# US 2017/0287470 A1 · Analysis of long-term audio recordings

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

- Number: US 2017/0287470 A1
- Document ID: US20170287470A1
- Status: Published application
- Kind: A1
- Application number: 15/084,070
- Filed: 2016-03-29
- Published: 2017-10-05
- Earliest claimed: 2016-03-29
- Assignees: Sensory, Incorporated
- Applicants: Sensory, Incorporated
- Inventors: Bryan Pellom; Todd F. Mozer
- Web page: https://patentgrep.com/patent/US20170287470A1

## CPC

- G10L 15/08: Speech classification or search
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06Q 30/0269: {based on user profile or attribute}
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 17/06: Decision making techniques; Pattern matching strategies
- G10L 17/00: Speaker identification or verification techniques
- G10L 2015/088: {Word spotting}
- G10L 2015/226: {using non-speech characteristics}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

Techniques for analyzing long-term audio recordings are provided. In one embodiment, a computing device can record audio captured from an environment of a user on a long-term basis (e.g., on the order of weeks, months, or years). The computing device can store the recorded audio on a local or remote storage device. The computing device can then analyze the recorded audio based one or more predefined rules and can enable one or more actions based on that analysis.

## Claims

### Claim 1

A method comprising:
recording, by a computing device, audio captured from an environment of a user on a continuous, long-term basis;
storing the recorded audio on a local or remote storage device;
analyzing the recorded audio based on or more predefined rules; and
enabling one or more actions based on the analyzing of the recorded audio.

### Claim 2 (depends on 1)

The method of claim 1 wherein the audio is captured from the environment of the user over a continuous time period spanning one or more weeks, months, or years.

### Claim 3 (depends on 1)

The method of claim 1 wherein analyzing the recorded audio comprises one or more of:
detecting one or more or more sounds of interest and identifying times in the recorded audio at which the sounds are detected;
identifying known or unknown speakers;
tagging portions of the audio with a GPS location;
tagging portions of the audio with calendar events of the user that are known to the computing device;
detecting one or more keywords of interest and identifying times in the recorded audio at which the sounds are detected; or
transcribing recognized speech.

### Claim 4 (depends on 1)

The method of claim 1 wherein enabling one or more actions based on the analyzing comprises:
receiving a query pertaining to the user and the recorded audio;
processing the query based on the recorded audio and metadata generated from the analyzing; and
returning a query result.

### Claim 5 (depends on 4)

The method of claim 4 wherein the query relates to the user's condition, preferences, or environment.

### Claim 6 (depends on 4)

The method of claim 4 wherein the query is a search request pertaining to an event, speaker, sound, or keyword of interest in the recorded audio.

### Claim 7 (depends on 1)

The method of claim 1 wherein enabling one or more actions based on the analyzing comprises:
automatically updating a profile associated with the user.

### Claim 8 (depends on 7)

The method of claim 7 where the updated profile is used to target one or more advertisements to the user.

### Claim 9 (depends on 1)

The method of claim 1 further comprising:
recording audio captured from an environment of one or more other users or user groups on a continuous, long-term basis; and
comparing the recorded audio for the various users or user groups based on one or more predefined criteria.

### Claim 10

A non-transitory computer readable medium having stored thereon program code executable by a processor of a computing device, the program code comprising cod that causes the processor to:
record audio captured from an environment of a user on a continuous, long-term basis;
store the recorded audio on a local or remote storage device;
analyze the recorded audio based on or more predefined rules; and
enable one or more actions based on the analyzing of the recorded audio.

### Claim 11 (depends on 10)

The non-transitory computer readable medium of claim 10 wherein the audio is captured from the environment of the user over a continuous time period spanning one or more weeks, months, or years.

### Claim 12 (depends on 10)

The non-transitory computer readable medium of claim 10 wherein the code that causes the processor to analyze the recorded audio comprises code that causes the processor to:
detect one or more or more sounds of interest and identifying times in the recorded audio at which the sounds are detected;
identify known or unknown speakers;
tag portions of the audio with a GPS location;
tag portions of the audio with calendar events of the user that are known to the computing device;
detect one or more keywords of interest and identifying times in the recorded audio at which the sounds are detected; or
transcribe recognized speech.

### Claim 13 (depends on 10)

The non-transitory computer readable medium of claim 10 wherein the code that causes the processor to enable one or more actions based on the analyzing comprises code that causes the processor to:
receive a query pertaining to the user and the recorded audio;
process the query based on the recorded audio and metadata generated from the analyzing; and
return a query result.

### Claim 14 (depends on 13)

The non-transitory computer readable medium of claim 13 wherein the query relates to the user's condition, preferences, or environment.

### Claim 15 (depends on 13)

The non-transitory computer readable medium of claim 13 wherein the query is a search request pertaining to an event, speaker, sound, or keyword of interest in the recorded audio.

### Claim 16 (depends on 10)

The non-transitory computer readable medium of claim 10 wherein the code that causes the processor to enable one or more actions based on the analyzing comprises code causes the processor to:
automatically update a profile associated with the user.

### Claim 17 (depends on 16)

The non-transitory computer readable medium of claim 16 where the updated profile is used to target one or more advertisements to the user.

### Claim 18 (depends on 10)

The non-transitory computer readable medium of claim 10 wherein the program code further comprises code that causes the processor to:
record audio captured from an environment of one or more other users or user groups on a continuous, long-term basis; and
compare the recorded audio for the various users or user groups based on one or more predefined criteria.

### Claim 19

A computing device comprising:
a microphone; and
a processor configured to:
record audio captured via the microphone from an environment of a user on a continuous, long-term basis;
store the recorded audio on a local or remote storage device;
analyze the recorded audio based on or more predefined rules; and
enable one or more actions based on the analyzing of the recorded audio.

### Claim 20 (depends on 19)

The computing device of claim 19 wherein the audio is captured from the environment of the user over a continuous time period spanning one or more weeks, months, or years.

### Claim 21 (depends on 19)

The computing device of claim 19 wherein analyzing the recorded audio comprises one or more of:
detecting one or more or more sounds of interest and identifying times in the recorded audio at which the sounds are detected;
identifying known or unknown speakers;
tagging portions of the audio with a GPS location;
tagging portions of the audio with calendar events of the user that are known to the computing device;
detecting one or more keywords of interest and identifying times in the recorded audio at which the sounds are detected; or
transcribing recognized speech.

### Claim 22 (depends on 19)

The computing device of claim 19 wherein enabling one or more actions based on the analyzing comprises:
receiving a query pertaining to the user and the recorded audio;
processing the query based on the recorded audio and metadata generated from the analyzing; and
returning a query result.

### Claim 23 (depends on 22)

The computing device of claim 22 wherein the query relates to the user's condition, preferences, or environment.

### Claim 24 (depends on 22)

The computing device of claim 22 wherein the query is a search request pertaining to an event, speaker, sound, or keyword of interest in the recorded audio.

### Claim 25 (depends on 19)

The computing device of claim 19 wherein enabling one or more actions based on the analyzing comprises:
automatically updating a profile associated with the user.

### Claim 26 (depends on 25)

The computing device of claim 25 where the updated profile is used to target one or more advertisements to the user.

### Claim 27 (depends on 19)

The computing device of claim 19 wherein the processor is further configured to:
record audio captured from an environment of one or more other users or user groups on a continuous, long-term basis; and
compare the recorded audio for the various users or user groups based on one or more predefined criteria.
