Identifying and generating audio cohorts based on audio data input

• US 8,301,443 B2
• Filed: 11/21/2008
• Issued: 10/30/2012
• Est. Priority Date: 11/21/2008
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Angell, Robert Lee, Friedlander, Robert R, Kraemer, James R
• Primary Examiner(s): Han, Qi
• Application Number:
  US12/275,830
• Publication Number:
  US 20100131263A1
• Time in Patent Office: 1,439 Days
• Field of Search: 704/9, 704/231, 704/245, 704/257, 704/278, 704/272
• US Class Current: 704/231
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence

Abstract

A computer implemented method, apparatus, and computer program product for generating audio cohorts. An audio analysis engine receives audio data from a set of audio input devices. The audio data is associated with a plurality of objects. The audio data comprises a set of audio patterns. The audio data is processed to identify attributes of the audio data to form digital audio data. The digital audio data comprises metadata describing the attributes of the audio data. A set of audio cohorts is generated using the digital audio data and cohort criteria. Each audio cohort in the set of audio cohorts comprises a set of objects from the plurality of objects that share at least one audio attribute in common.

Claims

1. A computer implemented method of generating audio cohorts, computer implemented method comprising:

receiving audio data from a set of audio sensors, by an audio analysis engine, wherein the audio data is associated with a plurality of objects, and wherein the audio data comprises a set of audio patterns;

processing the audio data to identify audio attributes associated with the plurality of objects to form digital audio data, wherein the digital audio data comprises metadata describing the audio attributes of the set of objects, wherein the audio attributes of the audio data comprise an identification of a sound, wherein the sound is identified as human speech, and wherein the audio attributes of the audio data identify one of sound identifications from a group consisting of a language spoken, a regional dialect associated with the human speech, an accent associated with the human speech, an identification of whether the speaker is male or female, an identification of words spoken in the human speech, and an identification of a vocalized breathing sound; and

generating a set of audio cohorts using the audio attributes associated with the digital audio data and cohort criteria, wherein each audio cohort in the set of audio cohorts comprises a set of objects from the plurality of objects that share at least one audio attribute in common.

2. The computer implemented method of claim 1, wherein the audio attributes of the audio data comprise sound wave properties, wherein a sound wave property is at least one of frequency, wavelength, amplitude, intensity, speed, and direction of a sound associated with an object in the plurality of objects.

3. The computer implemented method of claim 1, wherein the audio attributes of the audio data comprise an origin of a sound, and wherein the audio attributes of the audio data identify whether the origin of the sound is outdoors or indoors based on a presence or absence of an echo.

4. The computer implemented method of claim 1, wherein the audio data is a first set of audio data generated at a first time interval, and further comprising:

receiving a second set of audio data taken at a second time interval; and

processing the first audio data and the second audio data to generate the digital audio data, wherein the digital audio data describes audio attributes of the first audio data and the second audio data.

5. The computer implemented method of claim 1, further comprising:

receiving the set of audio cohorts by an inference engine; and

processing the set of audio cohorts by the inference engine, wherein the inference engine uses the set of audio cohorts to generate a set of inferences, and wherein the set of inferences predict a future event.

6. The computer implemented method of claim 1, wherein identifying the set of audio cohorts using the digital audio data and the cohort criteria further comprises:

analyzing the digital audio data using cohort constraints with the cohort criteria, by a cohort generation engine, to identify the set of audio cohorts.

7. The computer implemented method of claim 1, wherein identifying the set of audio cohorts using the digital audio data further comprises:

analyzing the digital audio data in a set of cohort generation data models, by a cohort generation engine, to identify the set of audio cohorts, wherein the set of cohort generation data models processes and identifies attributes of sounds associated with vibrations, wherein the set of cohort generation data models identifies customers speaking a particular language.

8. The computer implemented method of claim 1, wherein the set of cohorts comprises a sound wave property cohort, wherein each object in the sound wave property cohort shares common sound wave attributes, and wherein the common sound wave attributes comprise at least two of a frequency, a wavelength, an amplitude, an intensity, a speed, and a direction of a sound associated with said each object in the sound wave property cohort.

9. The computer implemented method of claim 1, further comprising:

processing the audio data to identify a cohort of accompanied customers, wherein accompanied customers are accompanied by a child while shopping.

10. The computer implemented method of claim 1, further comprising:

processing the audio data to identify a medical condition of a patient, wherein the audio data comprises vocalized abnormal breathing sounds from the patient.

