# US 2017/0287464 A1 · Method and apparatus to synthesize voice based on facial structures

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

- Number: US 2017/0287464 A1
- Document ID: US20170287464A1
- Status: Published application
- Kind: A1
- Application number: 15/440,371
- Filed: 2017-02-23
- Published: 2017-10-05
- Earliest claimed: 2014-09-25
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Shamim Begum; Alexander A. Oganezov
- Web page: https://patentgrep.com/patent/US20170287464A1

## CPC

- G10L 13/027: Concept to speech synthesisers; Generation of natural phrases from machine-based concepts (generation of parameters for speech synthesis out of text G10L13/08)
- G06V 40/176: {Dynamic expression}
- G10L 13/033: Voice editing, e.g. manipulating the voice of the synthesiser
- G10L 13/047: Architecture of speech synthesisers
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Disclosed are embodiments for use in an articulatory-based text-to-speech conversion system configured to establish an articulatory speech synthesis model of a person's voice based on facial characteristics defining exteriorly visible articulatory speech synthesis model parameters of the person's voice and on a predefined articulatory speech synthesis model selected from among stores of predefined models.

## Claims

### Claim at position 1

1-7. (canceled)

### Claim 8

A method for speech to text conversion, comprising:
sending, to an articulatory model server, exterior facial structural information of a person;
receiving, from the articulatory model server, at least a portion of a predefined articulatory model that corresponds to the exterior facial structural information; and
converting text input to speech output based at least partly on the predefined articulatory model.

### Claim 9 (depends on 8)

The method of claim 8, in which the exterior facial structural information includes one or both of a picture of the person's face or articulatory parameters extracted from the picture.

### Claim 10 (depends on 9)

The method of claim 9, in which the portion of the predefined articulatory model includes invisible articulatory parameters corresponding to a modeled person who is different from the person shown in the picture.

### Claim 11 (depends on 9)

The method of claim 9, in which the portion of the predefined articulatory model includes visible articulatory parameters corresponding to a modeled person who is different from the person shown in the picture.

### Claim 12 (depends on 9)

The method of claim 9, in which the exterior facial structural information includes a picture of the person's face, and in which the sending causes the articulatory model server to extract the articulatory parameters from the picture.

### Claim 13 (depends on 9)

The method of claim 9, in which the sending causes the articulatory model server to match the person's picture to a stored picture of a person represented by the predefined articulatory model.

### Claim 14 (depends on 9)

The method of claim 9, in which the sending causes the articulatory model server to match the articulatory parameters extracted from the picture to those of the predefined articulatory model.

### Claim 15

A method for speech to text conversion, comprising:
receiving, from a user equipment device, exterior facial structural information of a person;
determining at least a portion of an articulatory model that corresponds to the exterior facial structural information based on a comparison of the exterior facial structural information to exterior facial structural information stored in a database of articulatory models; and
sending, to the user equipment device, the at least the portion of the articulatory model that corresponds to the exterior facial structural information of the person.

### Claim 16 (depends on 15)

The method of claim 15, in which the exterior facial structural information includes one or both of a picture of the person's face or articulatory parameters extracted from the picture.

### Claim 17 (depends on 16)

The method of claim 16, in which the portion of the predefined articulatory model includes invisible articulatory parameters corresponding to a modeled person who is different from the person shown in the picture.

### Claim 18 (depends on 16)

The method of claim 16, in which the portion of the predefined articulatory model includes visible articulatory parameters corresponding to a modeled person who is different from the person shown in the picture.

### Claim 19 (depends on 16)

The method of claim 16, in which the exterior facial structural information includes a picture of the person's face, and in which the receiving causes an articulatory model server to extract the articulatory parameters from the picture.

### Claim 20 (depends on 16)

The method of claim 16, in which the receiving causes an articulatory model server to match the person's picture to a stored picture of a person represented by the predefined articulatory model.

### Claim 21 (depends on 16)

The method of claim 16, in which the receiving causes an articulatory model server to match the articulatory parameters extracted from the picture to those of the predefined articulatory model.