# US 2025/0166599 A1 · Method and device for speech synthesis

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

- Number: US 2025/0166599 A1
- Document ID: US20250166599A1
- Status: Published application
- Kind: A1
- Application number: 18/940,215
- Filed: 2024-11-07
- Published: 2025-05-22
- Earliest claimed: 2023-11-20
- Assignees: Hyundai Motor Company; Kia Corporation
- Applicants: Hyundai Motor Company; Kia Corporation
- Inventors: Seong Soo YAE
- Web page: https://patentgrep.com/patent/US20250166599A1

## CPC

- G10L 13/02: Methods for producing synthetic speech; Speech synthesisers
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

In a method and device for speech synthesis, the method of outputting text input as sound from an electronic device, includes receiving a text input including characters from at least two languages and at least one symbol, generating a plurality of ordered groups by sequencing, wherein the plurality of ordered groups includes character groups including characters from a common language, and a symbol group including symbols, by segmenting the text input sequentially by language and by symbol, generating sound segments corresponding to each of the character groups by use of a plurality of text-to-speech (TTS) engines supporting different languages, generating an output sound by merging the sound segments according to the sequencing of the character groups within the plurality of ordered groups, and displaying the symbol of the symbol group on a display while outputting the output sound by use of a speaker.

## Claims

### Claim 1

A method of outputting text input as sound from an electronic device, the method comprising:
receiving, by at least one processor, a text input including characters from at least two languages and at least one or more symbols;
generating, by the at least one processor, a plurality of ordered groups by sequencing, wherein the plurality of ordered groups includes character groups including characters from a common language, and a symbol group including symbols, by segmenting the text input sequentially by language and by symbol;
generating, by the at least one processor, sound segments corresponding to each of the character groups by use of a plurality of text-to-speech (TTS) engines supporting different languages;
generating, by the at least one processor, an output sound by merging the sound segments according to the sequencing of the character groups within the plurality of ordered groups; and
displaying, by the at least one processor, the symbols of the symbol group on a display and outputting the output sound by use of a speaker.

### Claim 2 (depends on 1)

The method of claim 1, further including:
replacing, by the at least one processor, characters of a character group expressed in a language not supported by the plurality of TTS engines with a phonetic representation according to a first language among the different languages supported by the plurality of TTS engines; and
generating, by the at least one processor, using a TTS engine supporting the first language among the plurality of TTS engines, a sound segment for the phonetic representation.

### Claim 3 (depends on 1)

The method of claim 1, further including:
stopping, by the at least one processor, the displaying of the symbols of the symbol group on the display upon termination of an output of a sound segment corresponding to a character group preceding the symbol group.

### Claim 4 (depends on 1)

The method of claim 1, wherein the displaying of the symbols of the symbol group on the display is timed based on a position of a character group preceding the symbol group and a number of characters in the character group preceding the symbol group.

### Claim 5 (depends on 1)

The method of claim 1, further including:
identifying, by the at least one processor, among the character groups, a character group including a number of characters above a preset threshold;
determining, by the at least one processor, a symbol corresponding to an emotional state of characters in the character group including the number of characters above the preset threshold; and
replacing, by the at least one processor, the character group including the number of characters above the preset threshold with a symbol group including the symbol corresponding to the emotional state.

### Claim 6 (depends on 1)

The method of claim 1, wherein the characters and the symbols in the text input include characters and symbols represented by Unicode.

### Claim 7 (depends on 1)

The method of claim 1, wherein the text input is provided in response to a query from a user of the electronic device, or provided as a mobile message received on a user terminal communicatively linked to the electronic device.

### Claim 8 (depends on 1)

The method of claim 1, wherein the plurality of TTS engines includes:
TTS engines embedded in the electronic device, TTS engines provided by a server communicatively linked to the electronic device, or a combination of the TTS engines in the electronic device and the TTS engines by the server.

### Claim 9 (depends on 1)

The method of claim 1, wherein the display includes a heads-up display of a vehicle provided with the electronic device.

