发明名称 Audio media mood visualization
摘要 An audio media visualization method and system. The method includes receiving by a computing processor, mood description data describing different human emotions/moods. The computer processor an audio file comprising audio data and generates a mood descriptor file comprising portions of the audio data associated with specified descriptions of the mood description data. The computer processor receives a mood tag library file comprising mood tags mapped to animated and/or still objects representing various emotions/moods and associates each animated and/or still object with an associated description. The computer processor synchronizes the animated and/or still objects with the portions of said audio data and presents the animated and/or still objects synchronized with the portions of said audio data.
申请公布号 US9235918(B2) 申请公布日期 2016.01.12
申请号 US201514596494 申请日期 2015.01.14
申请人 International Business Machines Corporation 发明人 Abuelsaad Tamer E.;Moore, Jr. John E.;Singi Rajeshkumar N.;Wentworth Robert R.
分类号 G06T13/20;G06F3/16 主分类号 G06T13/20
代理机构 Schmeiser, Olsen & Watts 代理人 Schmeiser, Olsen & Watts ;Chung Matthew
主权项 1. A method comprising: receiving, by a computer processor of a computing apparatus, an audio file comprising audio data presented by an author; generating, by said computer processor, a mood descriptor file comprising portions of said audio data associated with specified descriptions of mood description data describing different human emotions/moods; receiving, by said computer processor, a mood tag library file comprising mood tags describing and mapped to mood based annotations comprising animated video images representing various emotions/moods; associating, by said computer processor based on said mood tags, each animated video image of said animated video images with an associated description of said specified descriptions; synchronizing, by said computer processor based on results of said associating, said animated video images with said portions of said audio data associated with said specified descriptions; first presenting, by said computer processor to a listener, said animated video images synchronized with said portions of said audio data associated with said specified descriptions; second presenting, by said computer processor to said listener at various intervals during said first presenting, specified video and/or audio messages; third presenting, by said computer processor to said listener after completion of said first presenting and said second presenting, questions associated with said specified video and/or audio messages; and determining, by said computer processor based on responses to said questions from the listener, if said listener has listened to all of said portions of said audio data.
地址 Armonk NY US