VIDEO CONTEXTUAL ADVERTISEMENTS USING SPEECH RECOGNITION

• US 20090199235A1
• Filed: 06/06/2008
• Published: 08/06/2009
• Est. Priority Date: 02/01/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Mahajan, Milind V., Surendran, Arungunram C., Nguyen, Patrick
• Granted Patent: US 8,190,479 B2
• Time in Patent Office: Days
• US Class Current: 725/34
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0271 Personalized advertisement
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04N 21/440236 by media transcoding, e.g. video is transformed into a slideshow of still pictures, audio is converted into text
• CPC Class Codes: H04N 21/4668 for recommending content, e.g. movies
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02
• CPC Class Codes: H04N 21/8405 represented by keywords

Abstract

Embodiments of a computer-implemented advertisement display system are disclosed. In one embodiment, the system includes a speech recognition component that processes a video clip and produces a corresponding collection of speech recognition data indicative of an audio portion of the video clip. The system also includes a collection of advertising material. An advertisement selection component selects an advertisement from the collection of advertising material based on the corresponding collection of speech recognition data. The system also includes a display. An advertisement presentation component displays an indication of the selected advertisement on the display during a simultaneous display of the video clip.

Claims

1. A computer-implemented advertisement display system, the system comprising:

a speech recognition component that processes a video clip and produces a corresponding collection of speech recognition data indicative of an audio portion of the video clip;

a collection of advertising material;

an advertisement selection component that selects an advertisement from the collection of advertising material based on the corresponding collection of speech recognition data;

a display; and

an advertisement presentation component that displays an indication of the selected advertisement on the display during a simultaneous display of the video clip.

2. The system of claim 1, wherein the corresponding collection of speech recognition data is a transcript of words recognized by the speech recognition component as being spoken during the audio portion of the video clip.

3. The system of claim 1, wherein the corresponding collection of speech recognition data is an acoustic representation of words spoken during the audio portion of the video clip.

4. The system of claim 2, wherein the indication of the selected advertisement is a highlighted word included within a copy of the transcript, the highlighted word being selectable so as to trigger a display of advertising material.

5. The system of claim 1, wherein the advertisement presentation component times the initial display of the indication of the selected advertisement to coincide with the video clip reaching a beginning of a conversation about a predetermined subject matter topic.

6. The system of claim 1, wherein advertisement presentation component times the initial display of the indication of the selected advertisement to coincide with the video clip reaching a point where a predetermined speaker begins speaking.

7. The system of claim 1, wherein the advertisement presentation component transitions from the selected advertisement to a different advertisement based on a corresponding transition in the video clip from a first subject matter topic to a different subject matter topic.

8. The system of claim 1, wherein the advertisement presentation component transitions from the selected advertisement to a different advertisement based on a corresponding transition in the video clip from one person speaking to another person speaking.

9. The system of claim 1, further comprising:

a conversation analysis component that processes the transcript and identifies a subject matter topic addressed during the video clip;

wherein when the advertisement selection component selects the advertisement, it does so as a function of the subject matter topic, an indication of which it receives from the conversation analysis component.

10. The system of claim 1, further comprising:

an acoustic analysis component that processes speech contained in the video clip and identifies a speaker that is a source of speech during the video clip;

wherein when the advertisement selection component selects the advertisement, it does so as a function of the speaker, an indication of which it receives from the conversation analysis component.

11. The system of claim 1, wherein when the advertisement selection component selects the advertisement, it does so by determining that a word that appears in the corresponding transcript is a key word to which the advertisement is to be assigned.

12. The system of claim 1, wherein when the advertisement selection component selects the advertisement, it does so by evaluating a monetary value of a word that appears in the corresponding transcript.

13. A computer-implemented method of displaying advertisements, the method comprising:

receiving a video clip;

processing the audio portion of the video clip so as to divide the video clip into a first chapter and a second chapter based on at least one characteristic of the audio portion;

assigning a first advertisement to the first chapter and a second advertisement to the second chapter;

displaying an indication of the first advertisement during a simultaneous display of the first chapter of the video clip; and

timing a transition from the display of the first advertisement to a display of the second advertisement when the video clip transitions from the first chapter to the second chapter.

14. The method of claim 13, wherein processing the audio portion of the video clip so as to divide the video clip comprises processing the audio portion so as to divide the video clip based on an identified transition between two subject matter topics during the video clip.

15. The method of claim 13, wherein processing the audio portion of the video clip so as to divide the video clip comprises processing the audio portion so as to divide the video clip based a transition between speakers during the video clip.

16. The method of claim 13, further comprising displaying a textual transcript of the audio portion of the video clip while the video is being displayed.

17. The method of claim 16, wherein displaying an indication of the first advertisement during a simultaneous display of the first chapter of the video clip comprises hyperlinking at least one keyword contained within the displayed textual transcript.

18. An advertisement selection component that selects an advertisement from a collection of advertising material based on a collection of speech recognition data, wherein the collection of speech recognition data corresponds to a chapter of a video clip, the chapter being less than all of the video clip.

19. The advertisement selection component of claim 18, wherein the collection of speech recognition data corresponds to a subject matter topic identified as being discussed during the chapter of the video clip.

20. The advertisement selection component of claim 18, wherein the collection of speech recognition data corresponds to a particular speaker identified as being the person speaking during the chapter of the video clip.