Abstract: A method for speech emotion recognition for enriching speech to text communications between users in speech chat sessions including: implementing a speech emotion recognition model to enable converting observed emotions in speech samples to enrich text with visual emotion content by: generating a data set of speech samples with labels of a plurality of emotion classes; extracting a set of acoustic features from each of the emotion classes; generating a machine learning (ML) model based on the acoustic features and data set; training the ML model from acoustic features from speech samples during speech chat sessions; predicting emotion content based on a trained ML model in the observed speech; generating enriched text based on predicted emotion content of the trained ML model; and presenting the enriched text in speech to text communications between users in the chat session for visual notice of an observed emotion in the speech sample.

Abstract: Embodiments are related to processing of one or more input audio feeds for generation of a target audio stream that includes at least one object of interest to a listener. In some embodiments, the target audio stream may exclusively or primarily include the sound of the object of interest to the listener, without including other persons. This allows a listener to focus on an object of his or her interest and not necessarily have to listen to the performances of other objects in the input audio feed. Some embodiments contemplate multiple audio feeds and/or with multiple objects of interest.

Abstract: Systems, methods, and devices are disclosed enabling smart search functionalities utilizing key scene changes appearing in video content. In various embodiments, the method includes the step or process of, while engaged in playback of the video content, receiving a user command at a playback device to shift a current playback position of the video content to a default search playback position (PPDS). In response to receipt of the user command, the playback device searches a time window encompassing the default search playback position (PPDS) for a key scene change in the video content. If locating a key scene change within the time window, the playback device shifts playback of the video content to a playback position corresponding to the key scene change (PPST). Otherwise, the playback device shifts playback of the video content to the default search playback position (PPDS).

Abstract: Various arrangements for generating thumbnail images for video content as the video content is being received are presented. A television receiver may first receive video content. A thumbnail generation process may be woken from a sleep state based on a predefined time period elapsing. The received video content may be monitored for a next-received I-frame. A thumbnail image may be created from the I-frame and may be mapped to a timestamp. The thumbnail generation process may then be caused to enter the sleep state for the predefined time period.

Abstract: Systems, methods, and devices are disclosed enabling smart search functionalities utilizing key scene changes appearing in video content. In various embodiments, the method includes the step or process of, while engaged in playback of the video content, receiving a user command at a playback device to shift a current playback position of the video content to a default search playback position (PPDS). In response to receipt of the user command, the playback device searches a time window encompassing the default search playback position (PPDS) for a key scene change in the video content. If locating a key scene change within the time window, the playback device shifts playback of the video content to a playback position corresponding to the key scene change (PPST). Otherwise, the playback device shifts playback of the video content to the default search playback position (PPDS).

Abstract: Embodiments are related to processing of one or more input audio feeds for generation of a target audio stream that includes at least one object of interest to a listener. In some embodiments, the target audio stream may exclusively or primarily include the sound of the object of interest to the listener, without including other persons. This allows a listener to focus on an object of his or her interest and not necessarily have to listen to the performances of other objects in the input audio feed. Some embodiments contemplate multiple audio feeds and/or with multiple objects of interest.

Abstract: Systems, methods, and devices are disclosed enabling smart search functionalities utilizing key scene changes appearing in video content. In various embodiments, the method includes the step or process of, while engaged in playback of the video content, receiving a user command at a playback device to shift a current playback position of the video content to a default search playback position (PPDS). In response to receipt of the user command, the playback device searches a time window encompassing the default search playback position (PPDS) for a key scene change in the video content. If locating a key scene change within the time window, the playback device shifts playback of the video content to a playback position corresponding to the key scene change (PPST). Otherwise, the playback device shifts playback of the video content to the default search playback position (PPDS).

Abstract: Various techniques are described herein for supporting voice command control of electronic programming guides (EPGs) and other media content selection systems. The voice input hardware and software components of a remote control device, television receiver, smartphone, virtual assistant, and/or other media device may receive voice commands from a user corresponding to a selection of a media content. In response to the received voice input, the media device may perform a speech-to-text conversion of the voice input, and then perform an analysis of the command text to determine one or more content selections of the user. The analysis may include identifying within the command text one or more television channel names, program names, or other media content names, as well as identifying other instructions, preferences, or other meaningful insights from the command text.

Abstract: Systems and methods for intelligent playback of media content may include an intelligent media playback system that, in response to determining the speech tempo in audio content by measuring syllable density of speech in the audio content, automatically adjusts a playback speed of the audio content as the audio content is being played based on the determined speech tempo. In some embodiments, the system may automatically and dynamically adjust the playback speed to result in a desired target speech tempo. In addition, the system may determine whether to automatically adjust playback speed of the audio content, as the media is being played, based on the detected speech tempo of the speech in the audio content and the determined type of content of media. Such automatic adjustments in playback speed result in more efficient playback of the audio content.

Abstract: Various arrangements for generating thumbnail images for video content as the video content is being received are presented. A television receiver may first receive video content. A thumbnail generation process may be woken from a sleep state based on a predefined time period elapsing. The received video content may be monitored for a next-received I-frame. A thumbnail image may be created from the I-frame and may be mapped to a timestamp. The thumbnail generation process may then be caused to enter the sleep state for the predefined time period.

