# US 2015/0104023 A1 · Generating A Reference Audio Fingerprint For An Audio Signal Associated With An Event

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2015/0104023 A1
- Document ID: US20150104023A1
- Status: Published application
- Kind: A1
- Application number: 14/052,521
- Filed: 2013-10-11
- Published: 2015-04-16
- Earliest claimed: 2013-10-11
- Assignees: Facebook, Inc., a Delaware corporation
- Applicants: Facebook, Inc., a Delaware corporation
- Inventors: Sergiy Bilobrov
- Web page: https://patentgrep.com/patent/US20150104023A1

## CPC

- G10L 25/54: for retrieval
- G06F 16/683: using metadata automatically derived from the content
- H04R 3/04: for correcting frequency response
- H04R 29/00: Monitoring arrangements; Testing arrangements {(for hearing aids H04R25/30; detection of loudspeaker connection H04R5/04; sound-field adaptation dependent on speaker detection H04S7/308)}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K)

## Abstract

An audio identification system generates a reference audio fingerprint associated with an event. The reference audio fingerprint is generated from samples of an audio signal associated with the event captured by multiple devices. To generate the reference audio fingerprint, fingerprints are generated from each sample, and the generated fingerprints are temporally aligned. Fingerprints associated a temporally overlapping portion of the audio signal are averaged, and the average value is associated with the temporally overlapping portion of the audio signal and included in the reference audio fingerprint. The reference audio fingerprint is stored along with identifying information, such as an event name, an event time, an event date, or other information describing the event associated with the audio signal from which the samples were captured.

## Claims

### Claim 1

A computer-implemented method comprising:
obtaining a plurality of samples of one or more audio signals, each sample representing a portion of an audio signal and associated with identifying information;
identifying a plurality of samples of an audio signal associated with an event based on the identifying information associated with the samples;
generating an audio fingerprint based on each of the identified plurality of samples;
combining the generated audio fingerprints into a temporally aligned series;
generating a reference audio fingerprint associated with the event by averaging audio fingerprints in the temporally aligned series associated with overlapping time intervals; and
storing the reference audio fingerprint and an association between the reference audio fingerprint and information describing the event.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein identifying the plurality of samples of an audio signal associated with an event based on the identifying information associated with the samples comprises:
identifying a plurality of samples associated with a location and associated with times within a specified time interval.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the information describing the event is selected from a group consisting of: a name of the event, a location associated with the event, a time associated with the event, one or more users of a social networking system associated with the event, and any combination thereof.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, further comprising:
receiving a test audio fingerprint generated from an audio signal;
comparing the test audio fingerprint to the reference audio fingerprint associated with the event; and
associating the information describing the event with the audio signal if the test audio fingerprint matches the reference audio fingerprint associated with the event.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, further comprising:
associating the information describing the event with a user of a social networking system; and
describing the user and the information describing the event to one or more additional users of the social networking system connected to the user.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, wherein describing the user and the information describing the event comprises:
generating a story indicating that the user is associated with the described event; and
providing the generated story to the one or more additional users connected to the user.

### Claim 7 (depends on 6)

The computer-implemented method of claim 6, wherein the generated story is included in a newsfeed presented to at least one of the one or more additional users.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein combining the generated audio fingerprints into a temporally aligned series comprises:
determining a bit error rate for each pairing of generated audio fingerprints; and
ordering the generated audio fingerprints based at least in part on the determined bit error rates so a bit error rate of adjacent generated audio fingerprints is minimized.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein generating a reference audio fingerprint associated with the event by averaging audio fingerprints in the temporally aligned series associated with overlapping time intervals comprises:
identifying audio fingerprints associated with an overlapping time interval;
determining an average value of the audio fingerprints associated with the overlapping time interval; and
storing the average value in association with the overlapping time interval.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, wherein the plurality of samples of the audio signal associated with the event were obtained from a plurality of client devices.

### Claim 11

A computer-implemented method comprising:
obtaining a plurality of samples of an audio signal associated with an event from a plurality of client devices associated with a plurality of different users;
generating an audio fingerprint based on each of the plurality of samples;
combining the generated audio fingerprints into a temporally aligned series;
generating a reference audio fingerprint associated with the event by averaging audio fingerprints in the temporally aligned series associated with overlapping time intervals; and
storing the reference audio fingerprint and an association between the reference audio fingerprint and information describing an event associated with the audio signal.

### Claim 12 (depends on 11)

The computer-implemented method of claim 11, wherein the information describing the event is selected from a group consisting of: a name of the event, a location associated with the event, a time associated with the event, one or more users of a social networking system associated with the event, and any combination thereof.

### Claim 13 (depends on 11)

The computer-implemented method of claim 11, further comprising:
receiving a test audio fingerprint generated from an audio signal;
comparing the test audio fingerprint to the reference audio fingerprint associated with the event; and
associating the information describing the event with the audio signal if the test audio fingerprint matches the reference audio fingerprint associated with the event.

### Claim 14 (depends on 11)

The computer-implemented method of claim 11, wherein combining the generated audio fingerprints into a temporally aligned series comprises:
determining a bit error rate for each pairing of generated audio fingerprints; and
ordering the generated audio fingerprints based at least in part on the determined bit error rates so a bit error rate of adjacent generated audio fingerprints is minimized.

### Claim 15 (depends on 11)

The computer-implemented method of claim 11, wherein generating a reference audio fingerprint associated with the event by averaging audio fingerprints in the temporally aligned series associated with overlapping time intervals comprises:
identifying audio fingerprints associated with an overlapping time interval;
determining an average value of the audio fingerprints associated with the overlapping time interval; and
storing the average value in association with the overlapping time interval.

### Claim 16 (depends on 1)

The computer-implemented method of claim 1, wherein at least a subset of client devices in the plurality of client devices are associated with different geographic locations.

### Claim 17

A system comprising:
a processor; and
a computer readable storage medium coupled to the processor, the computer readable storage medium having instructions encoded thereon that, when executed by the processor, cause the processor to:
receive a plurality of samples of an audio signal, the samples received from one or more client devices;
generate an audio fingerprint based on each of the plurality of samples;
combine the generated audio fingerprints into a temporally aligned series; and
generate a reference audio fingerprint associated with the event by averaging audio fingerprints in the temporally aligned series associated with overlapping time intervals.

### Claim 18 (depends on 17)

The system of claim 17, wherein a plurality of the one or more client devices are associated with different geographic locations.

### Claim 19 (depends on 17)

The system of claim 17, wherein the information describing the event is selected from a group consisting of: a name of the event, a location associated with the event, a time associated with the event, one or more users of a social networking system associated with the event, and any combination thereof.

### Claim 20 (depends on 17)

The system of claim 17, wherein the instructions, when executed by the processor to cause the processor to combine the generated audio fingerprints into a temporally aligned series, further cause the processor to:
determine a bit error rate for each pairing of generated audio fingerprints; and
order the generated audio fingerprints based at least in part on the determined bit error rates so a bit error rate of adjacent generated audio fingerprints is minimized.
