Abstract: Aspects of the present disclosure involve a device comprising a computer-readable storage medium storing a program and method for providing contextual information with a keyboard interface. The program and method provide for receiving a media content item provided by a second device; displaying, on a screen of the device, the media content item together with a reply element, the reply element being user-selectable to generate a reply message with respect to the media content item; receiving user selection of the reply element; and in response to receiving the user selection, displaying, in a first preset area of the screen, a keyboard interface for user selection of text to include in the reply message, and displaying, in a second preset area of the screen, a context information interface which is user-selectable to provide information corresponding to at least one type of context associated with the media content item.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for presenting participant reactions to a virtual conference. The program and method provide for a virtual conference between plural participants; provide, for each of the plural participants, display of a reaction button which is selectable by the participant to indicate a reaction to the virtual conference; receive indication of selections of the reaction button by one or more of the plural participants; and in response to receiving the indication, provide, for each of the plural participants, display of reaction icons and audio output based on the selections, determine that a rate at which the selections were received meets a threshold rate, and provide, in response to the determining, for modified audio output associated with the selections.

Abstract: A server-side administrative interface for a social media platform allows for restriction of defined geographical areas. Social media items originating from such restricted areas are automatically filtered or age-restricted for availability via a map-based graphical user interface of the social media platform.

Abstract: A map-based graphical user interface (GUI) for a public messaging platform allows a user location-based to their own expired ephemeral content. Such expired content is no longer available to other users for online viewing. The user can, however, switch the GUI between a live mode and a historical mode, access to their own expired content in the historical mode being facilitated in a manner closely similar to that for viewing live publicly available content.

Abstract: Systems, methods, and devices are provided for generating and using text-to-speech (TTS) data for improved speech recognition models. A main model is trained with keyword independent baseline training data. In some instances, acoustic and language model sub-components of the main model are modified with new TTS training data. In some instances, the new TTS training is obtained from a multi-speaker neural TTS system for a keyword that is underrepresented in the baseline training data. In some instances, the new TTS training data is used for pronunciation learning and normalization of keyword dependent confidence scores in keyword spotting (KWS) applications. In some instances, the new TTS training data is used for rapid speaker adaptation in speech recognition models.

Abstract: Systems, methods, and devices are provided for generating and using text-to-speech (TTS) data for improved speech recognition models. A main model is trained with keyword independent baseline training data. In some instances, acoustic and language model sub-components of the main model are modified with new TTS training data. In some instances, the new TTS training is obtained from a multi-speaker neural TTS system for a keyword that is underrepresented in the baseline training data. In some instances, the new TTS training data is used for pronunciation learning and normalization of keyword dependent confidence scores in keyword spotting (KWS) applications. In some instances, the new TTS training data is used for rapid speaker adaptation in speech recognition models.

Abstract: A server-side administrative interface for a social media platform allows for restriction of defined geographical areas. Social media items originating from such restricted areas are automatically filtered or age-restricted for availability via a map-based graphical user interface of the social media platform.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for presenting participant reactions to a virtual conference. The program and method provide for a virtual conference between plural participants; provide, for each of the plural participants, display of a reaction button which is selectable by the participant to indicate a reaction to the virtual conference; receive indication of selections of the reaction button by one or more of the plural participants; and in response to receiving the indication, provide, for each of the plural participants, display of reaction icons and audio output based on the selections, determine that a rate at which the selections were received meets a threshold rate, and provide, in response to the determining, for modified audio output associated with the selections.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for providing automatically navigating between rooms within a virtual space for virtual conferencing. The program and method provide for virtual conferencing between plural participants within a first room of plural rooms included within the virtual space; provide, for each of the plural participants, display of a participant video element which corresponds to the participant and which includes a user-selectable button for requesting that the participant follow another participant with respect to navigating between the plural rooms; receive a first indication of a user selection, by a first participant, of the user-selectable button corresponding to a second participant; receive a second indication that the second participant authorizes following the first participant when navigating between the plural rooms; and provide for the second participant to follow the first participant.

Abstract: A server-side administrative interface for a social media platform allows for restriction of defined geographical areas. Social media items originating from such restricted areas are automatically filtered or age-restricted for availability via a map-based graphical user interface of the social media platform.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for presenting participant reactions to a virtual conference. The program and method provide for a virtual conference between plural participants; provide, for each of the plural participants, display of a reaction button which is selectable by the participant to indicate a reaction to the virtual conference; receive indication of selections of the reaction button by one or more of the plural participants; and in response to receiving the indication, provide, for each of the plural participants, display of reaction icons and audio output based on the selections, determine that a rate at which the selections were received meets a threshold rate, and provide, in response to the determining, for modified audio output associated with the selections.

Abstract: In one or more implementations, usage of augmented reality content items may be tracked based on characteristics of respective target audiences of the augmented reality content items. User tracking components may be included with respective instances of the augmented reality content items that analyze characteristics of users of the client application access the augmented reality content items in relation to the characteristics of the target audiences.

Abstract: Aspects of the present disclosure involve a device comprising a computer-readable storage medium storing a program and method for providing contextual information with a keyboard interface. The program and method provide for receiving a media content item provided by a second device; displaying, on a screen of the device, the media content item together with a reply element, the reply element being user-selectable to generate a reply message with respect to the media content item; receiving user selection of the reply element; and in response to receiving the user selection, displaying, in a first preset area of the screen, a keyboard interface for user selection of text to include in the reply message, and displaying, in a second preset area of the screen, a context information interface which is user-selectable to provide information corresponding to at least one type of context associated with the media content item.

Abstract: Systems, methods, and devices are provided for generating and using text-to-speech (TTS) data for improved speech recognition models. A main model is trained with keyword independent baseline training data. In some instances, acoustic and language model sub-components of the main model are modified with new TTS training data. In some instances, the new TTS training is obtained from a multi-speaker neural TTS system for a keyword that is underrepresented in the baseline training data. In some instances, the new TTS training data is used for pronunciation learning and normalization of keyword dependent confidence scores in keyword spotting (KWS) applications. In some instances, the new TTS training data is used for rapid speaker adaptation in speech recognition models.

Abstract: A server-side administrative interface for a social media platform allows for restriction of defined geographical areas. Social media items originating from such restricted areas are automatically filtered or age-restricted for availability via a map-based graphical user interface of the social media platform.