Reference content determination from audio content
AssigneeAudible, Inc.
InventorRobert Patrick Tierney
Life of this patent
Estimating the term…
Abstract
Systems and methods are provided for causing aural and/or visual presentation of reference content, such as word definitions, in response to a request regarding a portion of media content during playback. In some embodiments, one or more words may be determined that may be of interest to the user from among words in a content window preceding a current playback position in the content, without the user specifying a specific word of interest. A presentation of reference content corresponding to the determined one or more words may be generated and presented aurally and/or visually in order to provide definitions, encyclopedia information, summary information, and/or other information regarding a portion of media content near the current playback position.
Claims25
A system comprising:
- an electronic dictionary data store configured to at least store a definition for each of a plurality of words;
- and
- a computing system comprising one or more hardware computing devices, said computing system in communication with the electronic dictionary data store, and configured to at least:
- receive a definition request initiated by a user during playback of an audio book, wherein the definition request comprises a current playback position associated with the audio book;
- determine text data representing a plurality of words spoken in a subset of the audio book preceding the current playback position;
- select, from the text data, a word to define, wherein the word to define has a highest word score among words appearing in the text data, wherein the highest word score is based at least in part on at least one of (a) a number of times the word appears in a collection of content or (b) a number of times the word is searched in a dictionary;
- retrieve a definition from the electronic dictionary data store for the word to define;
- and
- generate content for presentation that comprises the retrieved definition.
A system comprising:
- an electronic reference content data store configured to at least store reference content for each of a plurality of words;
- and
- a computing system comprising one or more hardware computing devices, said computing system in communication with the electronic reference content data store, and configured to at least:
- receive a reference content request initiated during playback of media content;
- determine text data representing a plurality of words spoken in a subset of the media content preceding a current playback position within the media content;
- select a word with a highest word score among words appearing in the text data, wherein the highest word score is based at least in part on at least one of (a) a number of times the word appears in a collection of content or (b) a number of times the word is searched in a reference source;
- retrieve reference content from the electronic reference content data store for the word;
- and
- generate content for presentation that comprises the retrieved reference content.
A computer-implemented method comprising:
- as implemented by one or more computing devices configured with specific executable instructions,
- receiving a reference content request initiated during playback of media content;
- in response to the reference content request, determining text data representing a plurality of words spoken in a subset of the media content relative to a current playback position within the media content;
- selecting, from the text data, a term with a highest term score, wherein the highest term score is based at least in part on at least one of (a) a number of times the term appears in a collection of content or (b) a number of times the term is searched in a reference source;
- retrieving reference content associated with the term;
- and
- generating content for presentation that comprises the retrieved reference content.
A computer-readable, non-transitory storage medium storing computer executable instructions that, when executed by one or more computing devices, configure the one or more computing devices to perform operations comprising:
- receiving a reference content request initiated during playback of media content;
- in response to the request, determining text data representing a plurality of words spoken in a subset of the media content relative to a current playback position within the media content;
- selecting, from the text data, a term with a highest term score, wherein the highest term score is based at least in part on at least one of (a) a number of times the term appears in a collection of content or (b) a number of times the term is searched in a reference source;
- retrieving reference content for the term;
- and
- generating content for presentation that comprises the retrieved reference content.
Dependencies are inferred from the claim text.