# US 2025/0157112 A1 · Apparatus and method for providing speech video

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

- Number: US 2025/0157112 A1
- Document ID: US20250157112A1
- Status: Published application
- Kind: A1
- Application number: 18/839,550
- Filed: 2022-08-23
- Published: 2025-05-15
- Earliest claimed: 2022-08-16
- Assignees: Deepbrain Ai Inc.
- Applicants: Deepbrain Ai Inc.
- Inventors: DOO HYUN KIM
- Web page: https://patentgrep.com/patent/US20250157112A1

## CPC

- G06T 13/205: {driven by audio data}
- G10L 21/10: Transforming into visible information
- G06T 13/40: of characters, e.g. humans, animals or virtual beings
- G10L 13/02: Methods for producing synthetic speech; Speech synthesisers
- H04N 5/265: Mixing
- H04N 21/43: Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware {(real-time communication protocols in data switching networks H04L65/00)}
- H04N 21/854: Content authoring
- G10L 2021/105: {Synthesis of the lips movements from speech, e.g. for talking heads}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

In a method for providing a speech video performed by a computing device according to one embodiment, first sections of a plurality of standby state videos are sequentially played back, wherein each standby state video includes the first section in which a person in the video is in a standby state and a second section for image interpolation between a last frame of the first section and a reference frame, a plurality of speech state images in which the person in the video is in a speech state and a speech voice based on a source of speech contents are generated and played back, when the generating of the plurality of speech state images and the speech voice is completed, the second section of the standby state video being played back at the time of completion, and a synthesized speech video is generated by synthesizing the plurality of speech state images and the speech voice with at least some of the plurality of standby state videos.

## Claims

### Claim 1

A method for providing a speech video performed by a computing device, the method comprising:
sequentially playing back first sections of a plurality of standby state videos, wherein each standby state video includes the first section in which a person in the video is in a standby state and a second section for image interpolation between a last frame of the first section and a reference frame;
generating a plurality of speech state images in which the person in the video is in a speech state and a speech voice based on a source of speech contents;
playing back, when the generating of the plurality of speech state images and the speech voice is completed, the second section of the standby state video being played back at the time of completion; and
generating a synthesized speech video by synthesizing the plurality of speech state images and the speech voice with at least some of the plurality of standby state videos.

### Claim 2 (depends on 1)

The method of claim 1, wherein in the playing back of the second section of the standby state video being played back at the time of completion, playback of the first section of the standby state video being played back at the time of completion is completed and the second section of the standby state video is played back.

### Claim 3 (depends on 1)

The method of claim 1, wherein the sequential playing back of the first sections of the plurality of standby state videos includes sequentially and repeatedly playing back the first sections of the plurality of standby state videos.

### Claim 4 (depends on 1)

The method of claim 1, wherein the last frame of the first section of a preceding standby state video and the first frame of the first section of a standby state video following the preceding standby state video are naturally connected to each other.

### Claim 5 (depends on 1)

The method of claim 1, wherein the plurality of speech state images are face images of the person in the video.

### Claim 6 (depends on 5)

The method of claim 5, wherein in the generating of the synthesized speech video, the synthesized speech video is generated by replacing a face of the person in the video with each speech state image and synthesizing the speech state image and the speech voice.

### Claim 7 (depends on 1)

The method of claim 1, wherein the reference frame is the first frame of the first section of a first standby state video among the plurality of standby state videos.

### Claim 8 (depends on 7)

The method of claim 7, wherein in the generating of the synthesized speech video, the synthesized speech video is generated by synthesizing the plurality of speech state images and the speech voice for frames within the first section of each standby state video, starting from the first frame of the first section of the first standby state video.

### Claim 9

An apparatus for providing a speech video, comprising:
a speech state image generator configured to generate a plurality of speech state images in which a person in the video is in a speech state based on a source of speech contents while sequentially playing back first sections of a plurality of standby state videos, wherein each standby state video includes the first section in which the person in the video is in a standby state and a second section for image interpolation between a last frame of the first section and a reference frame;
a speech voice generator configured to generate a speech voice based on the source of the speech contents while sequentially playing back the first sections of the plurality of standby state videos;
a playback unit configured to sequentially play back the first sections of the plurality of standby state videos, and when the generating of the plurality of speech state images and the speech voice is completed, play back the second section of the standby state video being played back at the time of completion; and
a synthesized speech video generator configured to generate a synthesized speech video by synthesizing the plurality of speech state images and the speech voice with at least some of the plurality of standby state videos.

### Claim 10 (depends on 9)

The apparatus of claim 9, wherein the playback unit completes playback of the first section of the standby state video being played back at the time of completion and plays back the second section of the standby state video.

### Claim 11 (depends on 9)

The apparatus of claim 9, wherein the playback unit sequentially and repeatedly plays back the first sections of the plurality of standby state videos.

### Claim 12 (depends on 9)

The apparatus of claim 9, wherein the last frame of the first section of a preceding standby state video and the first frame of the first section of a standby state video following the preceding standby state video are naturally connected to each other.

### Claim 13 (depends on 9)

The apparatus of claim 9, wherein the plurality of speech state images are face images of the person in the video.

### Claim 14 (depends on 13)

The apparatus of claim 13, wherein the synthesized speech video generator generates the synthesized speech video by replacing a face of the person in the video with each speech state image and synthesizing the speech state image and the speech voice.

### Claim 15 (depends on 9)

The apparatus of claim 9, wherein the reference frame is the first frame of the first section of a first standby state video among the plurality of standby state videos.

### Claim 16 (depends on 15)

The apparatus of claim 15, wherein synthesized speech video generator generates the synthesized speech video by synthesizing the plurality of speech state images and the speech voice for frames within the first section of each standby state video, starting from the first frame of the first section of the first standby state video.
