Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for audio-visual speech separation. A method includes: receiving, by a user device, a first indication of one or more first speakers visible in a current view recorded by a camera of the user device, in response, generating a respective isolated speech signal for each of the one or more first speakers that isolates speech of the first speaker in the current view and sending the isolated speech signals for each of the one or more first speakers to a listening device operatively coupled to the user device, receiving, by the user device, a second indication of one or more second speakers visible in the current view recorded by the camera of the user device, and in response generating and sending a respective isolated speech signal for each of the one or more second speakers to the listening device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for audio-visual speech separation. A method includes: receiving, by a user device, a first indication of one or more first speakers visible in a current view recorded by a camera of the user device, in response, generating a respective isolated speech signal for each of the one or more first speakers that isolates speech of the first speaker in the current view and sending the isolated speech signals for each of the one or more first speakers to a listening device operatively coupled to the user device, receiving, by the user device, a second indication of one or more second speakers visible in the current view recorded by the camera of the user device, and in response generating and sending a respective isolated speech signal for each of the one or more second speakers to the listening device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for audio-visual speech separation. A method includes: receiving, by a user device, a first indication of one or more first speakers visible in a current view recorded by a camera of the user device, in response, generating a respective isolated speech signal for each of the one or more first speakers that isolates speech of the first speaker in the current view and sending the isolated speech signals for each of the one or more first speakers to a listening device operatively coupled to the user device, receiving, by the user device, a second indication of one or more second speakers visible in the current view recorded by the camera of the user device, and in response generating and sending a respective isolated speech signal for each of the one or more second speakers to the listening device.

Abstract: One or more processors may output for display, an interface including a data classification section including two or more class nodes, a training section including a training node, and an evaluation section including an evaluation node. At a first class node a first set of training data may be captured and at a second class node a second set of training data may be captured. In response to an input received at the training node, a classification model based on the first set of training data and the second set of training data may be trained. Evaluation data may be captured in an evaluation node, and using the trained classification model, classifications for each piece of the evaluation data may be determined. A visual representation of the classification for each piece of the evaluation data may be output for display within the evaluation node.

Abstract: One or more processors may output for display, an interface including a data classification section including two or more class nodes, a training section including a training node, and an evaluation section including an evaluation node. At a first class node a first set of training data may be captured and at a second class node a second set of training data may be captured. In response to an input received at the training node, a classification model based on the first set of training data and the second set of training data may be trained. Evaluation data may be captured in an evaluation node, and using the trained classification model, classifications for each piece of the evaluation data may be determined. A visual representation of the classification for each piece of the evaluation data may be output for display within the evaluation node.

Abstract: Computer-readable media and related methods for processing hand-drawn image elements are disclosed. A method includes selecting an image element model to replace an image element derived from a hand-drawn user input, correcting the selected image element model, and displaying the corrected image element model on an electronic display. A computer-readable medium includes computer-readable instructions stored thereon. The computer-readable instructions are configured to instruct a processor to determine whether an image element model is a suitable replacement for a hand-drawn image element, perform correction on the image element model if it is determined that the image element model is a suitable replacement, display the corrected image element model if it is determined that the image element model is a suitable replacement, and display the hand-drawn image element model if it is determined that the image element model is not a suitable replacement.

Abstract: A method is provided that comprises receiving, from a user device, a first input indicating a first color, from a color palette, as a source color. The method further comprises receiving, from the user device, a second input indicating a second color from the color palette as a target color. The method also comprises receiving, from the user device, a plurality of user movement indicators representing an incremental mixing of the target color into the source color. The method further comprises defining a plurality of colors based on the first input, the second input and the plurality of user movement indicators. The method also comprises storing, data associated with each color from the plurality of colors. The method further comprises sending, for each color from the plurality of colors, a signal to display a representation of that color on the user interface associated with the user device.

Abstract: A graphical user interface (GUI) including an illustration can be rendered. In response to receiving a signal from an input device indicating a location within the illustration, a layer can be defined. When the layer is applied to the illustration, the GUI can be updated such that a portion of the illustration under a filter is displayed as an altered feature. The filter can overlay the indicated location. In some embodiments, another portion of the illustration different from indicated location may not be filtered. Similarly stated, only a portion of the layer can include the filter and/or the layer may not overlay the entire illustration. A signal can be received from the input device indicating a use of the tool on the layer and, in response, the altered feature can be modified.

Abstract: A graphical user interface (GUI) including an illustration can be rendered. In response to receiving a signal from an input device indicating a location within the illustration, a layer can be defined. When the layer is applied to the illustration, the GUI can be updated such that a portion of the illustration under a filter is displayed as an altered feature. The filter can overlay the indicated location. In some embodiments, another portion of the illustration different from indicated location may not be filtered. Similarly stated, only a portion of the layer can include the filter and/or the layer may not overlay the entire illustration. A signal can be received from the input device indicating a use of the tool on the layer and, in response, the altered feature can be modified.

Abstract: A method is provided that comprises receiving, from a user device, a first input indicating a first color, from a color palette, as a source color. The method further comprises receiving, from the user device, a second input indicating a second color from the color palette as a target color. The method also comprises receiving, from the user device, a plurality of user movement indicators representing an incremental mixing of the target color into the source color. The method further comprises defining a plurality of colors based on the first input, the second input and the plurality of user movement indicators. The method also comprises storing, data associated with each color from the plurality of colors. The method further comprises sending, for each color from the plurality of colors, a signal to display a representation of that color on the user interface associated with the user device.