Method and apparatus for identificaton of broadcast source

• US 7,986,913 B2
• Filed: 02/18/2005
• Issued: 07/26/2011
• Est. Priority Date: 02/19/2004
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Landmark Digital Services LLC
• Inventors: Wang, Avery Li-Chun
• Primary Examiner(s): SOBUTKA, PHILIP
• Application Number:
  US10/589,543
• Publication Number:
  US 20070143777A1
• Time in Patent Office: 2,349 Days
• Field of Search: None
• US Class Current: 455/2.01
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04B 17/23 Indication means, e.g. displays, alarms, audible means
• CPC Class Codes: H04H 20/71 Wireless systems
• CPC Class Codes: H04H 20/88 Stereophonic broadcast systems multiplex system in general H04J
• CPC Class Codes: H04H 2201/50 characterised by the use of watermarks
• CPC Class Codes: H04H 2201/90 characterised by the use of signatures
• CPC Class Codes: H04H 60/27 Arrangements for recording or accumulating broadcast information or broadcast-related information
• CPC Class Codes: H04H 60/37 for identifying segments of broadcast information, e.g. scenes or extracting programme ID
• CPC Class Codes: H04H 60/43 for identifying broadcast channels
• CPC Class Codes: H04H 60/44 for identifying broadcast stations
• CPC Class Codes: H04H 60/58 of audio determination or detection of speech characteristics in general G10L25/00; speech recognition in general G10L15/00
• CPC Class Codes: H04H 60/63 for services of sales data processing systems or methods specially adapted for electronic commerce G06Q30/00

Abstract

A user (102) hears an audio program being broadcast and can record a sample of the audio. The sample is then conveyed to an analyzing means (106) to determine to which broadcast station the user is listening. The analyzing means monitors many broadcast channels. Thus, characteristics of the audio sample and samples taken from the broadcast channels can be compared to find a match. Broadcast information pertaining to the broadcast channel from which the match was found may then be reported back to the user, combined with an advertisement of a promotion, prize notification, discount offers, and other information specific for a certain radio station for example.

Claims

1. A method for identifying a broadcast source of content comprising:

receiving an audio sample and a time at which the audio sample was recorded, the audio sample being a rendition of a segment of an original recording;

identifying characteristics of the audio sample and an estimated time offset of the audio sample, the estimated time offset of the audio sample defining a time difference between a beginning of the original recording and a beginning of the audio sample;

comparing the characteristics and the estimated time offset of the audio sample with characteristics and time offsets of broadcast samples taken from broadcast stations at approximately the time at which the audio sample was recorded, each of the time offsets of the broadcast samples defining a time difference between a beginning of a broadcast sample and a beginning of a corresponding original recording; and

based on the comparison, identifying a broadcast station from which the audio sample was broadcast.

2. The method of claim 1, wherein identifying the broadcast station from which the audio sample was broadcast comprises:

identifying a broadcast sample from the broadcast samples taken from the broadcast stations that has characteristics which most closely match the characteristics of the audio sample; and

selecting the broadcast station from which the identified broadcast sample was taken to be the broadcast station from which the audio sample was broadcast.

3. The method of claim 2, wherein the step of comparing comprises comparing characteristics and the estimated time offset of the audio sample with the characteristics and the time offset of each broadcast sample.

4. The method of claim 1, wherein upon identifying a sample from the samples taken from the broadcast stations that has characteristics which substantially match the characteristics of the audio sample, the step of identifying a broadcast station comprises selecting the broadcast station from which the identified broadcast sample was taken to be the broadcast station from which the audio sample was broadcast.

5. The method of claim 1, further comprising comparing an identity of the audio sample with identities of the broadcast samples taken from the broadcast stations.

6. The method of claim 1, further comprising reporting information relating to the broadcast station to a user who recorded the audio sample.

7. The method of claim 6, wherein the broadcast information includes an advertisement.

8. The method of claim 1, further comprising:

continually recording broadcast samples from each of the broadcast stations;

recording a time at which each of the broadcast samples was recorded;

identifying characteristics of each of the broadcast samples; and

identifying an estimated time offset of each of the broadcast samples.

9. The method of claim 1 further comprising:

recording the audio sample over a transition between audio programs on the same broadcast station;

comparing the transition within the audio sample with transitions within the broadcast samples taken from the broadcast stations; and

identifying a content alignment between the transition within the audio sample and at least one transition within a broadcast sample taken from the broadcast stations.

