Abstract: In embodiments, apparatuses, methods and storage media are described that are associated with training adaptive speech recognition systems (“ASR”) using audio and text obtained from captioned video. In various embodiments, the audio and caption may be aligned for identification, such as according to a start and end time associated with a caption, and the alignment may be adjusted to better fit audio to a given caption. In various embodiments, the aligned audio and caption may then be used for training if an error value associated with the audio and caption demonstrates that the audio and caption will aid in training the ASR. In various embodiments, filters may be used on audio and text prior to training. Such filters may be used to exclude potential training audio and text based on filter criteria. Other embodiments may be described and claimed.

Abstract: In an exemplary method, a media content recommendation system interfaces with a knowledge graph system to access knowledge graph data that represents a knowledge graph relationship between a subject and a media program in a knowledge graph, generates, based on the knowledge graph data, a media content recommendation that includes recommendation content indicating the media program and the knowledge graph relationship between the subject and the media program, and outputs the media content recommendation for presentation to a user by a user computing device.

Abstract: In an exemplary method, a media content recommendation system determines that a media service account of an end user of a media service is linked to a social media account of the end user, accesses social media data from the social media account of the end user of the media service, generates a media content recommendation personalized to the end user of the media service based on the social media data, and provides the media content recommendation to an access device for presentation to the end user of the media service.

Abstract: An exemplary method of identifying a media program clip associated with a trending topic includes receiving a plurality of media content streams representative of a plurality of media programs, detecting, while the media content streams are being received, caption data included in the media content streams and associated with the media programs, identifying, based on the detected caption data, a trending topic associated with the plurality of media programs, and identifying a media program clip associated with the trending topic. Corresponding systems and methods are also described.

Abstract: In embodiments, apparatuses, methods and storage media are described that are associated with content distribution. In embodiments, one or more frames may be displayed on a display, and the frame or frames with the highest luminance level of those frames may be identified. A camera may be configured to capture an image at a point in time based at least in part on display of the frame with the highest luminance level. In some embodiments, the luminance level of the frames may be identified based at least in part on analysis of the frames by a device prior to display of the frames. In other embodiments, the luminance level of the frames may be identified based at least in part on the receipt of luminance data from a server.

Abstract: Apparatuses, methods and storage medium associated with content consumption, are disclosed herein. In embodiments, the apparatus may include a presentation engine to play the media content; and a user interface engine to facilitate a user in controlling the playing of the media content. The user interface engine may include a user identification engine to acoustically identify the user; an acoustic speech recognition engine to recognize speech in voice input of the user, using an acoustic speech recognition model specifically trained for the user, and a user command processing engine to process recognized speech as user commands. Other embodiments may be described and/or claimed.

Abstract: In embodiments, apparatuses, methods and storage media are described that are associated with remote control of media devices. A remote control and a content player may be configured to facilitate a secured pairing process. The remote control may be configured to send non-secured signals (such as through an IR transmitter) as well as send and receive secured signals (such as via an RF transceiver). The remote control may non-securely broadcast an uncompressed identifier of itself. Then, in response to being turned on or asked to pair, the remote control may send a pairing request to the player that includes a compressed identifier. The player may then identify the remote control based on the compressed identifier and the previously-broadcast uncompressed identifier and the remote control and player may then perform a pairing process without requiring additional action on the part of a user. Other embodiments may be described and/or claimed.

Abstract: In embodiments, apparatuses, methods and storage media are described that are associated with performing identity-based access control for content. A content consumption device may be configured to control access to presented content based on identities of one or more content consumers that are physically proximate to the device. The content consumption device may be configured to perform facial and/or voice recognition on one or more content consumers to determine an identity for the one or more content consumers. The content consumption device may be configured to determine access permissions for the identified content consumers. At various times, access to a piece of content may change based on who is physically proximate to the content consumption device. Other embodiments may be described and claimed.

Abstract: In embodiments, apparatuses, methods and storage media are described that are associated with recognition of speech based on sequences of named entities. Language models may be trained as being associated with sequences of named entities. A language model may be selected for speech recognition after identification of one or more sequences of named entities by an initial language model. After identification of the one or more sequences of named entities, weights may be assigned to the one or more sequences of named entities. These weights may be utilized to select a language module and/or update the initial language model to one that is associated with the identified one or more sequences of named entities. In various embodiments, the language model may be repeatedly updated until the recognized speech converges sufficiently to satisfy a predetermined threshold. Other embodiments may be described and claimed.

Abstract: In embodiments, apparatuses, methods and storage media are described that are associated with training adaptive speech recognition systems (“ASR”) using audio and text obtained from captioned video. In various embodiments, the audio and caption may be aligned for identification, such as according to a start and end time associated with a caption, and the alignment may be adjusted to better fit audio to a given caption. In various embodiments, the aligned audio and caption may then be used for training if an error value associated with the audio and caption demonstrates that the audio and caption will aid in training the ASR. In various embodiments, filters may be used on audio and text prior to training. Such filters may be used to exclude potential training audio and text based on filter criteria. Other embodiments may be described and claimed.

Abstract: In embodiments, apparatuses, methods and storage media are described that are associated with remote control of media devices. A remote control and a content player may be configured to facilitate a secured pairing process. The remote control may be configured to send non-secured signals (such as through an IR transmitter) as well as send and receive secured signals (such as via an RF transceiver). The remote control may non-securely broadcast an uncompressed identifier of itself. Then, in response to being turned on or asked to pair, the remote control may send a pairing request to the player that includes a compressed identifier. The player may then identify the remote control based on the compressed identifier and the previously-broadcast uncompressed identifier and the remote control and player may then perform a pairing process without requiring additional action on the part of a user. Other embodiments may be described and/or claimed.

Abstract: In embodiments, apparatuses, methods and storage media are described that are associated with content distribution. In embodiments, one or more frames may be displayed on a display, and the frame or frames with the highest luminance level of those frames may be identified. A camera may be configured to capture an image at a point in time based at least in part on display of the frame with the highest luminance level. In some embodiments, the luminance level of the frames may be identified based at least in part on analysis of the frames by a device prior to display of the frames. In other embodiments, the luminance level of the frames may be identified based at least in part on the receipt of luminance data from a server.

Abstract: Digital media content from files, streaming data, broadcast data, optical disks, or other storage devices can be linked to Internet information. Identifiers extracted from the media content can be used to direct Internet searches for more information related to the media content.

Abstract: An object depicted with a video file may be located in a search process. The located object may then be extracted from the digital video file. The extracted depiction may then be modified independently of the video file.

Abstract: A processor includes a pipeline having first and second stages and a shift register having first and second latches. An interface circuit is used to provide a clock signal from a clock signal line to the first and second stages based, at least in part, on first and second bits to be stored in the first and second latches, respectively.