# US 2025/0157460 A1 · Detection device, detection method, and program

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

- Number: US 2025/0157460 A1
- Document ID: US20250157460A1
- Status: Published application
- Kind: A1
- Application number: 18/832,147
- Filed: 2022-01-25
- Published: 2025-05-15
- Earliest claimed: 2022-01-25
- Assignees: NTT TechnoCross Corporation
- Applicants: NTT TechnoCross Corporation
- Inventors: Takaaki FUKUTOMI; Kazuhira MATSUI; Asato TANAKA; Toshihiko TANAKA
- Web page: https://patentgrep.com/patent/US20250157460A1

## CPC

- G10L 15/08: Speech classification or search
- G10L 15/10: using distance or distortion measures between unknown speech and reference templates
- G06F 16/243: {Natural language query formulation}
- G06F 40/35: Discourse or dialogue representation
- G10L 15/00: Speech recognition (G10L17/00 takes precedence)
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- H04M 3/5133: {Operator terminal details}
- H04M 3/5175: {Call or contact centers supervision arrangements}
- G10L 2015/088: {Word spotting}
- H04M 2201/38: Displays
- H04M 2201/40: using speech recognition
- 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)
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

A detection device according to an embodiment includes: a detection part configured to detect a word of interest from a result of applying speech recognition to a dialogue between a plurality of parties, based on a detection condition for the word of interest to be detected, the word of interest being a term, a word, an expression, a phrase, or a sentence that is supposed to be noticed or paid attention to; and a display information providing part configured to transmit display information to a predetermined terminal when the word of interest is detected, the display information being for displaying the detected word of interest or a display component representing the detected word of interest in a pre-registered display mode.

## Claims

### Claim 1

A detection device comprising:
a processor; and
a memory having instructions stored thereon that, when executed by the processor, cause the processor to:
detect a word of interest from a speech recognition result of a dialogue, wherein the dialogue is between a plurality of parties, the detecting a word of interest is based on a detection condition for the word of interest, and the word of interest comprises at least one of a term, a word, an expression, a phrase, or a sentence that is to be noticed or paid attention to at least by a party of the plurality of parties; and
transmit, based on the detected word of interest, display information to a predetermined terminal, wherein the display information specifies a pre-registered display mode to display at least either one of the detected word of interest or a display component representing the detected word of interest.

### Claim 2 (depends on 1)

The detection device according to claim 1,
wherein the detection condition comprises a detection pattern and a predetermined number of occurrences of the detection pattern in the speech recognition result, the detection pattern represents at least either one of a regular expression of the word of interest to be detected or a character sequence representing the word of interest to be detected, and
wherein the instructions when executed by the processor further cause the processor to detect the word of interest based on a number of times the detection pattern occurs in the speech recognition result and the predetermined number of occurrences of the detection pattern.

### Claim 3 (depends on 2)

The detection device according to claim 2,
wherein the detection condition further comprises at least either one of a scene in which the detection pattern is spoken, or a type of statement in which the detection pattern is spoken, and
wherein the instructions when executed by the processor further cause the processor to detect the word of interest based on matching a scene or a type of statement in which the detection pattern occurs in the speech recognition result and the scene or the type of statement set in the detection condition.

### Claim 4 (depends on 2)

The detection device according to claim 2, wherein the instructions when executed by the processor further cause the processor to determine the predetermined number of occurrences of the detection pattern based on a distribution of occurrences of the detection pattern in past dialogues.

### Claim 5 (depends on 2)

The detection device according to claim 2, wherein the instructions when executed by the processor further cause the processor to detect the word of interest based on context of the dialogue from a beginning of the speech recognition result of the dialogue to a part of the speech recognition result where the detection pattern occurs.

### Claim 6 (depends on 1)

The detection device according to claim 1, wherein the instructions when executed by the processor further cause the processor to transmit the display information to a first terminal used by a predetermined one speaker of a party of the plurality of parties in the dialogue, and the display information specifies a pre-registered color as an emphasis to display the detected word of interest.

### Claim 7 (depends on 6)

The detection device according to claim 6, wherein the instructions when executed by the processor further cause the processor to transmit the display information to a second terminal that is used by a person monitoring and assisting the predetermined one speaker, the display information being for displaying the display component with emphasis in a pre-registered color.

### Claim 8 (depends on 7)

The detection device according to claim 7, wherein the the instructions when executed by the processor further cause the processor to transmit, based on detecting the word of interest, information to the second terminal, the information indicates detection of the word of interest to the second terminal by using a pre-registered sound.

### Claim 9 (depends on 1)

The detection device according to claim 1, wherein the instructions when executed by the processor further cause the processor to:
search for dialogue history information by using the word of interest as a search condition, in a database, wherein the database stores dialogue history information that represents speech recognition results of past dialogues; and
transmit the display information to a third terminal that specifies the search condition, wherein the display information comprises:
dialogue history information that is obtained from the search, and
the word of interest included in a speech recognition result represented by the dialogue history information obtained from the search.

### Claim 10

A detection method that causes a computer to:
detect a word of interest from a speech recognition result of a dialogue, wherein the dialogue is between a plurality of parties, the detecting a word of interest is based on a detection condition for the word of interest, and the word of interest comprises at least one of a term, a word, an expression, a phrase, or a sentence that is to be noticed or paid attention to at least by a party of the plurality of the parties; and
transmit, based on the detected word of interest, display information to a predetermined terminal, wherein the display information specifies a pre-registered display mode to display at least either one of the detected word of interest or a display component representing the detected word of interest.

### Claim 11 (depends on 10)

A non-transitory recording medium storing a program that, when executed on a computer, causes the computer to perform the detection method of claim 10.
