Abstract: A processor-implemented method for recognizing a natural language on a mobile device includes receiving an audio input. The method further includes using a neural network to generate local text corresponding to the audio input. The method still further includes generating a local confidence value for accuracy of the local text. The method includes transmitting, to a remote device, data corresponding to the audio input. The method further includes receiving remote text corresponding to the data, along with a remote confidence score for accuracy of the remote text. The method still further includes outputting the local text in response to the local confidence value being higher than the remote confidence score, and outputting the remote text in response to the remote confidence score being higher than the local confidence value.

Abstract: Methods, systems, computer-readable media, and apparatuses for gesture recognition are disclosed for audio control. The gestures can be used for audio control in virtualized environments. The audio control can include generating a sound that mimics an effect of a modification of a sound wave that would occur if the gesture were performed in a non-virtualized environment.

Abstract: Methods, systems, computer-readable media, and apparatuses for gesture recognition are disclosed for audio control. The gestures can be used for audio control in virtualized environments. The audio control can include generating a sound that mimics an effect of a modification of a sound wave that would occur if the gesture were performed in a non-virtualized environment.

Abstract: Methods, systems and devices are provided for controlling a wearable device. Embodiments include receiving a facial movement indication from a facial movement detector measured contemporaneously with an input audio signal. Additionally, whether a first movement pattern associated with the wearer speaking is a movement match to the facial movement indication may be determined. In this way, a speaking gain profile may be applied to the input audio signal for generating an augmented audio segment in response to determining the first movement pattern is the movement match to the facial movement indication. Thus, the augmented audio segment may be output.

Abstract: A hearing aid device and methods implemented in hearing aid devices activate a radio frequency (RF) transceiver for communicating sounds signals for remote processing on a mobile computing device in response to the device detecting reception of meaningful sound, such as speech. Selectively activating the RF transceiver when sound is meaningful and avoiding powering the RF transceiver when detected sound is of little value to the wearer enables hearing aid to use the mobile computing device to process meaningful sound signals (e.g., speech from another person) while conserving batter power, thereby prolonging its battery life. The hearing aid device and methods may also deactivate the RF transceiver when the hearing aid device does not detect a meaningful sound signal.

Abstract: The present invention relates to an adaptive frequency hopping apparatus in a wireless personal area network (WPAN) system, wherein predetermined packets of data can be correctly transmitted by estimating the channel qualities of operating bands in advance and transmitting the packets through a proper band.

Abstract: The present invention relates to an adaptive frequency hopping apparatus in a wireless personal area network (WPAN) system, wherein predetermined packets of data can be correctly transmitted by estimating the channel qualities of operating bands in advance and transmitting the packets through a proper band.