Abstract: A speaker identification/verification system comprises at least one feature extractor for extracting a plurality of audio features from speaker voice data, a plurality of speaker-specific subsystems, and a decision module. Each of the speaker-specific subsystem comprises: a neural network configured to generate an estimate of the plurality of extracted audio features based on the plurality of extracted audio features, and an error module. Each of the plurality of neural networks is associated with one of a plurality of speakers, and the one speaker associated with each of the plurality of neural networks is different for all neural networks. The error module is configured to estimate an error based on the plurality of extracted audio features and the estimate of the plurality of extracted audio features generated by the associated neural network. The neural networks are speaker-specific auto-encoders trained for one user and therefore calibrated on that particular user's speech.

Abstract: A speech-enhancing noise filter is disclosed. The noise filter comprises a microphone for acquiring speech data from a user; a feature extraction module configured to extract a plurality of features characterizing the speech data; a neural network configured to receive the plurality of extracted features and to estimate a noise profile from the plurality of extracted features; a noise removal module configured to remove the noise profile from the noisy speech data; and a reconstruction module configured to generate a waveform from the plurality of frames after removal of the noise profile from each of those frames. The neural network is trained to isolate various types of noise from the user speech in the speech data and then subtract the noise from the speech data, thus leaving only the user speech free of noise.

Abstract: An unscented Kalman filter is used to enable sensor calibration independently of the actual design of the subject sensors. By utilizing an unscented Kalman filter, an underlying calibration methodology is developed that is sensor-unspecific, such that a single calibration methodology and related systems may be used to calibrate various sensors, without the need to re-calculate a calibration factor for each specific sensor, and without the need to design a separate filtering mechanism to compensate for noise. In this way, various calibration inputs can be allowed to change over time without the need to change the codebase on which the calibration methodology otherwise operates. In multi-electrode systems, the methodology may incorporate a fusion algorithm to provide a single, fused sensor glucose value. The fusion algorithm may incorporate, and/or work in conjunction with, Electrochemical Impedance Spectroscopy (EIS) procedures.

Abstract: Embodiments of a computer implemented method of generating a variable structure regression model. The method includes receiving data input including historical data, an output variable, a plurality of input variables; establishing a set of linguistic rules for the plurality of input variables; establishing variable structure regression equations using the set of linguistic rules, the output variable, the input variables, and the historical data; optimizing membership functions and regression coefficients of the variable structure regression equations; and generating a variable structure regression model from the optimized membership functions, the regression coefficients, and the variable structure regression equations. The exact mathematical structure of these linguistic terms and the number of terms are established simultaneously, thereby freeing the end user from trial and error time-consuming studies.