### Claim 10

An electronic apparatus for outputting text input as sound, the apparatus comprising:
a memory configured to store instructions; and
at least one processor configured to execute the instructions,
wherein the at least one processor is configured for, by executing the instructions:
receiving the text input including characters from at least two languages and at least one or more symbols;
generating a plurality of ordered groups by sequencing, wherein the plurality of ordered groups includes character groups including characters from a common language, and a symbol group including symbols, by segmenting the text input sequentially by language and by symbol;
generating sound segments corresponding to each of the character groups by use of a plurality of text-to-speech (TTS) engines supporting different languages;
generating an output sound by merging the sound segments according to the sequencing of the character groups within the plurality of ordered groups; and
displaying the symbols of the symbol group on a display and outputting the output sound by use of a speaker.

### Claim 11 (depends on 10)

The electronic apparatus of claim 10, wherein the at least one processor is configured to further perform:
replacing characters of a character group expressed in a language not supported by the plurality of TTS engines with a phonetic representation according to a first language among the different languages supported by the plurality of TTS engines; and
generating, using a TTS engine supporting the first language among the plurality of TTS engines, a sound segment for the phonetic representation.

### Claim 12 (depends on 10)

The electronic apparatus of claim 10, wherein the at least one processor is configured to further perform:
stopping the displaying of the symbols of the symbol group on the display upon termination of an output of a sound segment corresponding to a character group preceding the symbol group.

### Claim 13 (depends on 10)

The electronic apparatus of claim 10, wherein the displaying of the symbols of the symbol group on the display is timed based on a position of a character group preceding the symbol group and a number of characters in the character group preceding the symbol group.

### Claim 14 (depends on 10)

The electronic apparatus of claim 10, wherein the at least one processor is configured to further perform:
identifying, among the character groups, a character group including a number of characters above a preset threshold;
determining a symbol corresponding to an emotional state of characters in the character group including the number of characters above the preset threshold; and
replacing the character group including the number of characters above the preset threshold with a symbol group including the symbol corresponding to the emotional state.

### Claim 15 (depends on 10)

The electronic apparatus of claim 10, wherein the characters and the symbols in the text input include characters and symbols represented by Unicode.

### Claim 16 (depends on 10)

The electronic apparatus of claim 10, wherein the text input is provided in response to a query from a user of the electronic apparatus, or provided as a mobile message received on a user terminal communicatively linked to the electronic apparatus.

### Claim 17 (depends on 10)

The electronic apparatus of claim 10, wherein the plurality of TTS engines includes:
TTS engines embedded in the electronic apparatus, TTS engines provided by a server communicatively linked to the electronic apparatus, or a combination of the TTS engines in the electronic apparatus and the TTS engines by the server.

### Claim 18 (depends on 10)

The electronic apparatus of claim 10, wherein the display includes a heads-up display of a vehicle provided with the electronic apparatus.

### Claim 19

A non-transitory computer-readable recording medium storing instructions executed in at least one processor for causing the at least one processor to perform:
receiving a text input including characters from at least two languages and at least one symbol;
generating a plurality of ordered groups by sequencing, wherein the plurality of ordered groups includes character groups including characters from a common language, and a symbol group including symbols, by segmenting the text input sequentially by language and by symbol;
generating sound segments corresponding to each of the character groups by use of a plurality of text-to-speech (TTS) engines supporting different languages;
generating an output sound by merging the sound segments according to the sequencing of the character groups within the plurality of ordered groups; and
displaying the symbols of the symbol group on a display and outputting the output sound by use of a speaker.

### Claim 20 (depends on 19)

The non-transitory computer-readable recording medium of claim 19, wherein the at least one processor is configured to further perform:
replacing characters of a character group expressed in a language not supported by the plurality of TTS engines with a phonetic representation according to a first language among the different languages supported by the plurality of TTS engines; and
generating, using a TTS engine supporting the first language among the plurality of TTS engines, a sound segment for the phonetic representation.
