KR20200066030A - Method for voice registration and certification using voice id system - Google Patents

Abstract

Disclosed is a method for voice registration and certification using a voice ID system capable of recognizing a voice of a user. The method comprises the steps of: obtaining voice data of a user; generating a unique identifier corresponding to the obtained voice data; obtaining a voice input of the user; and verifying the voice input based on the unique identifier.

Description

Voice registration and authentication method using voice ID system {METHOD FOR VOICE REGISTRATION AND CERTIFICATION USING VOICE ID SYSTEM}

The present invention relates to a voice registration and authentication method using a voice ID system.

The method of verifying a user's speech using a voice recognizer plays a large role in filtering out meaningless data, but on the contrary, there are limitations in using the voice recognizer.

In the case of the speech recognizer, if the user's speech content is not learned in the language model of the corresponding speech recognizer, there is a tendency to recognize it as the most similar learned content. Can cause

For example, in the case of Korean, when speaking using a dialect or a completely new Internet term that appears differently depending on the region, the actual audio and the recognized text are different, so it cannot be used as learning data.

Therefore, in order to overcome these limitations and improve the quality of crowdsourcing data, the user must first express his or her words as text, and when the user directly utters the text, the sound recognized by the recognizer is the actual user's intention. There is a need to develop a method to quantify how similar a phonetic text is.

The problem to be solved by the present invention is to provide a voice registration and authentication method using a voice ID system.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

A voice registration and authentication method using a voice ID system according to an aspect of the present invention for solving the above-described problems comprises: obtaining a user's voice data, generating a unique identifier corresponding to the obtained voice data, And obtaining a user's voice input and verifying the voice input based on the unique identifier.

In addition, the generating of the unique identifier may include extracting a voice matrix from the voice data using the integrated voice model generated based on a reference model, and using the voice matrix and the ID of the user. And registering a voice ID.

In addition, the step of performing the verification may include, using the integrated speech model, extracting a speech matrix from the speech input, and performing a search and scoring based on the speech matrix extracted from the speech input and the user ID. However, the scoring may include a step characterized in that it is performed using a scoring model generated based on the reference model.

Other specific matters of the present invention are included in the detailed description and drawings.

According to the disclosed embodiment, it is possible to provide a system capable of pre-registering voices of users having characteristics unique to each other through voice ID registration and recognizing the voices of the users based on this.

Based on this, there is an advantage of using a text-to-speech system to combat computer fraud such as generating audio, and authenticating a user on behalf of a third-party voice application.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a diagram illustrating a voice registration and authentication method using a voice ID system according to an embodiment.

Advantages and features of the present invention, and methods for achieving them will be clarified with reference to embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments allow the disclosure of the present invention to be complete, and are common in the technical field to which the present invention pertains. It is provided to fully inform the skilled person of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for describing the embodiments and is not intended to limit the present invention. In the present specification, the singular form also includes the plural form unless otherwise specified in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components other than the components mentioned. Throughout the specification, the same reference numerals refer to the same components, and “and/or” includes each and every combination of one or more of the components mentioned. Although "first", "second", etc. are used to describe various components, it goes without saying that these components are not limited by these terms. These terms are only used to distinguish one component from another component. Therefore, it goes without saying that the first component mentioned below may be the second component within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used as meanings commonly understood by those skilled in the art to which the present invention pertains. In addition, terms defined in the commonly used dictionary are not ideally or excessively interpreted unless explicitly defined.

The term "part" or "module" as used in the specification refers to a hardware component such as software, FPGA, or ASIC, and "part" or "module" performs certain roles. However, "part" or "module" is not meant to be limited to software or hardware. The "unit" or "module" may be configured to be in an addressable storage medium or may be configured to reproduce one or more processors. Thus, as an example, "part" or "module" means components, processes, functions, attributes, such as software components, object-oriented software components, class components and task components. Includes procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, database, data structures, tables, arrays and variables. The functionality provided within components and "parts" or "modules" can be combined into a smaller number of components and "parts" or "modules" or into additional components and "parts" or "modules" Can be further separated.

In the present specification, the computer means all kinds of hardware devices including at least one processor, and may be understood as a meaning encompassing software configurations operating in the corresponding hardware device according to embodiments. For example, a computer may be understood as meaning including, but not limited to, a smart phone, a tablet PC, a desktop, a laptop, and a user client and application running on each device.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Each method and step described in this specification is described as being performed by a computer, but the subject of each step is not limited thereto, and according to an embodiment, at least some of the steps may be performed in different devices.

