Sharp Laboratories of America, Inc

Fredrick Norman Hill

Bryan Hallberg

A low overhead voice activity detection technique for a noise-canceling bioacoustic sensor consumes, as inputs, signals generated by a body microphone and an environment microphone and produces, as an output based on these inputs, an indication of whether voice activity is present. The technique applies a novel dual ANC configuration that produces, in addition to the normal noise reduction function, a signal composed of environmental sounds with body sounds attenuated and a signal composed of body sounds projected into the acoustic environment, primarily speech sounds. The technique then applies to these derived signals an algorithm based on the scientific observation that speech intensity, within limits, rises and falls to match environmental sound intensity to provide voice activity detection.

Voice activity detection for noise-canceling bioacoustic sensor

A model-based method for assessing acoustic signal quality in a heart monitoring device. The personal heart sound interval distribution of a person being actively monitored is compared with a modeled global heart sound interval distribution shared by most human beings after which processing action is taken consistent with the quality assessment. The error in the best fit between the personal interval distribution and the global interval distribution is presumed to be caused predominantly by noise, allowing the quality of the fit to serve as a proxy for the level of noise in the acoustic signal and used in making processing decisions.

Growing community of inventors

Portland, OR, United States of America

Fredrick Norman Hill