发明名称 Method of processing a text, gesture, facial expression, and/or behavior description comprising a test of the authorization for using corresponding profiles for synthesis
摘要 The invention relates to a method of processing a text, gesture, facial expression, and/or behavior description wherein the text, gesture, facial expression, and/or behavior description is synthesized by means of a speech, gesture, facial expression, and/or behavior profile, provided that an authorization code legitimizes the use of the speech, gesture, facial expression, and/or behavior profile for the synthesis.
申请公布号 US9092885(B2) 申请公布日期 2015.07.28
申请号 US200210479555 申请日期 2002.06.05
申请人 Nuance Communications, Inc. 发明人 Scholl Holger
分类号 G10L13/00;G10L25/00;G10L21/00;H04L9/32;G06F7/04;G06T13/00;G10L21/06 主分类号 G10L13/00
代理机构 Wolf, Greenfield & Sacks, P.C. 代理人 Wolf, Greenfield & Sacks, P.C.
主权项 1. A method carried out by a processor for processing text, hand gesture, facial expression, and behavior descriptions, wherein the processor is programmed to perform the method as a result of execution of program instructions, the method comprising acts of: selecting, based on a first input from a user, a profile from a plurality of predetermined profiles, wherein each profile in the plurality of predetermined profiles is associated with a respective personality; determining, based on a second input from the user, the text, hand gesture, facial expression, and behavior descriptions; and synthesizing speech and at least one moving image using both: the text, hand gesture, facial expression, and behavior descriptions determined based on the second input from the user, andthe profile selected based on the first input from the user, wherein the selected profile comprises information indicative of speech, hand gesture, facial expression, and behavior characteristics of the personality associated with the selected profile,provided that an authorization code received from the user legitimizes use of the selected profile for the act of synthesizing, wherein the authorization code is associated with the selected profile, and wherein at least one description selected from a group consisting of the text, hand gesture, facial expression, and behavior descriptions is obtained by performing a recognition process on one or more picture signals based on the second input from the user.
地址 Burlington MA US