CPC G10L 15/197 (2013.01) [G10L 15/26 (2013.01)] | 21 Claims |
1. A system comprising:
a processor; and
a memory coupled to the processor, the memory comprising computer executable instructions that, when executed by the processor, performs a method comprising:
detecting an access of audio content by a user, wherein the access of the audio content causes auditory presentation of the audio content to the user;
identifying an acronym in the audio content;
searching for the acronym and for a corresponding acronym expansion for the acronym in user-specific content, the user-specific content including a document associated with the user;
determining that the acronym is not familiar to the user;
generating a first confidence score for the corresponding acronym expansion based on a user-specific context, the user-specific context including at least one of the user's recency of interaction with the document and a user interaction type with respect to the document;
comparing the first confidence score to a threshold value;
determining that the first confidence score does not meet the threshold value;
upon determining that the first confidence score does not meet the threshold value, generating a second confidence score for the corresponding acronym expansion based on a global context;
generating a total confidence score for the corresponding acronym expansion by combining the first confidence score with the second confidence score; and
based on the total confidence score, dynamically substituting the corresponding acronym expansion for the acronym during the auditory presentation of the audio content.
|