Method and apparatus for multimedia content filtering

Abstract

Method and apparatus for multimedia content filtering are described herein. In one embodiment, an example of a network access device, in response to multimedia content transmitted from a source over a first network and destined to a destination over a second network, opens the multimedia content within the network access device interfacing the first and second networks. A content rating operation is performed on the opened multimedia content to determine whether the multimedia content should be transmitted to the destination over the second network. Other methods and apparatuses are also described.

What is claimed is: 
     
         1 . A method for multimedia content filtering, the method comprising:
 receiving at a network access device, a stream of multimedia content transmitted from a source over a first network and destined for a destination over a second network; and   executing instructions stored in memory of the network access device, wherein execution of the instructions by a processor:
 extracts audio content from the multimedia content in real-time while the multimedia content is streaming, 
 recognizes an audio pattern within the extracted audio content, 
 determines that the stream of multimedia content should not be completed based on a policy associated with the recognized audio pattern, and 
 terminates the stream of the multimedia content. 
   
     
     
         2 . The method of  claim 1 , wherein the determination that the stream of media content should not be completed is performed on a packet level. 
     
     
         3 . The method of  claim 1 , further comprising extracting other multi-media content in real-time for filtering. 
     
     
         4 . The method of  claim 3 , wherein the other multi-media content includes images. 
     
     
         5 . The method of  claim 3 , wherein the other multi-media content includes video content. 
     
     
         6 . The method of  claim 1 , wherein the determination that the stream of media content should not be completed is based on a list of vocabulary or semantics found to be offensive to a user. 
     
     
         7 . The method of  claim 1 , wherein the determination that the stream of media content should not be completed is customizable around one or more of the following: specific users, groups, IP subnets, or time. 
     
     
         8 . A non-transitory machine readable storage medium having embodied thereon executable code that when executed causes a machine to perform a method for multimedia content filtering, the method comprising:
 receiving at a network access device, a stream of multimedia content transmitted from a source over a first network and destined for a destination over a second network;   extracting audio content from the multimedia content in real-time while the multimedia content is streaming;   recognizing an audio pattern within the extracted audio content, determining that the stream of multimedia content should not be completed based on a policy associated with the recognized audio pattern, and   terminating the stream of the multimedia content.   
     
     
         9 . The non-transitory machine readable storage medium of  claim 8 , wherein the determination that the stream of media content should not be completed is performed on a packet level. 
     
     
         10 . The non-transitory machine readable storage medium of  claim 8  further comprising extracting other multi-media content in real-time for filtering. 
     
     
         11 . The non-transitory machine readable storage medium of  claim 10 , wherein the other multi-media content includes images. 
     
     
         12 . The non-transitory machine readable storage medium of  claim 10 , wherein the other multi-media content includes video content. 
     
     
         13 . The non-transitory machine readable storage medium of  claim 8 , wherein the determination that the stream of media content should not be completed is based on a list of vocabulary or semantics found to be offensive to a user. 
     
     
         14 . The non-transitory machine readable storage medium of  claim 8 , wherein the determination that the stream of media content should not be completed is customizable around one or more of the following: specific users, groups, IP subnets, or time. 
     
     
         15 . A system for multimedia content filtering, the system comprising:
 a network access device that receives a stream of multimedia content transmitted from a source over a first network and destined for a destination over a second network;   an audio codec that extracts audio content from the multimedia content in real-time while the multimedia content is streaming;   a speech recognition engine that recognizes an audio pattern within the extracted audio content; and   a content filtering unit that:
 determines that the stream of multimedia content should not be completed based on a policy associated with the recognized audio pattern, and 
 terminates the stream of the multi media content. 
   
     
     
         16 . The system of  claim 15 , wherein the determination that the stream of media content should not be completed is performed on a packet level. 
     
     
         17 . The system of  claim 15 , further comprising extracting other multi-media content in real-time for filtering. 
     
     
         18 . The system of  claim 17 , wherein the other multi-media content includes images. 
     
     
         19 . The system of  claim 17 , wherein the other multi-media content includes video content. 
     
     
         20 . The system of  claim 15 , wherein the determination that the stream of media content should not be completed is based on a list of vocabulary or semantics found to be offensive to a user. 
     
     
         21 . The system of  claim 15 , wherein the determination that the stream of media content should not be completed is customizable around one or more of the following: specific users, groups, IP subnets, or time.