10. A method for identifying a broadcast source of content comprising:

comparing an identity of an audio sample with identities of broadcast audio samples taken from broadcast channels being monitored;

comparing a time offset of the audio sample with time offsets of the broadcast audio samples, wherein a time offset of a sample defines a relative time offset of the sample plus an elapsed time between when the sample was taken and a common reference time, wherein the sample corresponds to a segment of a media file and the time offset of the sample defines a time difference between a beginning of the media file and a beginning of the sample; and

based on substantially matching identities and substantially matching time offsets, identifying a broadcast channel from which the audio sample was recorded.

11. The method of claim 10, further comprising:

identifying variations in the audio sample, the variations including non-music material superimposed upon the audio sample; and

comparing the variations in the audio sample with variations in the broadcast audio samples.

12. The method of claim 10, further comprising:

identifying an identity change within the audio sample; and

comparing a first identify of the audio sample with identities of the broadcast audio samples, and comparing a second identity of the audio sample with identities of the broadcast audio samples.

13. The method of claim 10, further comprising:

determining a stretch factor of the audio sample, the stretch factor defining a difference between a speed at which the audio sample was broadcast and a speed of an original playback of the audio sample; and

comparing the stretch factor of the audio sample with stretch factors of the broadcast audio samples.

14. The method of claim 10, further comprising collecting broadcast audio samples from the broadcast channels at time intervals such that at least one audio sample is taken per audio program for each broadcast channel.

15. The method of claim 10, further comprising reporting the broadcast channel to a user.

16. A monitoring station comprising:

broadcast channel samplers for sampling audio from respective broadcast stations;

an audio recognition engine for determining characteristics of the audio sampled from the respective broadcast stations, and for determining an estimated time offset of the audio between a beginning of an original recording from which the audio sample was taken and a time at which the audio sample was taken; and

a processor for (i) receiving a user audio sample, (ii) comparing the characteristics and the estimated time offset of the audio sampled from the respective broadcast stations and taken at approximately the time at which the user audio sample was recorded with characteristics and a time offset of the user audio sample, and (iii) based on the comparisons, identifying a broadcast station from which the user audio sample was broadcast.

17. The monitoring station of claim 16, wherein the broadcast channel samplers sample the audio from the respective broadcast stations on a continual basis.

18. The monitoring station of claim 16, wherein the broadcast channel samplers sample the audio from the respective broadcast stations at time intervals such that at least one audio sample is taken per audio program for each respective broadcast station.

19. The monitoring station of claim 16, further comprising memory for storing the characteristics of the audio sampled from the respective broadcast stations and the estimated time offset of the audio sampled from the respective broadcast stations.

20. The monitoring station of claim 19, wherein after a predetermined amount of time, the monitoring station writes over stored information of the audio sampled from the respective broadcast stations to refresh the information so as to coordinate stored information with audio samples currently being broadcast.

21. The monitoring station of claim 16, wherein the processor receives a recording of the user audio sample.

22. The monitoring station of claim 16, wherein the processor receives the characteristics of the user audio sample.

23. The monitoring station of claim 22, wherein the processor is also operable to compare an identity of the user audio sample with identities of the audio sampled from the respective broadcast stations.

24. A method for identifying a broadcast source of content comprising:

recording an audio sample;

recording a time at which the audio sample was recorded;

identifying characteristics of the audio sample and an estimated time offset of the audio sample, the estimated time offset defining a time difference between a beginning of a corresponding identified content file and when the recording of the audio sample begins;

recording audio samples from each of a plurality of broadcast stations;

recording a time at which each of the audio samples from each of the plurality of broadcast stations was sampled;

identifying characteristics and estimated time offsets of the broadcast samples from each of the plurality of broadcast stations, each estimated time offset of the broadcast samples defining a time difference between a beginning of a corresponding identified content file and when the respective recording of the respective broadcast sample begins;

comparing the characteristics and the estimated time offset of the audio sample with the characteristics and the estimated time offsets of the broadcast samples taken from the plurality of broadcast stations at approximately the time at which the audio sample was recorded; and

based on the comparison, identifying a broadcast station from which the audio sample was broadcast.