Abstract: A system and method for analyzing a customer load and/or generation profile in order to disaggregate the customer load and/or generation profile is provided. The analysis of the customer load and/or customer generation profile may thereby determine the one or more devices that are operating and that contribute to the customer load and/or generation profile. In this way, the system and method may automatically analyze the customer load and/or generation profile in order to determine the one or more devices that contribute to the load and/or generation profile.

Abstract: Systems and methods consistent with the present invention allow an energy consumption index to be generated from DR response data and influencer data. The energy consumption index may indicate the energy consumption of a consumer before receiving a DR signal, the change in the consumption after the consumer receives a DR signal, and the consumer's propensity to respond to a DR signal. Systems and methods consistent with the present invention also allow energy providers to monitor, forecast, and plan for changes in consumer demand for energy. Various energy planning tools may facilitate an energy provider's ability to monitor, forecast, and plan for such changes.

Abstract: The invention concerns a method for determining a calibration value indicating the extent of loss of calibration of a group of three or more sensors in a sensor network, the method involving receiving a plurality of data values captured over a period of time by each of the sensors, determining by a processing unit (404) at least one correlation value associated with each sensor, each correlation value corresponding to the correlation between the data values captured by the associated sensor and the data values captured by at least one other sensor; extracting by a high pass filter (410) a noise component of the correlation values and outputting the calibration value determined based on the difference between the noise component and a reference noise value.

Abstract: Systems and methods consistent with the present invention allow an energy consumption index to be generated from DR response data and influencer data. The energy consumption index may indicate the energy consumption of a consumer before receiving a DR signal, the change in the consumption after the consumer receives a DR signal, and the consumer's propensity to respond to a DR signal. Systems and methods consistent with the present invention also allow energy providers to monitor, forecast, and plan for changes in consumer demand for energy. Various energy planning tools may facilitate an energy provider's ability to monitor, forecast, and plan for such changes.

Abstract: A system and method for analyzing a customer load and/or generation profile in order to disaggregate the customer load and/or generation profile is provided. The analysis of the customer load and/or customer generation profile may thereby determine the one or more devices that are operating and that contribute to the customer load and/or generation profile. In this way, the system and method may automatically analyze the customer load and/or generation profile in order to determine the one or more devices that contribute to the load and/or generation profile.

Abstract: The invention concerns a method for determining a calibration value indicating the extent of loss of calibration of a group of three or more sensors in a sensor network, the method involving receiving a plurality of data values captured over a period of time by each of the sensors, determining by a processing unit (404) at least one correlation value associated with each sensor, each correlation value corresponding to the correlation between the data values captured by the associated sensor and the data values captured by at least one other sensor; (410) a noise component of the correlation values and outputting the calibration value determined based on the difference between the noise component and a reference noise value.

Abstract: A method for performing noise adaptation of a target speech signal input to a speech recognition system, where the target speech signal contains both additive and convolutional noises. The method includes estimating an additive noise bias and a convolutional noise bias; in the target speech signal; and jointly compensating the target speech signal for the additive and convolutional noise biases in a feature domain.

Abstract: Methods and apparatus for blind channel estimation of a speech signal corrupted by a communication channel are provided. One method includes converting a noisy speech signal into either a cepstral representation or a log-spectral representation; estimating a correlation of the representation of the noisy speech signal; determining an average of the noisy speech signal; constructing and solving, subject to a minimization constraint, a system of linear equations utilizing a correlation structure of a clean speech training signal, the correlation of the representation of the noisy speech signal, and the average of the noisy speech signal; and selecting a sign of the solution of the system of linear equations to estimate an average clean speech signal in a processing window.

Abstract: Methods and apparatus for blind channel estimation of a speech signal corrupted by a communication channel are provided. One method includes converting a noisy speech signal into either a cepstral representation or a log-spectral representation; estimating a correlation of the representation of the noisy speech signal; determining an average of the noisy speech signal; constructing and solving, subject to a minimization constraint, a system of linear equations utilizing a correlation structure of a clean speech training signal, the correlation of the representation of the noisy speech signal, and the average of the noisy speech signal; and selecting a sign of the solution of the system of linear equations to estimate an average clean speech signal in a processing window.

Abstract: A method for performing noise adaptation of a target speech signal input to a speech recognition system, where the target speech signal contains both additive and convolutional noises. The method includes estimating an additive noise bias and a convolutional noise bias; in the target speech signal; and jointly compensating the target speech signal for the additive and convolutional noise biases in a feature domain.