公开(公告)号：CA2567505A1

公开(公告)日：2008-05-09

申请号：CA2567505

申请日：2006-11-09

Applicant: IBM CANADA

Inventor： BOYLE CURRIE ,  ZHANG YU

IPC: G11B27/02 ,  G06F40/00 ,  G06T1/00 ,  G10L13/00

Abstract: There is disclosed a system and method for interpreting and describing graph ic images. In an embodiment, the method of inserting a description of an image into an audio recording, includes interpreting an image and producing a word description o f the image including at least one image keyword; parsing an audio recording into a plurality of audio clips, and producing a transcription of each audio clip, each audio clip transcription including at least one audio keyword; calculating a similarity distance between the at least one image keyword and the at least one audio keyword of each audio clip; and selecting the audio clip transcription having the shortest similarity distance to the at least one image keyword as the location to insert the word description of the image. The word description o f the image may then be appended to the selected audio clip to produce an augmented audio recording including the interpreted word description of the image.