ENGINE, SYSTEM AND METHOD OF PROVIDING AUDIO TRANSCRIPTIONS FOR USE IN CONTENT RESOURCES

• US 20150255065A1
• Filed: 03/10/2015
• Published: 09/10/2015
• Est. Priority Date: 03/10/2014
• Status: Abandoned Application

• Current Assignee: Veritone Media
• Original Assignee: Veritone Media
• Inventors: Steelberg, Chad
• Application Number:
  US14/643,580
• Publication Number:
  US 20150255065A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: H04N 21/234336 by media transcoding, e.g. video is transformed into a slideshow of still pictures or audio is converted into text
• CPC Class Codes: H04N 21/251 Learning process for intelligent management, e.g. learning user preferences for recommending movies details of learning user preferences for the retrieval of video data in a video database G06F16/739; computer systems using learning methods G06N3/08
• CPC Class Codes: H04N 21/2668 Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles information retrieval from the Internet by querying with filtering and personalisation G06F16/9535; arrangements for replacing or switching information during the broadcast H04H20/10; push services over packet-switching network H04L12/1859; adaptation of message content in packet-switching networks H04L51/063
• CPC Class Codes: H04N 21/4316 for displaying supplemental content in a region of the screen, e.g. an advertisement in a separate window
• CPC Class Codes: H04N 21/8405 represented by keywords
• CPC Class Codes: H04N 21/8456 by decomposing the content in the time domain, e.g. in time segments

Abstract

The present invention relates to the transcription of audio, and, more particularly, to an engine, system and method of providing audio transcriptions for use in content resources.

Claims

1. A method of providing content, comprising:

receiving a stream comprising media content;

chunking the received stream into media snippets of a predetermined length, wherein each media snippet is keyed to at least one keyword;

automatically, and substantially commensurate with said receiving of the stream, generating a transcript for each of the media snippets;

providing the transcript, and the media snippet uniquely corresponded thereto, for access by a user.

2. The method of claim 1, wherein the media content consists of audio.

3. The method of claim 1, wherein the media content comprises video.

4. The method of claim 1, wherein the predetermined length is one of three, five, or seven minutes.

5. The method of claim 1, wherein said providing comprises posting to the cloud.

6. The method of claim 1, wherein said providing comprises providing an html link in a browser window.

7. The method of claim 1, wherein said providing comprises at least springing a secondary browser window substantially consisting of the transcript.

8. The method of claim 1, wherein said providing comprises providing in a search engine results window, responsive to a search by the user.

9. The method of claim 1, wherein said providing comprises a native providing of the transcript and the media snippet, absent generation of intermediate content to enable said providing.

10. A method of publishing content, comprising:

publishing a content stream comprising at least audio content and keywords indicative of the audio content to a transcription engine for transcription of the audio content;

matching the audio content uniquely to the transcription;

allowing for the providing of at least the audio content and, distinct therefrom, the matched transcription, to a requesting user at a time substantially commensurate with said publishing.

11. A method of providing social media content, comprising:

receiving a plurality of streams, each comprising media content;

assessing at least one keyword relevant to each of the plurality of streams;

programmatically channelizing each of the plurality of received streams into a plurality of channels based upon the respective at least one keyword;

automatically, and substantially commensurate in time with said programmatically channelizing, generating a transcript for each of the channels;

providing the transcript, and the channel uniquely corresponded thereto, for access by a user as the social media content.

12. The method of claim 11, wherein said programmatically channelizing further comprises assessing at least one trend according to appearances of the at least one keyword across multiple ones of the plurality of streams.

13. The method of claim 12, wherein the appearances comprise a quantitative number of appearances.

14. The method of claim 12, wherein the appearances comprise a qualitative assessment of appearances.

15. A method of receiving content, comprising:

receiving a plurality of streams, each comprising media content;

receiving an indication of at least one keyword relevant to each of the plurality of streams, wherein the indication further comprises at least one trend related to the at least one keyword;

programmatically channelizing, for ultimate consumption by a social media user, of each of the plurality of received streams into a plurality of channels based upon the respective at least one trend;

receiving a transcript for each of the channels for ultimate consumption by the social media user substantially commensurate in time with the ultimate consumption by the social media user of the channel.

16. A non-transitory computing system comprising code for execution by at least one computing processor, wherein execution of the code by the at least one processor provides:

an audio content layer capable of receiving a plurality of audio streams;

a broadcast layer capable of transceiving broadcasted ones of the plurality of audio streams over at least three different broadcast means;

an application programming interface (API) layer capable of manipulating broadcasted ones of the plurality of audio streams to provide a plurality of end-user applications, wherein the manipulating comprises at least a transcription of at least portions of each of the broadcasted ones of the plurality of audio streams and at least one selected from the group consisting of a quantitative appearance in the portions of each of the broadcasted ones of the plurality of audio streams, a qualitative appearance in the portions of each of the broadcasted ones of the plurality of audio streams, a geography of interest in the portions of each of the broadcasted ones of the plurality of audio streams, a geography of generation of the portions of each of the broadcasted ones of the plurality of audio streams, an audience profile of the portions of each of the broadcasted ones of the plurality of audio streams, and a verification of the content of the portions of each of the broadcasted ones of the plurality of audio streams.

17. A non-transitory computing system comprising code for execution by at least one computing processor, wherein execution of the code by the at least one processor provides a media asset conversion comprising the steps of:

receiving a stream comprising media content;

chunking the received stream into media snippets of a predetermined length, wherein each media snippet is keyed to at least one keyword;

automatically, and substantially commensurate with said receiving of the stream, generating a transcript for each of the media snippets;

providing the transcript, and the media snippet uniquely corresponded thereto, for access by a user.