# US 2022/0044691 A1 · Voice recognition device, control method of voice recognition device, content reproducing device, and content transmission/reception system

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

- Number: US 2022/0044691 A1
- Document ID: US20220044691A1
- Status: Published application
- Kind: A1
- Application number: 17/414,194
- Filed: 2018-12-18
- Published: 2022-02-10
- Earliest claimed: 2018-12-18
- Assignees: Nissan Motor Co., Ltd.; RENAULT s.a.s.
- Applicants: Nissan Motor Co., Ltd.; Renault S.A.S.
- Inventors: Hideo Omura
- Web page: https://patentgrep.com/patent/US20220044691A1

## CPC

- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 17/26: Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
- G10L 25/69: for evaluating synthetic or decoded voice signals
- G10L 25/81: for discriminating voice from music
- G10L 25/84: for discriminating voice from noise
- G10L 19/018: Audio watermarking, i.e. embedding inaudible data in the audio signal
- G10L 25/93: Discriminating between voiced and unvoiced parts of speech signals (G10L25/90 takes precedence)
- G10L 2015/223: {Execution procedure of a spoken command}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A voice analyzer analyzes whether a voice signal input into a voice input unit includes a specific characteristic component. A voice recognizer recognizes a voice represented by the voice signal input into the voice input unit. A response instruction unit instructs a response to a response operation unit that operates in response to the voice recognized by the voice recognizer. A controller controls the voice recognizer not to execute voice recognition processing by the voice recognizer or controls the response instruction unit not to instruct the response operation unit about an instruction content by the voice recognized by the voice recognizer, when the voice analyzer analyzes that the voice signal includes the specific characteristic component.

## Claims

### Claim 1

A voice recognition device comprising:
a voice input unit into which a voice signal is input;
a voice analyzer configured to analyze whether a specific characteristic component is included in the voice signal input into the voice input unit;
a voice recognizer configured to recognize a voice represented by the voice signal input into the voice input unit;
a response instruction unit configured to instruct a response to a response operation unit that operates in response to the voice recognized by the voice recognizer;
a controller configured to control the voice recognizer not to execute voice recognition processing by the voice recognizer or to control the response instruction unit not to instruct the response operation unit about an instruction content by the voice recognized by the voice recognizer, when the voice analyzer analyzes that the voice signal includes the specific characteristic component; and
a reproducing device detection unit configured to detect presence of a content reproducing device including a voice output unit,
wherein the voice analyzer analyzes whether the voice signal input into the voice input unit includes the specific characteristic component when the reproducing device detection unit detects the presence of the content reproducing device.

### Claim 2

(canceled)

### Claim 3 (depends on 1)

The voice recognition device according to claim 1,
wherein the specific characteristic component is an artificial waveform component superimposed on the voice signal at a predetermined time interval.

### Claim 4 (depends on 1)

The voice recognition device according to claim 1,
wherein the voice signal is a voice signal included in a content of television broadcasting, radio broadcasting, or internet broadcasting.

### Claim 5

(canceled)

### Claim 6

A control method of a voice recognition device by a processor comprising:
detecting whether a content reproducing device including a voice output unit reproduces a content;
analyzing whether a specific characteristic component is included in a voice signal input into a voice input unit when it is detected that the content reproducing device reproduces a content;
recognizing a voice by executing voice recognition processing of the voice represented by the voice signal input into the voice input unit when it is detected that the voice signal does not include the specific characteristic component;
instructing a response to a response operation unit that operates in response to a recognized voice; and
performing control not to execute the voice recognition processing of the voice represented by the voice signal input into the voice input unit or perform control not to instruct the response operation unit about an instruction content by the voice recognized by executing the voice recognition processing, when it is analyzed that the voice signal includes the specific characteristic component.

### Claim 7

(canceled)

### Claim 8

A content reproducing device comprising:
a content input unit configured to input a content signal including at least a voice signal;
a content reproducer configured to reproduce the content signal;
a voice output unit configured to output a voice of the content signal;
a voice recognition device detection unit configured to detect presence of a voice recognition device; and
a content signal corrector configured to correct the voice signal such that the voice signal includes a specific characteristic component, in order for a voice recognition device to distinguish the voice output by the voice output unit from a voice uttered by a person, when the voice recognition device detection unit detects the presence of the voice recognition device.

