# US 10,872,605 B2 · Translation device

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

- Number: US 10,872,605 B2
- Document ID: US10872605B2
- Status: Granted
- Kind: B2
- Application number: 16/031,536
- Filed: 2018-07-10
- Published: 2018-11-08
- Granted: 2020-12-22
- Earliest claimed: 2016-07-08
- Assignees: Panasonic Intellectual Property Management Co., Ltd.
- Applicants: Panasonic Intellectual Property Management Co., Ltd.
- Inventors: Yusuke Adachi; Takayuki Hayashi
- Web page: https://patentgrep.com/patent/US10872605B2

## CPC

- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G06F 40/51: Translation evaluation
- G06F 40/58: Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
- G10L 15/005: {Language recognition}
- G10L 21/00: Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility (G10L19/00 takes precedence)
- G10L 13/00: Speech synthesis; Text to speech systems
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 2015/221: {Announcement of recognition results}
- 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

A translation device includes a first receiver, a second receiver, a first output unit, and a second output unit. The first receiver receives a first voice and converts the first voice into a first voice signal. The second receiver receives a second voice and converts the second voice into a second voice signal. The first output unit outputs a voice corresponding to second translation data generated based on the second voice signal. The second output unit outputs a voice corresponding to first translation data generated based on the first voice signal. The first receiver is disposed near a mouth of a first user. The first output unit is disposed at a position at which the first output unit is in contact with an ear of the first user. The second receiver and the second output unit are disposed on a head of the first user.

## Claims

### Claim 1

A translation device comprising:
a hat;
a first receiver that receives a first voice and converts the first voice into a first voice signal, the first voice being voice of a first user, the first user wearing the hat;
a second receiver that receives a second voice and converts the second voice into a second voice signal, the second voice being voice of a second user, the second user being different from the first user;
a first output unit that outputs a voice corresponding to second translation data generated by translating second voice data based on the second voice signal;
a second output unit that outputs a voice corresponding to first translation data generated by translating first voice data based on the first voice signal; and
an evaluation presentation unit that presents, by using vibration, to the first user an evaluation value of translation from the first voice data to the first translation data and an evaluation value of translation from the second voice data to the second translation data, wherein
the first receiver is disposed near a mouth of the first user,
the first output unit is disposed at a position at which the first output unit is in contact with an ear of the first user,
the second receiver and the second output unit are disposed on a front outer surface of the hat so as to increase isolation between the voice output by the first output unit and the voice output by the second output unit, and to increase isolation between the first voice received by the first receiver and the second voice received by the second receiver, and
the evaluation presentation unit is disposed inside the hat.

### Claim 2 (depends on 1)

The translation device according to claim 1, wherein the second receiver and the second output unit are directed in a same direction as a face of the first user is directed.

### Claim 3 (depends on 1)

The translation device according to claim 1, wherein the first receiver and the first output unit constitute a headset.

### Claim 4 (depends on 1)

The translation device according to claim 1, further comprising:
a first display unit that displays a character image represented by first reverse translation data, the first reverse translation data being generated by reversely translating the first translation data; and
a second display unit that displays a character image represented by second reverse translation data, the second reverse translation data being generated by reversely translating the second translation data.

### Claim 5 (depends on 4)

The translation device according to claim 4, wherein
the first display unit is disposed near an eye of the first user, and
the second display unit is disposed on the front outer surface of the hat.

### Claim 6 (depends on 1)

The translation device according to claim 1, further comprising a controller that generates the first translation data and the second translation data.

### Claim 7 (depends on 1)

The translation device according to claim 1, further comprising a communication unit that communicates with a translation server,
wherein the communication unit transmits the first voice data and the second voice data to the translation server and receives the first translation data and the second translation data generated by the translation server.

### Claim 8

A translation device comprising:
a hat;
a first receiver that receives a first voice and converts the first voice into a first voice signal, the first voice being voice of a first user, the first user wearing the hat;
a second receiver that receives a second voice and converts the second voice into a second voice signal, the second voice being voice of a second user, the second user being different from the first user;
a first output unit that outputs a voice corresponding to second translation data generated by translating second voice data based on the second voice signal;
a second output unit that outputs a voice corresponding to first translation data generated by translating first voice data based on the first voice signal; and
an evaluation presentation unit that presents, by using vibration, to the first user an evaluation value of translation from the first voice data to the first translation data and an evaluation value of translation from the second voice data to the second translation data,
wherein the first receiver and the first output unit constitute a headset,
the second receiver and the second output unit are disposed on a front outer surface of the hat so as to increase isolation between the voice output by the first output unit and the voice output by the second output unit, and to increase isolation between the first voice received by the first receiver and the second voice received by the second receiver, and
the evaluation presentation unit is disposed inside the hat.

### Claim 9

A device comprising:
a hat;
a first receiver that receives a first voice and converts the first voice into a first voice signal, the first voice being voice of a first user, the first user wearing the hat;
a second receiver that receives a second voice and converts the second voice into a second voice signal, the second voice being voice of a second user, the second user being different from the first user;
a first output unit that outputs a voice corresponding to second generated data generated based on the second voice signal;
a second output unit that outputs a voice corresponding to first generated data generated based on the first voice signal; and
an evaluation presentation unit that presents, by using vibration, to the first user an evaluation value of translation from the first voice data to the first translation data and an evaluation value of translation from the second voice data to the second translation data,
wherein the first receiver and the first output unit constitute a headset, and
the second receiver and the second output unit are disposed on a front outer surface of the hat so as to increase isolation between the voice output by the first output unit and the voice output by the second output unit, and to increase isolation between the first voice received by the first receiver and the second voice received by the second receiver, and
the evaluation presentation unit is disposed inside the hat.