Abstract: As a media program is aired to listeners, a control system monitors audio data transmitted to the listeners and interactions received from the listeners to determine whether the media program has violated or may violate one or more rules. The audio data is processed to identify words expressed therein and features of the audio data. Additionally, features of users (e.g., a creator or any listeners or guests) may be calculated based on any information or data available regarding such users. An embedding is formed with data representing the words, the audio features and the user features, and provided to a model trained to determine whether a media program is at risk of violating any rules. One or more actions are selected and executed or recommended based on a score generated by the model representing a level of risk that a rule has been, is being or will be violated.

Abstract: The present disclosure describes techniques for dynamically determining when information is to be output to a user, as well as what information is to be output to a user. A natural language processing system may receive, from a first device, first data representing information to be output at a first point during a skill session. The natural language processing system may also receive, from a second device, second data representing a natural language input. The natural language processing system may determine a skill component is to execute with respect to the natural language input. The natural language processing system may send, to the skill component, second data representing the natural language input. The natural language processing system may receive, from the skill component, an indication that an ongoing first skill session with the second device has reached the first point.

Abstract: Method and apparatus for detecting text encoding errors caused by previously encoding the electronic document in multiple encoding formats. Non-word portions are removed from the electronic document. Embodiments determine whether words in the electronic document are likely to contain one or more text encoding errors, by dividing the first word into n-grams of length 2 or more. For each of the plurality of n-grams, a database is queried to determine a respective probability of the n-gram appearing in each of a plurality of recognized languages, and upon determining that the determined probabilities of two consecutive n-grams are each less than a predefined threshold probability, the first word is added to a list of words that likely contain text encoding errors. A confidence level that the first word includes the one or more text encoding errors is calculated, based on a lowest determined probably for the n-grams for the first word.

Abstract: The present disclosure describes techniques for dynamically determining when information is to be output to a user, as well as what information is to be output to a user. A natural language processing system may receive, from a first device, first data representing information to be output at a first point during a skill session. The natural language processing system may also receive, from a second device, second data representing a natural language input. The natural language processing system may determine a skill component is to execute with respect to the natural language input. The natural language processing system may send, to the skill component, second data representing the natural language input. The natural language processing system may receive, from the skill component, an indication that an ongoing first skill session with the second device has reached the first point.

Abstract: Systems, methods, and computer-readable media are disclosed for systems and methods for intelligent content rating determination. Example methods include determining presence of a first feature in a first frame of a video using an object recognition algorithm, determining presence of a second feature in an audio file associated with the video using an audio processing algorithm, and determining presence of a third feature in a text file associated with the video using a natural language processing algorithm. Certain embodiments may include generating a predicted content rating for the video using a machine learning model, where the predicted content rating is based at least in part on the first feature, the second feature, and the third feature, and using feedback data for the predicted content rating to retrain the machine learning model.

Abstract: The present disclosure describes techniques for dynamically determining when information is to be output to a user, as well as what information is to be output to a user. A natural language processing system may receive, from a first device, first data representing information to be output at a first point during a skill session. The natural language processing system may also receive, from a second device, second data representing a natural language input. The natural language processing system may determine a skill component is to execute with respect to the natural language input. The natural language processing system may send, to the skill component, second data representing the natural language input. The natural language processing system may receive, from the skill component, an indication that an ongoing first skill session with the second device has reached the first point.

Abstract: Systems, methods, and computer-readable media are disclosed for systems and methods for intelligent content rating determination. Example methods include determining presence of a first feature in a first frame of a video using an object recognition algorithm, determining presence of a second feature in an audio file associated with the video using an audio processing algorithm, and determining presence of a third feature in a text file associated with the video using a natural language processing algorithm. Certain embodiments may include generating a predicted content rating for the video using a machine learning model, where the predicted content rating is based at least in part on the first feature, the second feature, and the third feature, and using feedback data for the predicted content rating to retrain the machine learning model.