Siemens Corporate Research, Inc.

Siemens Enterprise Communications Gmbh & Co. Kg

University System of Maryland

Siemens Aktiengesellschaft

Siemens Corporation Research, Inc.

Siemens Medical Solutions Usa, Inc.

Insurance Services Office, Inc.

Siemens Corporation

Siemens Enterprise Communications, Inc.

Radu Victor Balan

Justinian Rosca

Octavian Sarca

Scott Rickard

Heiko Claussen

Chih-Wei Huang

Yenming Mark Lai

Dorin Comaniciu

Eghart Fischer

Maneesh Kumar Singh

Sandra Sudarsky

Volkmar Hamacher

Michael T Loiacono

Alexander N Jourjine

Dongmian Zou

Liang Hong

Christophe Beaugeant

Ning Ping Fan

Scott Thurston Rickard, Jr

Peter Casazza

Dan Edidin

Eghard Fischer

Michael Loiacono

Computer vision systems and methods for optimized computer vision using deep neural networks and Lipschitz analysis are provided. The system receives signals or data related to visual imagery, such as data from a camera, and feed-forwards the signals/data through the multiple layers of a convolutional neural network (CNN). At one or more layers of the CNN, the system determines at least one Bessel bound of that layer. The system then determines a Lipschitz bound based on the one or more Bessel bounds. The system then applies the Lipschitz bound to the signals. Once the Lipschitz bound is applied, the system can feed-forward the signals to other processes of the layer or to a further layer.

Systems and methods for optimized computer vision using deep neural networks and Litpschitz analysis

Placement of microphones and design of filters in a microphone network are solved simultaneously. Using filterbanks with multiple sub-channels for each microphone, the design of the filter response is solved simultaneously with placement. By using an objective function that penalizes the number of sub-channels in any solution, only some of many possible sub-channels and corresponding microphones and filters are selected while also solving for the filter responses for the selected sub-channels. For a given target location, the location of the microphones and the filter responses to beamform are optimized.

Simultaneous solution for sparsity and filter responses for a microphone network

Systems and methods are provided to determine a subset of D microphones in a set of N microphones on a perimeter of a space to monitor a target location. The space is divided into L interference locations. An equation is solved to determine microphone weights for the N microphones by minimizing the maximum gain for signals related to the target location and interference locations, further optimized over an lpenalty by applying a Lagrange multiplier to an lnorm of the microphone weights in a manner that determines a set of D non-zero microphones weights and a set of (N-D) microphone weights that are zero or close to zero. Microphone weights are determined for at least 2 different frequencies.

Broadband sensor location selection using convex optimization in very large scale arrays

Systems and methods are provided to create an acoustic map of a space containing multiple acoustic sources. Source localization and separation takes place by sampling an ultra large microphone array containing over 1020 microphones. The space is divided into a plurality of masks, wherein each masks represents a pass region and a complementary rejection region. Each mask is associated with a subset of microphones and beamforming filters that maximize a gain for signals coming from the pass region of the mask and minimizes the gain for signals from the complementary region according to an optimization criterion. The optimization criterion may be a minimization of a performance function for the beamforming filters. The performance function is preferably a convex function. A processor provides a scan applying the plurality of masks to locate a target source. Processor based systems to perform the optimization are also provided.

Method and apparatus for acoustic area monitoring by exploiting ultra large scale arrays of microphones

A method for measuring degree of packet congestion on a channel of a packet communication network. The method includes: during a training mode, generating an mathematical relationship between the degree of packet congestion on the channel and a plurality of measurable features of the network over a plurality of network conditions; and, during a subsequent normal operating mode, periodically measuring the plurality of measurable features and applying the generated mathematical relationship to such periodically measured plurality of measurable features to determine actual degree of congestion on the channel; and comparing the actual degree of congestion on the channel with a predetermined channel congestion threshold level. The degree of packet congestion on the channel is saturation level. The measurable features include: time delay between transmission starts and terminations of the previously transmitted packet; the fraction of time the channel is busy; and, average number of packet transmission retries.

