Systems and Methods for Automated Media Commentary

摘要

Techniques for providing automated media commentary are provided. A user agent requests audio commentary for media. In response, a service searches data sources to identify the specified media, finds information related to those entities, generates text that represents those information, combines the text into a textual monologue, and synthesizes speech audio from that textual monologue. The service selects relevant information to be likely unknown to the user while also being desired by the user.

主权项

1. A computer-implementable method for generating audible information related to media, the method comprising:
sending a request for audible commentary to a service from a user agent controlled by a user; retrieving the user's media history, information history, search states; sampling segments of a search space comprising data sources; selecting novel information in the search space; generating utterances based on a the selected novel information; constructing a textual monolog from the generated utterances; synthesizing speech from the textual monolog; playing the synthesized speech for the user; and updating the user's media history, information history, and search states after confirmation that the user received the monolog.