Abstract: Embodiments are related to processing of one or more input audio feeds for generation of a target audio stream that includes at least one object of interest to a listener. In some embodiments, the target audio stream may exclusively or primarily include the sound of the object of interest to the listener, without including other persons. This allows a listener to focus on an object of his or her interest and not necessarily have to listen to the performances of other objects in the input audio feed. Some embodiments contemplate multiple audio feeds and/or with multiple objects of interest.

Abstract: Embodiments are related to processing of one or more input audio feeds for generation of a target audio stream that includes at least one object of interest to a listener. In some embodiments, the target audio stream may exclusively or primarily include the sound of the object of interest to the listener, without including other persons. This allows a listener to focus on an object of his or her interest and not necessarily have to listen to the performances of other objects in the input audio feed. Some embodiments contemplate multiple audio feeds and/or with multiple objects of interest.

Abstract: Embodiments are related to processing of one or more input audio feeds for generation of a target audio stream that includes at least one object of interest to a listener. In some embodiments, the target audio stream may exclusively or primarily include the sound of the object of interest to the listener, without including other persons. This allows a listener to focus on an object of his or her interest and not necessarily have to listen to the performances of other objects in the input audio feed. Some embodiments contemplate multiple audio feeds and/or with multiple objects of interest.

Abstract: Methods and systems are provided for presenting media content with reduced latency. An exemplary method involves obtaining, by a tuner at a media device, media content broadcast on a broadcast channel and buffering, at the media device, a recent subset of the media content in a buffer associated with the tuner. In response to selection of the broadcast channel for presentation on a destination device coupled to the media device, the method continues by transcoding at least a portion of the buffered subset of the media content at the media device and providing the transcoded subset of the media content to the destination device.

Abstract: A distributed computing system for artificial intelligence in relating a second multimedia program content with a first multimedia program content based on a key reference. A user terminal is set up locally in a user's environment to monitor a first multimedia program content consumed by the user. The user's reaction to a portion of the first multimedia program content is detected by the user terminal. The relevant portion of the first multimedia program content is identified and parsed to obtain a reference portion. The reference portion is related to a second multimedia portion using database mapping and machine learning.

Abstract: A media transfer method includes establishing a data connection between a mobile device and an accessory device such that the accessory device acts as a host configured to control access to first content stored within the accessory device. A a request for the first content is sent from the mobile device to the accessory device. In response to the request for the first content, the method includes sending, from the accessory device, the first content to the mobile device via the data connection, wherein first content is sent as a first transaction comprising a single header and a plurality of headerless data packets.

Abstract: A video services receiver and related operating methods are presented here. The video services receiver is configured to maintain a database that indicates a viewing pattern for a user of the video services receiver. The video services receiver is configured to detect a condition that is inconsistent with the maintained viewing pattern for the user. In response to the detection of an inconsistent condition, the video services receiver records a designated program event included in the viewing pattern for the user, wherein the recording addresses the detected condition. In some scenarios, the receiver buffers the designated program event to allow the user to view the entirety of the buffered program event. In other scenarios, the receiver records the designated program event and sends a notification to the user when the receiver determines that the user is absent or is not viewing any programming from the receiver.

Abstract: A video services receiver and related operating methods are presented here. The video services receiver is configured to maintain a database that indicates a viewing pattern for a user of the video services receiver. The video services receiver is configured to detect a condition that is inconsistent with the maintained viewing pattern for the user. In response to the detection of an inconsistent condition, the video services receiver records a designated program event included in the viewing pattern for the user, wherein the recording addresses the detected condition. In some scenarios, the receiver buffers the designated program event to allow the user to view the entirety of the buffered program event. In other scenarios, the receiver records the designated program event and sends a notification to the user when the receiver determines that the user is absent or is not viewing any programming from the receiver.

Abstract: Systems, devices and methods are described to obtain a lower-quality replacement when the reception of a direct broadcast satellite (DBS) or other broadcast television signal becomes weak or unavailable due to weather, maintenance or other circumstances. The received broadcast television signal is monitored by a receiver, antenna, outdoor unit or the like. When the received broadcast signal becomes weak or unavailable, the television receiver obtains a lower quality replacement for received broadcast signal from a network service or other alternate source to thereby continue the playback of the television program. Lower quality alternatives may include lower quality video streams, audio streams, text tickers, web pages or the like.

Abstract: Systems, devices and methods are described to obtain a lower-quality replacement when the reception of a direct broadcast satellite (DBS) or other broadcast television signal becomes weak or unavailable due to weather, maintenance or other circumstances. The received broadcast television signal is monitored by a receiver, antenna, outdoor unit or the like. When the received broadcast signal becomes weak or unavailable, the television receiver obtains a lower quality replacement for received broadcast signal from a network service or other alternate source to thereby continue the playback of the television program. Lower quality alternatives may include lower quality video streams, audio streams, text tickers, web pages or the like.