Method for congestion detection in packet transmission networks

A method for controlling packet flow in a packet transmission network. The method includes determining a parameter representative of packet congestion on the network, and adjusting a flow of packets onto the network in accordance with such parameter. The adjusting is a function of the time history of the parameter and the time average of such parameter relative to predetermined threshold levels. The adjusting selects one of a plurality of states, transitions between the states being a function of the time history of the parameter and the time average of such parameter relative to predetermined threshold levels.

Method and apparatus to inspect wireless traffic and mitigate packet elimination for wireless saturation avoidance

A method for estimating packet collisions within a wireless network, comprising: for each transmit packet an Access Point (AP) of the network records statistics transmission information; based on this statistical information the AP computes: Total number of slot times generated during this transmission, n; Total number of deferrals, m; and Total number of unsuccessful transmissions, Q s; and using a sequence (m,n,Q) of statistics for each access category (AC), the AP computes the probability of collision for unsuccessful packets, p.

Method and apparatus for estimating collision probability in a wireless network

A system and method for non-square blind source separation (BSS) under coherent noise. The system and method for non-square BSS estimates the mixing parameters of a mixed source signal and filters the estimated mixing parameters so that output noise is reduced and the mixed source signal is separated from the noise. The filtering is accomplished by a linear filter that performs a beamforming for reducing the noise and another linear filter that solves a source separation problem by selecting time-frequency points where, according to a W-disjoint orthogonality assumption, only one source is active.

System and method for non-square blind source separation under coherent noise by beamforming and time-frequency masking

A system and method for nonlinear signal enhancement is provided. The method comprises: performing a linear transformation on a measured signal comprising a source component and a noise component; determining a modulus of the linear transformed signal; estimating a noise-free part of the linear transformed signal; and reconstructing the source component of the measured signal using the noise-free part of the linear transformed signal.

System and method for nonlinear signal enhancement that bypasses a noisy phase of a signal

A method is presented for eliminating an unwanted signal (e.g., background music, interference, etc.) from a mixture of a desired signal and the unwanted signal via time-frequency masking. Given a mixture of the desired signal and the unwanted signal, the goal of the present invention is to eliminate or at least reduce the effects of the unwanted signal to obtain an estimate of the desired signal.

Method for eliminating an unwanted signal from a mixture via time-frequency masking

An adaptive differential microphone array method comprises receiving a signal, estimating a measured signal spectral covariance matrix of the signal, and estimating a direction of arrival of the signal based on the measured signal spectral covariance matrix of the signal. The method further comprises determining a fractional delay, and applying a differential microphone array filter to the signal based on the direction of arrival and the fractional delay.

System and method for adaptive multi-sensor arrays

The present invention is generally directed to a system and method for enhancing speech using a multi-channel noise filtering process that is based on psychoacoustic masking effects. A speech enhancement/noise reduction scheme according to the present invention is designed to satisfy the psychoacoustic masking principle and to minimize the signal total distortion by exploiting multiple microphone signals to enhance the useful speech signal at reduced level of artifacts.

Multi-channel speech enhancement system and method based on psychoacoustic masking effects

A virtual environment system includes an acoustic localizer for detecting the location of sound sources in a local environment, a user data I/O device, a remote data I/O device in a remote world, and a system controller in data communication with the acoustic localizer, user data I/O device and remote data I/O device. Control of the remote data I/O device within the remote world is commanded by the system controller in response to movements of a user as detected by the acoustic localizer, and data acquired from the remote world by the remote data I/O device is transmitted to the user.

System and method for remotely experiencing a virtual environment

A multichannel source activity detection system, e.g., a voice activity detection (VAD) system, and method that exploits spatial localization of a target audio source is provided. The method includes the steps of receiving a mixed sound signal by at least two microphones; Fast Fourier transforming each received mixed sound signal into the frequency domain; filtering the transformed signals to output a signal corresponding to a spatial signature of a source; summing an absolute value squared of the filtered signal over a predetermined range of frequencies; and comparing the sum to a threshold to determine if a voice is present. Additionally, the filtering step includes multiplying the transformed signals by an inverse of a noise spectral power matrix, a vector of channel transfer function ratios, and a source signal spectral power.

Growing community of inventors

Levittown, PA, United States of America

Radu Victor Balan