Comcast Cable Communications, LLC

George Thomas Des Jardins

Vikrant Sagar

Erik Schwartz

Scot Gregory Zola

Edward David Monnerat

Mehul S Patel

Jonathan Alan Leech

Wenyan Li

Ferhan Ture

Jose Casillas

Methods and apparatus for improving speech recognition accuracy in media content searches are described. An advertisement for a media content item is analyzed to identify keywords that may describe the media content item. The identified keywords are associated with the media content item for use during a voice search to locate the media content item. A user may speak the one or more of the keywords as a search input and be provided with the media content item as a result of the search.

Content analysis to enhance search

According to some aspects, disclosed methods and systems may include determining, by a device and based on historical data associated with a first user, a first user profile comprising one or more content recommendation periods each associated with a time period and a content classification, and in response to detecting a user interaction, selecting a first content recommendation period of the one or more content recommendation periods. The methods and system may also include determining one or more content candidates corresponding to the content classification from a plurality of content assets based on an amount of remaining time in the time period associated with the first content recommendation period and a correlation between the historical data associated with the first user and one or more contextual features associated with the plurality of content assets, and transmitting, to a client device, an indication of the one or more content candidates.

Dynamic content recommendations

A system for removing noise from an audio signal is described. For example, noise caused by content playing in the background during a voice command or phone call may be removed from the audio signal representing the voice command or phone call. By removing noise, the signal to noise ratio of the audio signal may be improved.

Removal of audio noise

This application describes methods, systems, and apparatus for allowing a user to easily determine whether the user and/or other user(s) have viewed content. For example, a program guide may display one or more graphics associated with the content (e.g., a movie poster), and in response to determining whether the user has viewed the content, the program guide may include an indication of whether the user has viewed the content. The program guide may include indications associated with multiple users (e.g., different colors, icons, graphics, or text). The program guide may filter the content based on whether the user has viewed the content (e.g., only display content the user has not viewed). A computing device storing the content may manage recording of the content based on whether the user has viewed the content (e.g., delete the recording if the user has viewed the content). A viewing history of the user may be maintained.

Content viewing tracking

Methods for automatically evaluating ASR outputs and providing annotations, including corrections, on the transcriptions—in order to improve recognition—may be based on an analysis of sessions of user voice queries, utilizing time-ordered ASR transcriptions of user voice queries (i.e., user utterances). This utterance-based approach may involve extracting both session-level and query-level characteristics from a voice query sessions and identifying patterns of query reformulation in order to detect erroneous transcriptions and automatically determine an appropriate correction. Alternative, or in addition, ASR outputs may be evaluated based on user behavior. The outcomes may be classified as positive or negative. An ASR transcription may be labeled using the description of the outcome. The labeled transcription may be used as training data to train a model to output improved transcriptions of voice queries.

Systems and methods for training voice query models

According to some aspects, disclosed methods and systems may include having a user input one or more speech commands into an input device of a user device. The user device may communicate with one or more components or devices at a local office or headend. The local office or the user device may transcribe the speech commands into language transcriptions. The local office or the user device may determine a mood for the user based on whether any of the speech commands may have been repeated. The local office or the user device may determine, based on the mood of the user, which content asset or content service to make available to the user device.

Determination of content services

Content analysis to enhance voice search

Systems and methods are described for processing and interpreting audible commands spoken in one or more languages. Speech recognition systems disclosed herein may be used as a stand-alone speech recognition system or comprise a portion of another content consumption system. A requesting user may provide audio input (e.g., command data) to the speech recognition system via a computing device to request an entertainment system to perform one or more operational commands. The speech recognition system may analyze the audio input across a variety of linguistic models, and may parse the audio input to identify a plurality of phrases and corresponding action classifiers. In some embodiments, the speech recognition system may utilize the action classifiers and other information to determine the one or more identified phrases that appropriately match the desired intent and operational command associated with the user's spoken command.

Dynamic language and command recognition

Systems and methods are described for processing and interpreting commands spoken in one or more languages. Speech recognition systems disclosed herein may be used as a stand-alone speech recognition system or comprise a portion of another content consumption system. The speech recognition system receives audio data associated with a multi-language command. The speech recognition system analyzes the audio data across a variety of linguistic models, and parses the audio data to determine a match phrase, of a plurality of phrases associated with a plurality of operational commands. The speech recognition system utilizes classifiers and/or other information to determine one or more phrases that appropriately match the desired intent and operational command associated with the user's spoken command.

Growing community of inventors

Washington, DC, United States of America

George Thomas Des Jardins