# US 2022/0044689 A1 · Authentication method, authentication system, smart speaker and program

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

- Number: US 2022/0044689 A1
- Document ID: US20220044689A1
- Status: Published application
- Kind: A1
- Application number: 17/425,275
- Filed: 2020-06-16
- Published: 2022-02-10
- Earliest claimed: 2020-01-20
- Assignees: Hakushitorock Co., Ltd.
- Applicants: Hakushitorock Co., Ltd.
- Inventors: Issei WATANABE
- Web page: https://patentgrep.com/patent/US20220044689A1

## CPC

- G10L 17/24: the user being prompted to utter a password or a predefined phrase
- G06F 3/16: Sound input; Sound output (speech processing G10L)
- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- G10L 17/06: Decision making techniques; Pattern matching strategies
- G10L 17/14: Use of phonemic categorisation or speech recognition prior to speaker recognition or verification
- 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)

## Abstract

An authentication method includes a first step and a second step. The first step causes a voice including a predetermined character string to be output from a speaker 23. The second step acquires voice information by receiving an utterance voice of the target user via a microphone 21 after the first step, and determines from the voice information whether the target user is the specific user or not. In the second step, it is determined whether a character string recognized from the voice information is matched to the predetermined character string. In the second step, it is determined whether characteristics of the utterance voice of the target user is matched to characteristics of the voice of the target user based on a characteristics amount recognized from the voice information and a characteristics amount of voice information registered in advance as the voice of the specific user.

## Claims

### Claim 1

An authentication method of a smart speaker, which is executed in an authentication system of a smart speaker having a speaker, a microphone and a control unit, and which authenticates whether a target user is a specific user registered in advance,
wherein the control unit executes,
a first step of causing a voice including a predetermined character string to be output from the speaker, and
a second step of acquiring voice information by receiving an utterance voice of the target user via the microphone after the first step, and determining from the voice information whether the target user is the specific user or not, and
wherein the second step executes,
a determination whether a character string recognized from the voice information is matched to the predetermined character string, and
a determination whether characteristics of the utterance voice of the target user is matched to characteristics of the voice of the target user based on a characteristics amount recognized from the voice information and a characteristics amount of voice information registered in advance as the voice of the specific user, and
wherein the predetermined character string is a character string generated to cause the target user to recite at a time of an authentication.

### Claim 2 (depends on 1)

The authentication method of a smart speaker according to claim 1,
wherein the second step further executes a determination whether a time until the voice information is to be acquired from a time when the first step is executed is within a predetermined time.

### Claim 3 (depends on 1)

The authentication method of a smart speaker according to claim 1,
wherein a voice that prompts the utterance is output before or after causing the voice including the predetermined character string to be output in the first step.

### Claim 4

An authentication system of a smart speaker having a speaker, a microphone and a control unit,
wherein the control unit is configured such as to,
cause a voice including a predetermined character string to be output from the speaker, and
acquire voice information by receiving an utterance voice of a target user via the microphone thereafter and determine from the voice information whether the target user is a specific user or not, and
wherein, in the determination, the control unit executes,
a determination whether a character string recognized from the voice information is matched to the predetermined character string, and
a determination whether characteristics of the utterance voice of the target user is matched to characteristics of the voice of the target user based on a characteristics amount recognized from the voice information and a characteristics amount of voice information registered in advance as the voice of the specific user, and
wherein the predetermined character string is a character string generated to cause the target user to recite at a time of an authentication.

### Claim 5 (depends on 4)

The authentication system of a smart speaker according to claim 4,
wherein, in the determination, the control unit further executes a determination whether a time until the voice information is to be acquired from a time of causing the voice including the predetermined character string to be output from the speaker is within a predetermined time.

### Claim 6

A smart speaker having a speaker, a microphone and a control unit,
wherein, the control unit is configured such as to,
cause a voice including a predetermined character string to be output from the speaker, and
acquire voice information by receiving an utterance voice of a target user via the microphone thereafter and determine from the voice information whether the target user is a specific user or not, and
wherein, in the determination, the control unit executes,
a determination whether a character string recognized from the voice information is matched to the predetermined character string, and
a determination whether characteristics of the utterance voice of the target user is matched to characteristics of the voice of the target user based on a characteristics amount recognized from the voice information and a characteristics amount of voice information registered in advance as the voice of the specific user, and
wherein the predetermined character string is a character string generated to cause the target user to recite at a time of an authentication.

### Claim 7 (depends on 6)

The smart speaker according to claim 6,
wherein, in the determination, the control unit further executes a determination whether a time until the voice information is to be acquired from a time of causing the voice including the predetermined character string to be output from the speaker is within a predetermined time.

### Claim 8 (depends on 1)

A program causing a computer to execute the authentication method according to claim 1.