11. A computer program product for generating audio cohort data, the computer program product comprising:

a computer usable storage device having computer usable program code embodied therewith, the computer usable program code comprising;

computer usable program code configured to receive audio data from a set of audio sensors, by an audio analysis engine, wherein the audio data is associated with a plurality of objects, and wherein the audio data comprises a set of audio patterns;

computer usable program code configured to process the audio data to identify audio attributes associated with the plurality of objects to form digital audio data, wherein the digital audio data comprises metadata describing the audio attributes of the set of objects, wherein the audio attributes of the audio data comprise an identification of a sound, wherein the sound is identified as human speech, and wherein the audio attributes of the audio data identify one of sound identifications from a group consisting of a language spoken, a regional dialect associated with the human speech, an accent associated with the human speech, an identification of whether the speaker is male or female, an identification of words spoken in the human speech, and an identification of a vocalized breathing sound;

computer usable program code configured to generate a set of audio cohorts using the audio attributes associated with the digital audio data and cohort criteria, wherein each audio cohort in the set of audio cohorts comprises a set of objects from the plurality of objects that share at least one audio attribute in common;

computer usable program code configured to receive the set of audio cohorts by an inference engine; and

computer usable program code configured to process the set of audio cohorts by the inference engine, wherein the inference engine uses the set of audio cohorts to generate a set of inferences, and wherein the set of inferences predict a future event.

12. The computer program product of claim 11, wherein the audio attributes of the audio data comprises sound wave properties, wherein a sound wave property is at least one of frequency, wavelength, amplitude, intensity, speed, and direction of a sound.

13. The computer program product of claim 11, wherein the audio attributes of the audio data comprise an origin of a sound.

14. The computer program product of claim 11 further comprising:

computer usable program code for processing the audio data to identify a medical condition of a patient, wherein the audio data comprises vocalized abnormal breathing sounds from the patient.

15. An apparatus comprising:

a bus system;

a communications system coupled to the bus system;

a memory connected to the bus system, wherein the memory includes computer usable program code; and

a processing unit coupled to the bus system, wherein the processing unit executes the computer usable program code to receive audio data from a set of audio sensors, by an audio analysis engine, wherein the audio data is associated with a plurality of objects, and wherein the audio data comprises a set of audio patterns;

process the audio data to identify audio attributes associated with the plurality of objects to form digital audio data, wherein the digital audio data comprises metadata describing the audio attributes of the set of objects, wherein the audio attributes of the audio data comprise an identification of a sound, wherein the sound is identified as human speech, and wherein the audio attributes of the audio data identify one of sound identifications from a group consisting of a language spoken, a regional dialect associated with the human speech, an accent associated with the human speech, an identification of whether the speaker is male or female, an identification of words spoken in the human speech, and an identification of a vocalized breathing sound;

generate a set of audio cohorts using the audio attributes associated with the digital audio data and cohort criteria, wherein each audio cohort in the set of audio cohorts comprises a set of objects from the plurality of objects that share at least one audio attribute in common;

receive the set of audio cohorts by an inference engine; and

process the set of audio cohorts by the inference engine, wherein the inference engine uses the set of audio cohorts to generate a set of inferences, and wherein the set of inferences predict a future event.

16. The apparatus of claim 15 wherein the audio attributes of the audio data comprise an identification of a sound, an origin of the sound, and sound wave properties of the sound, wherein a sound wave property is at least one of frequency, wavelength, amplitude, intensity, speed, and direction of the sound.

17. An audio cohort generation system comprising:

a set of audio sensors, wherein the set of audio sensors comprises a microphone;

a data processing system, wherein the data processing system comprises;

an audio analysis engine, wherein the audio analysis engine receives audio data from a set of audio sensors, wherein the audio data is in an analog format, and wherein the audio data identifies a set of audio patterns associated with a plurality of objects;

processes the audio data and identify audio attributes of the audio data to form digital audio data, wherein the digital audio data comprises metadata describing the audio attributes associated with the plurality of objects, wherein the audio attributes of the audio data comprise an identification of a sound, wherein the sound is identified as human speech, and wherein the audio attributes of the audio data identify one of sound identifications from a group consisting of a language spoken, a regional dialect associated with the human speech, an accent associated with the human speech, an identification of whether the speaker is male or female, an identification of words spoken in the human speech, and an identification of a vocalized breathing sound;

a cohort generation engine, wherein the cohort generation engine generates a set of audio cohorts using the digital audio data and cohort criteria, wherein each audio cohort in the set of audio cohorts comprises a set of objects from the plurality of objects that share at least one audio attribute in common; and

an inference engine, wherein the inference engine uses the set of audio cohorts to generate a set of inferences, and wherein the set of inferences predict a future event.