H03H2021/0034

Systems and methods for parallelizing and pipelining a tunable blind source separation filter

A method of processing a plurality of time-varying signals received at a sensor communicatively coupled to a signal data processor to identify at least one parameter of at least one of the plurality of time-varying signals is provided. The method includes receiving, at a plurality of blind source separation (BSS) modules of the signal data processor, signals derived from the plurality of time-varying signals, each BSS module of the plurality of BSS modules including a filtering subsystem having a pipelined architecture and a parallelized architecture. The method also includes generating a plurality of blind source separated signals, and transmitting at least one pulse descriptor word (PDW) parameter vector signal to a computing device of the signal data processor. The method further includes identifying the at least one parameter from the at least one PDW parameter vector signal, and outputting the at least one parameter from the signal data processor.

SYSTEMS AND METHODS FOR PARALLELIZING AND PIPELINING A TUNABLE BLIND SOURCE SEPARATION FILTER
20180076835 · 2018-03-15 ·

A method of processing a plurality of time-varying signals received at a sensor communicatively coupled to a signal data processor to identify at least one parameter of at least one of the plurality of time-varying signals is provided. The method includes receiving, at a plurality of blind source separation (BSS) modules of the signal data processor, signals derived from the plurality of time-varying signals, each BSS module of the plurality of BSS modules including a filtering subsystem having a pipelined architecture and a parallelized architecture. The method also includes generating a plurality of blind source separated signals, and transmitting at least one pulse descriptor word (PDW) parameter vector signal to a computing device of the signal data processor. The method further includes identifying the at least one parameter from the at least one PDW parameter vector signal, and outputting the at least one parameter from the signal data processor.

COGNITIVE SIGNAL PROCESSOR FOR SIMULTANEOUS DENOISING AND BLIND SOURCE SEPARATION
20180076795 · 2018-03-15 ·

Described is a cognitive signal processor for signal denoising and blind source separation. During operation, the cognitive signal processor receives a mixture signal that comprises a plurality of source signals. A denoised reservoir state signal is generated by mapping the mixture signal to a dynamic reservoir to perform signal denoising. At least one separated source signal is identified by adaptively filtering the denoised reservoir state signal.

SOUND SOURCE SEPARATION APPARATUS
20180040327 · 2018-02-08 ·

A sound source separation apparatus includes: a separation-matrix processor that transforms a plurality of observation signals corresponding to sounds being propagated from a plurality of sound sources into a frequency-domain signal group the separation-matrix processor updating a separation matrix based on the frequency-domain signal group and transforming the updated separation matrix into time-series filter coefficients to output; a filter-coefficient transformer that partially removes non-causal components from the filter coefficients to transform the filter coefficients, and a separator that supplies the filter coefficients to a filter group, the separator generating a plurality of separation signals separated from the plurality of observation signals corresponding to the separation matrix.

Methods of blind source separation filter resource management
09866422 · 2018-01-09 · ·

Systems and methods that solve the problem of scheduling the fixed filter resources of a blind source separation subsystem by choosing in real time the center frequency and bandwidth of each filter in such a way as to allow new and existing signals to be separated out in consistent channels, with as few missed signals as possible given the filter resources available. The proposed method comprises an algorithm that uses a periodic time/frequency covering map to set the center frequency and bandwidth of each filter over all time by acquiring energy measurements from the filtering subsystem using existing filter settings and continuously adaptively updating those settings while maintaining optimal coverage in time and frequency.

Automatic signal composition for media conferences

Implementations for compositing two input signals to form a higher quality signal are described. A first input signal is received from a first input device and a second input signal is received from a second input device. The first input signal and the second input signal are combined into a composite input signal. It is then determined that the composite input signal has a higher quality than either the first input signal or the second input signal individually. Based on that determination, the composite input signal is selected for use by the media conferencing service as part of a media conference.