1 is a diagram illustrating a voice registration and authentication method using a voice ID system according to an embodiment.

Hereinafter, a voice authentication method for performing authentication using a user's voice, and a data collection and learning method for performing the authentication are disclosed.

Referring to FIG. 1, the voice ID system is mainly composed of three processes, which may include a model training process, a voice registration process, and a voice authentication process.

In one embodiment, a process of generating an integrated speech model and a scoring model based on reference model training may be performed.

For example, the reference model is trained to generate an integrated voice model using the entire collected voice data. The integrated speech model is used to extract the speech matrix of the user speech, and the scoring model can be used to calculate the similarity score between the registered speech data and the received speech data.

In one embodiment, the voice model trainer may generate an integrated voice model and a scoring model by performing learning using each speaker's ID and an audio corpus.

In one embodiment, a voice registration process may be performed.

For example, a user can submit approximately 5 minutes of voice data for voice registration, and the computer can use this to generate a unique identifier that acts as a voice ID. Since the human voice is unique for each individual due to each pitch, formant, and other characteristics, a unique identifier can be generated for each person.

When the user's voice data is obtained, the computer uses a voice matrix extractor to generate a unique voice matrix based on the user's voice data. The resulting matrix can be homomorphically encrypted and stored based on the smart contract with the user ID. In addition, homomorphic encryption keeps the voice matrix safe while allowing different IDs to be compared.

That is, the computer can learn the reference voice model based on all the voice data stored in the database, and generate the user's own voice matrix by comparing the user's voice data with the reference model. The voice matrix thus generated may be used as a voice ID, which may be encrypted and stored based on a smart contract.

In one embodiment, a voice authentication process may be performed.

When an input voice is received from a user, and there is a request for data verification or user authentication, the computer may input the received voice into a voice matrix extractor to generate a voice matrix.

The resulting matrix can also be encrypted and then matched against the stored speech matrix to search for matches.

Specifically, the computer extracts the input speech into a speech matrix using a speech matrix extractor, and the extracted speech matrix is used for searching and scoring by a scoring model based on a comparison user ID. As a result of scoring, a similarity score is output, and authentication may be performed based on the similarity score.

By using the voice ID system according to the disclosed embodiment, ownership of the received voice data can be confirmed, and computer fraud through a method such as generating audio using a text conversion system is eliminated, and a third-party voice application is used. Instead, user authentication can be performed.

The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, a software module executed by hardware, or a combination thereof. The software modules may include Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), Flash Memory, Hard Disk, Removable Disk, CD-ROM, or It may reside on any type of computer readable recording medium well known in the art.

The components of the present invention may be implemented as a program (or application) to be executed in combination with a hardware computer, and stored in a medium. The components of the present invention can be implemented in software programming or software components, and similarly, embodiments include C, C++, including various algorithms implemented in a combination of data structures, processes, routines or other programming components. , Can be implemented in programming or scripting languages such as Java, assembler, etc. Functional aspects can be implemented with algorithms running on one or more processors.

The embodiments of the present invention have been described with reference to the accompanying drawings, but a person skilled in the art to which the present invention pertains may implement the present invention in other specific forms without changing its technical spirit or essential features. You will understand. Therefore, it should be understood that the above-described embodiments are illustrative in all respects and not restrictive.

Claims (3)

In the computer-implemented method,
Obtaining the user's voice data;
Generating a unique identifier corresponding to the acquired voice data;
Obtaining a user's voice input; And
Performing verification of the voice input based on the unique identifier; Containing,
Voice registration and authentication method using voice ID system. According to claim 1,
Generating the unique identifier,
Extracting a speech matrix from the speech data using an integrated speech model generated based on a reference model; And
Registering the user's voice ID using the voice matrix and the user's ID; Containing,
Voice registration and authentication method using voice ID system. According to claim 2,
The step of performing the verification,
Extracting a speech matrix from the speech input using the integrated speech model; And
Performing a search and scoring based on the voice matrix extracted from the voice input and the user ID, wherein the scoring is performed using a scoring model generated based on the reference model; Containing,
Voice registration and authentication method using voice ID system.

Images