters are low-order adaptable infinite impulse (IIR) filters.
15. The method as set forth in claim 13 , wherein the error is a negative power of the output signal, and wherein the separated source signals are extracted by minimizing the negative power of each filter's output signal.
16. The method as set forth in claim 13 , wherein, as the one or more mixtures of source signals is passed through each filter, each filter adapts such that its filter center frequency converges on a filter center frequency of a separated source signal.
17. The method as set forth in claim 13 , wherein the filter center frequency adapter prevents more than one filter from extracting any given source signal at the same time.
18. The method as set forth in claim 13 , wherein the filter center frequency adapter integrates a plurality of adaptation methods that operate together or alone to select new filter center frequencies, wherein an adaptation method in the plurality of adaptation methods is selected based on a filter's state.