# US 10,482,877 B2 · Remote sensor voice recognition

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

- Number: US 10,482,877 B2
- Document ID: US10482877B2
- Status: Granted
- Kind: B2
- Application number: 15/754,270
- Filed: 2015-08-28
- Published: 2018-08-23
- Granted: 2019-11-19
- Earliest claimed: 2015-08-28
- Assignees: Hewlett-Packard Development Company, L.P.
- Applicants: Hewlett-Packard Development Company, L.P.
- Inventors: David H. Hanes
- Web page: https://patentgrep.com/patent/US10482877B2

## CPC

- G10L 15/20: Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech (G10L21/02 takes precedence)
- G10L 15/28: Constructional details of speech recognition systems
- G10L 17/22: Interactive procedures; Man-machine interfaces
- G10L 21/0208: Noise filtering
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Examples described herein include systems, methods, and devices for transmitting a media signal to the remote sensor, receiving a sound signal from the remote sensor, and monitoring the sound signal and the media signal to recognize voice commands.

## Claims

### Claim 1

A computing device comprising:
a processor; and
a non-transitory computer readable medium coupled to the processor and comprising instructions that when executed by the processor cause the processor to:
establish a bi-directional wireless communication link between the computing device and a remote sensor comprising a speaker and a microphone, the remote sensor separate from the computing device;
transmit a first audio signal to the remote sensor for playback on the speaker;
receive a second audio signal from the microphone in the remote sensor;
process the second audio signal to generate a processed audio signal;
send the processed audio signal to a voice recognition routine to recognize a voice command within the processed audio signal; and
initiate an automation command controlling the first audio signal transmitted to the remote sensor for playback on the speaker, based on the recognized voice command,
wherein the processor is to process the second audio signal to generate the processed audio signal by:
detecting the first audio signal within the second audio signal;
determining a time delay between the first audio signal as transmitted to the remote sensor and the first audio signal as detected within the second audio signal;
time-shifting the first audio signal as detected within the second audio signal according to the determined time delay; and
subtracting the time-shifted first audio signal as detected within the second audio signal from the second audio signal,
and wherein the computing device is to both transmit the first audio signal to the remote sensor and receive back the second audio signal from the remote sensor.

### Claim 2 (depends on 1)

The computing device of claim 1 wherein the second audio signal comprises ambient sounds detected by the microphone.

### Claim 3 (depends on 2)

The computing device of claim 2 wherein the ambient sounds comprises the first audio signal played on the speaker.

### Claim 4

A method comprising:
transmitting, by a computer system, for playback on a speaker of a remote sensor a first audio signal to the remote sensor over a bi-directional wireless communication link between the computer system and the remote sensor, the remote sensor separate from the computer system;
receiving, by the computer system, a second audio signal detected at a microphone of the remote sensor, the second audio signal received by the computing system from the remote sensor over the bi-directional wireless communication link;
processing, by the computer system, the second audio signal to generate a process audio signal;
recognizing, by the computer system, recognizable voice commands within the processed audio signal;
initiating, by the computer system, automation commands controlling the first audio signal transmitted to the remote sensor for playback on the speaker, based on the recognizable voice commands that have been recognized,
wherein processing the second audio signal to generate the processed audio signal comprises:
detecting within the second audio signal a third audio signal transmitted to a second remote sensor for playback at the second remote sensor, the second audio signal different from the first audio signal;
detecting within the second audio signal the first audio signal; and
subtracting the detected first audio signal and the detected third audio signal from the second audio signal,
and wherein the computing system is to both transmit the first audio signal to the remote sensor and receive back the second audio signal from the remote sensor.