Using speech recognition to determine advertisements relevant to audio content and/or audio content relevant to advertisements

• US 20070078708A1
• Filed: 09/30/2005
• Published: 04/05/2007
• Est. Priority Date: 09/30/2005
• Status: Abandoned Application

• Current Assignee: Google Inc. (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Yu, Hua, Moreno, Pedro
• Application Number:
  US11/241,834
• Publication Number:
  US 20070078708A1
• Time in Patent Office: Days
• US Class Current: 705/14.690
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0273 Determination of fees for advertising

Abstract

Serving advertisements with (e.g., in) audio documents may be improved by (a) accepting at least a portion of a document including audio content, (b) analyzing the audio content to determine relevancy information for the document, and (c) determining at least one advertisement relevant to the document using at least the relevancy information and serving constraints associated with advertisements. The advertisements may be scored if more than one advertisement was determined to be relevant to the document. Then, at least one of the advertisements to be served with an ad spot for the document may be determined using at least the scores. Examples of documents include radio programs, live or recorded musical works with lyrics, live or recorded dramatic works with dialog or a monolog, live or recorded talk shows, voice mail, segments of an audio conversation, etc. The audio content may be analyzed to determine relevancy information for the document by converting the audio content to textual information using speech recognition. Then, relevancy information may be determined from the textual information.

Claims

1. A computer-implemented method comprising:

a) accepting at least a portion of a document including audio content;

b) analyzing the audio content to determine relevancy information for the document;

c) determining at least one advertisement relevant to the document using at least the relevancy information and serving constraints associated with advertisements.

2. The computer-implemented method of claim 1 further comprising:

d) if more than one advertisement was determined to be relevant to the document, then further scoring the advertisements; and

e) determining, using at least the scores, at least one of the advertisements to be served with an ad spot for the document.

3. The computer-implemented method of claim 2 wherein the act of scoring the advertisements determines scores using offer information associated with each of the advertisements.

4. The computer-implemented method of claim 3 wherein the offer information is one of (A) a price per impression, and (B) a maximum price per impression.

5. The computer-implemented method of claim 1 wherein the serving constraint associated with the advertisements includes at least one targeting keyword.

6. The computer-implemented method of claim 1 wherein the serving constraint associated with the advertisements includes at least one targeting topic.

7. The computer-implemented method of claim 1 wherein the document is a radio program.

8. The computer-implemented method of claim 1 wherein the document includes a live or recorded musical work with lyrics.

9. The computer-implemented method of claim 1 wherein the document includes a live or recorded dramatic work with dialog or a monolog.

10. The computer-implemented method of claim 1 wherein the document includes a live or recorded talk show.

11. The computer-implemented method of claim 1 wherein the document includes a voice mail.

12. The computer-implemented method of claim 1 wherein the document includes a segment of an audio conversation.

13. The computer-implemented method of claim 1 wherein the act of analyzing the audio content to determine relevancy information for the document includes

i) converting the audio content to textual information using speech recognition, and

ii) determining relevancy information from the textual information.

14. The computer-implemented method of claim 13 wherein the act of determining relevancy information from the textual information includes generating a term vector from the textual information.

15. The computer-implemented method of claim 13 wherein the act of determining relevancy information from the textual information includes generating a weighted term vector from the textual information.

16. The computer-implemented method of claim 13 wherein the act of determining relevancy information from the textual information includes determining one or more clusters from the textual information.

17. The computer-implemented method of claim 13 wherein the act of determining relevancy information from the textual information includes determining one or more probabilistic hierarchical inferential learner clusters from the textual information.

18. The computer-implemented method of claim 13 wherein the act of determining relevancy information from the textual information includes determining one or more categories from the textual information.

19. The computer-implemented method of claim 13 wherein the act of determining relevancy information from the textual information includes determining one or more vertical categories from the textual information.

20. The computer-implemented method of claim 1 wherein the document including audio content is streamed from a source to a client device, and

wherein the act of analyzing the audio content to determine relevancy information for the document occurs while the document is being streamed.

21. The computer-implemented method of claim 1 wherein the document including audio content is streamed from a source to a client device, and

wherein the act of analyzing the audio content to determine relevancy information for the document occurs before the document is streamed.

22. The computer-implemented method of claim 1 wherein the audio document includes spoken information, and

wherein the act of analyzing the audio content to determine relevancy information for the document includes inferring a user gender from the spoken information.

23. The computer-implemented method of claim 1 wherein the audio document includes spoken information, and

wherein the act of analyzing the audio content to determine relevancy information for the document includes inferring at least one of (A) a user nationality, and (B) a user ethnicity from the spoken information.

24. Apparatus comprising:

a) means for accepting at least a portion of a document including audio content;

b) means for analyzing the audio content to determine relevancy information for the document; and

c) means for determining at least one advertisement relevant to the document using at least the relevancy information and serving constraints associated with advertisements.

25. The apparatus of claim 24 further comprising:

d) means for scoring the advertisements if more than one advertisement was determined to be relevant to the document; and

e) means for determining, using at least the scores, at least one of the advertisements to be served with an ad spot for the document.

26. The apparatus of claim 24 wherein the means for analyzing the audio content to determine relevancy information for the document include

i) means for converting the audio content to textual information using speech recognition, and

ii) means for determining relevancy information from the textual information.