Abstract: The present disclosure is directed to computer-implemented systems and methods for performing recognition over a network of devices. In general, the systems and methods implement a machine-learned recognizability model that can process information such as a person's voice, facial characteristics, or similar information to determine a recognizability score without necessarily generating or storing biometric information that could be used to identify the person. The recognizability score can act as a proxy for the quality of the information as a reference for biometric recognition that can be performed on other devices in the network of devices. Thus a single device can be used to enroll a person in the network (e.g., by capturing a number of photographs of the person). Thereafter, connection to the other devices can utilize a sensor (e.g., a camera) on the other devices to compare features of the reference information to the input received by the sensor.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating predictions for whether a target person is speaking during a portion of a video. In one aspect, a method includes obtaining one or more images which each depict a mouth of a given person at a respective time point. The images are processed using an image embedding neural network to generate a latent representation of the images. Audio data corresponding to the images is processed using an audio embedding neural network to generate a latent representation of the audio data. The latent representation of the images and the latent representation of the audio data is processed using a recurrent neural network to generate a prediction for whether the given person is speaking.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating predictions for whether a target person is speaking during a portion of a video. In one aspect, a method includes obtaining one or more images which each depict a mouth of a given person at a respective time point. The images are processed using an image embedding neural network to generate a latent representation of the images. Audio data corresponding to the images is processed using an audio embedding neural network to generate a latent representation of the audio data. The latent representation of the images and the latent representation of the audio data is processed using a recurrent neural network to generate a prediction for whether the given person is speaking.