Abstract: A method can perform a process with a method including capturing an image, determining an environment that a user is operating a computing device, detecting a hand gesture based on an object in the image, determining, using a machine learned model, an intent of a user based on the hand gesture and the environment, and executing a task based at least on the determined intent.

Abstract: A speaker verification method includes receiving audio data corresponding to an utterance, processing a first portion of the audio data that characterizes a predetermined hotword to generate a text-dependent evaluation vector, and generating one or more text-dependent confidence scores. When one of the text-dependent confidence scores satisfies a threshold, the operations include identifying a speaker of the utterance as a respective enrolled user associated with the text-dependent confidence score that satisfies the threshold and initiating performance of an action without performing speaker verification. When none of the text-dependent confidence scores satisfy the threshold, the operations include processing a second portion of the audio data that characterizes a query to generate a text-independent evaluation vector, generating one or more text-independent confidence scores, and determining whether the identity of the speaker of the utterance includes any of the enrolled users.

Abstract: A method can perform a process with a method including capturing an image, determining an environment that a user is operating a computing device, detecting a hand gesture based on an object in the image, determining, using a machine learned model, an intent of a user based on the hand gesture and the environment, and executing a task based at least on the determined intent.

Abstract: A method can perform a process with a method including capturing an image, determining an environment that a user is operating a computing device, detecting a hand gesture based on an object in the image, determining, using a machine learned model, an intent of a user based on the hand gesture and the environment, and executing a task based at least on the determined intent.

Abstract: A speaker verification method includes receiving audio data corresponding to an utterance, processing a first portion of the audio data that characterizes a predetermined hotword to generate a text-dependent evaluation vector, and generating one or more text-dependent confidence scores. When one of the text-dependent confidence scores satisfies a threshold, the operations include identifying a speaker of the utterance as a respective enrolled user associated with the text-dependent confidence score that satisfies the threshold and initiating performance of an action without performing speaker verification. When none of the text-dependent confidence scores satisfy the threshold, the operations include processing a second portion of the audio data that characterizes a query to generate a text-independent evaluation vector, generating one or more text-independent confidence scores, and determining whether the identity of the speaker of the utterance includes any of the enrolled users.

Abstract: A system and method may provide for spatial and semantic auto-completion of an augmented or mixed reality environment. The system may detect physical objects in a physical environment based on analysis of image frames captured by an image sensor of a computing device. The system may detect spaces in the physical environment that are occupied by the detected physical objects, and may detect spaces that are unoccupied in the physical environment. Based on the identification of the detected physical objects, the system may gain a semantic understanding of the physical environment, and may determine suggested objects for placement in the physical environment based on the semantic understanding. The system may place virtual representations of the suggested objects in a mixed reality scene of the physical environment for user consideration.

Abstract: A method can perform a process with a method including capturing an image, determining an environment that a user is operating a computing device, detecting a hand gesture based on an object in the image, determining, using a machine learned model, an intent of a user based on the hand gesture and the environment, and executing a task based at least on the determined intent.

Abstract: A system and method may provide for spatial and semantic auto-completion of an augmented or mixed reality environment. The system may detect physical objects in a physical environment based on analysis of image frames captured by an image sensor of a computing device. The system may detect spaces in the physical environment that are occupied by the detected physical objects, and may detect spaces that are unoccupied in the physical environment. Based on the identification of the detected physical objects, the system may gain a semantic understanding of the physical environment, and may determine suggested objects for placement in the physical environment based on the semantic understanding. The system may place virtual representations of the suggested objects in a mixed reality scene of the physical environment for user consideration.

Abstract: A system and method for creating an augmented reality (AR) environment are disclosed. AR effects are determined based on events detected in captured audio and combined with captured video to create an AR environment for an application. The resulting AR experience is triggered, generated, altered or otherwise controlled by sound, such as speech.