### Claim 9 (depends on 8)

The content reproducing device according to claim 8,
wherein the content signal corrector is a processor which obtains a spectrum envelope of a frequency of the voice signal, and convolves an artificial waveform component as the specific characteristic component in the spectrum envelope at a predetermined time interval.

### Claim 10

(canceled)

### Claim 11

A content transmission and reception system comprising:
a content output device configured to output at least a voice of a content signal including a voice signal corrected such that a specific characteristic component is included in the voice signal uttered by a person; and
a voice recognition device configured to perform control not to execute voice recognition processing by a voice recognizer or to perform control not to respond to an instruction content by a recognized voice, when it is analyzed whether the input voice signal includes the specific characteristic component and analyzed that the input voice signal includes the specific characteristic component, in a case where it is detected that the content output device is outputting the voice of the content signal.

### Claim 12

A content transmission and reception system comprising:
a voice recognition device configured to perform control not to execute voice recognition processing by a voice recognition unit or to perform control to not respond to an instruction content by a recognized voice, when it is analyzed whether an input voice signal includes a specific characteristic component and analyzed that the input voice signal includes the specific characteristic component; and
a content output device configured to output a content signal including a corrected voice signal by performing correction such that the specific characteristic component is included in the voice signal included in the content signal, when outputting the content signal including the voice signal uttered by a person, in a case where presence of the voice recognition device is detected.

### Claim 13

A voice recognition device comprising:
a voice input unit into which a voice signal is input;
a voice analyzer configured to analyze whether a specific characteristic component is included in the voice signal input into the voice input unit;
a voice recognizer configured to recognize a voice represented by the voice signal input into the voice input unit;
a response instruction unit configured to instruct a response to a response operation unit that operates in response to the voice recognized by the voice recognizer;
a controller configured to control the voice recognizer not to execute voice recognition processing by the voice recognizer or to control the response instruction unit not to instruct the response operation unit about an instruction content by the voice recognized by the voice recognizer, when the voice analyzer analyzes that the voice signal includes the specific characteristic component; and
a reproducing device detection unit configured to detect that a content reproducing device including a voice output unit reproduces a content,
wherein the voice analyzer analyzes whether the voice signal input into the voice input unit includes the specific characteristic component when the reproducing device detection unit detects that the content reproducing device reproduces a content.

### Claim 14 (depends on 13)

The voice recognition device according to claim 13, wherein the specific characteristic component is an artificial waveform component superimposed on the voice signal at a predetermined time interval.

### Claim 15 (depends on 13)

The voice recognition device according to claim 13, wherein the voice signal is a voice signal included in a content of television broadcasting, radio broadcasting, or internet broadcasting.

### Claim 16

A control method of a voice recognition device by a processor comprising:
detecting whether a content reproducing device including a voice output unit is present;
analyzing whether a specific characteristic component is included in a voice signal input into a voice input unit when presence of the content reproducing device is detected;
recognizing a voice by executing voice recognition processing of the voice represented by the voice signal input into the voice input unit when it is detected that the voice signal does not include the specific characteristic component;
instructing a response to a response operation unit that operates in response to a recognized voice; and
performing control not to execute the voice recognition processing of the voice represented by the voice signal input into the voice input unit or perform control not to instruct the response operation unit about an instruction content by the voice recognized by executing the voice recognition processing, when it is analyzed that the voice signal includes the specific characteristic component.

### Claim 17 (depends on 16)

The control method of a voice recognition device according to claim 16, wherein the specific characteristic component is an artificial waveform component superimposed on the voice signal at a predetermined time interval.

### Claim 18

A content transmission and reception system comprising:
a content output device configured to output at least a voice of a content signal including a voice signal corrected such that a specific characteristic component is included in the voice signal uttered by a person; and
a voice recognition device configured to perform control not to execute voice recognition processing by a voice recognition unit or to perform control not to respond to an instruction content by a recognized voice, when it is analyzed whether the input voice signal includes the specific characteristic component and analyzed that the input voice signal includes the specific characteristic component, in a case where presence of the content output device is detected.

### Claim 19 (depends on 6)

The control method of a voice recognition device according to claim 6, wherein the specific characteristic component is an artificial waveform component superimposed on the voice signal at a predetermined time interval.
