Abstract: Certain aspects of the present disclosure provide techniques and apparatus for improved machine learning. Voice data from a first user is received. In response to determining that the voice data includes an utterance of a defined keyword, a user verification score is generated by processing the voice data using a first user verification machine learning (ML) model, and a quality of the voice data is determined. In response to determining that the user verification score and determined quality satisfy one or more defined criteria, a second user verification ML model is updated based on the voice data.

Abstract: A method for verifying at least one sound sample to be used in generating a sound detection model in an electronic device includes receiving a first sound sample; extracting a first acoustic feature from the first sound sample; receiving a second sound sample; extracting a second acoustic feature from the second sound sample; and determining whether the second acoustic feature is similar to the first acoustic feature.

Abstract: A wireless communication system and related techniques and apparatuses are disclosed that predict future disconnections or other connection impairments with end-user portable devices in advance so that service interruptions can be handled more gracefully. The system can predict the loss of service based on user-usage information associated with the portable device, such as the current GPS location of the device, its direction and velocity of travel, a user calendar, user habits and other information, such as the time of day, weather conditions, or wireless network coverage maps. An impairment handling method is selected that alters the content presented by the portable device. The impairment handling method is executed by the system upon detecting the impairment of the wireless connection so that the content is altered during occurrence of the impairment. The alteration of the content is done to mitigate the user-perceived effect of the impairment.

Abstract: A method for verifying at least one sound sample to be used in generating a sound detection model in an electronic device includes receiving a first sound sample; extracting a first acoustic feature from the first sound sample; receiving a second sound sample; extracting a second acoustic feature from the second sound sample; and determining whether the second acoustic feature is similar to the first acoustic feature.