Intelligent voice recognizing method, apparatus, and intelligent computing device

Patent metadata

Field	Value
Publication number	US-11580992-B2
Application number	US-201916557624-A
Country	US
Kind code	B2
Filing date	Aug 30, 2019
Priority date	Aug 5, 2019
Publication date	Feb 14, 2023
Grant date	Feb 14, 2023

Abstract

An intelligent voice recognition method, voice recognition apparatus and intelligent computing device are disclosed. An intelligent voice recognition method of a voice recognition apparatus according to an embodiment of the present invention detects a voice of a user, receives an authentication request from the user, and performs authentication for the user on the basis of a result of determination of whether authentication for the user has recently been performed and a result of recognition of the voice of the user, thereby reducing a time and the quantity of calculations necessary for user authentication. One or more of the voice recognition apparatus and the intelligent computing device can be associated with artificial intelligence (AI) modules, unmanned aerial vehicle (UAV) robots, augmented reality (AR) devices, virtual reality (VR) devices, 5G service related devices, etc.

First claim

What is claimed is:

1. An intelligent voice recognition method of a voice recognition apparatus, the intelligent voice recognition method comprising:
detecting a voice of a user;
receiving an authentication request from the user;
determining whether authentication for the user has recently been performed in response to the authentication request; and
performing authentication for the user based on a result of determination of whether authentication for the user has recently been performed and a result of recognition of the voice of the user,
wherein the performing of authentication for the user comprises performing authentication for the user when valid authentication for the user has been performed within a predetermined critical period and performing additional authentication for the user before authentication for the user is performed when the valid authentication has not been performed, and
wherein the performing of additional authentication comprises performing first additional authentication based on whether a speech of the user under predetermined conditions is detected.

2. The intelligent voice recognition method of claim 1 , wherein the speech of the user under the predetermined conditions includes call conversations with other users preset in the voice recognition apparatus or conversations with other speakers acquired through a microphone of the voice recognition apparatus.

3. The intelligent voice recognition method of claim 1 , wherein the performing of additional authentication comprises performing the first additional authentication and second additional authentication when the speech of the user under the predetermined conditions is not detected.

4. The intelligent voice recognition method of claim 3 , wherein the first additional authentication comprises:
providing an inquiry based on the voice of the user;
receiving an answer to the inquiry from the user; and
determining that the first additional authentication is successful when the answer is consistent with a predetermined answer.

5. The intelligent voice recognition method of claim 4 , wherein the second additional authentication comprises:
determining whether the voice of the user is detected on the authentication request;
determining whether a total amount of the voice of the user is equal to or greater than a predetermined threshold value when the voice of the user is detected; and
determining that the second additional authentication for the user is successful when the total amount of the voice of the user is equal to or greater than the predetermined threshold value.

6. The intelligent voice recognition method of claim 1 , further comprising:
receiving, from a network, downlink control information (DCI) used to schedule transmission of data of the voice acquired from a microphone included in the voice recognition apparatus; and
transmitting the voice data to the network based on the DCI.

7. The intelligent voice recognition method of claim 6 , further comprising:
performing an initial access procedure with the network based on a synchronization signal block (SSB); and
transmitting the voice data to the network through a physical uplink shared channel (PUSCH),
wherein the SSB and a demodulation reference signal (DM-RS) of the PUSCH are quasi-co-located (QCLed) for QCL type D.

8. The intelligent voice recognition method of claim 6 , further comprising:
controlling a communication module to transmit the voice data to an artificial intelligence processor included in the network; and
controlling the communication module to receive AI-processed information from the AI processor,
wherein the AI-processed information is information representing an authentication probability for the user recognized through the voice data.

9. A voice recognition apparatus for recognizing a voice with intelligence, the voice recognition apparatus comprising:
a microphone configured to detect a voice of a user;
a communication module configured to receive an authentication request from the user; and
a processor configured to determine whether authentication for the user has recently been performed in response to the authentication request and to perform authentication for the user based on a result of determination of whether authentication for the user has recently been performed and a result of recognition of the voice of the user,
wherein the processor performs authentication for the user when valid authentication for the user has been performed within a predetermined critical period and performs additional authentication for the user before authentication for the user is performed when the valid authentication has not been performed, and
wherein the processor performs first additional authentication based on whether a speech of the user under predetermined conditions is detected.

10. The voice recognition apparatus of claim 9 , wherein the speech of the user under the predetermined conditions includes call conversations with other users preset in the voice recognition apparatus or conversations with other speakers acquired through a microphone of the voice recognition apparatus.

11. The voice recognition apparatus of claim 9 , wherein the processor performs the first additional authentication and second additional authentication when the speech of the user under the predetermined conditions is not detected.

12. The voice recognition apparatus of claim 11 , wherein the processor provides an inquiry based on the voice of the user through an output unit, receives an answer to the inquiry from the user through the input unit, and determines that the first additional authentication is successful when the answer is consistent with a predetermined answer in the first additional authentication.

13. The voice recognition apparatus of claim 12 , wherein the processor determines whether the voice of the user is detected on the authentication request, determines whether a total amount of the voice of the user is equal to or greater than a predetermined threshold value when the voice of the user is detected, and determines that the second additional authentication for the user is successful when the total amount of the voice of the user is equal to or greater than the predetermined threshold value in the second additional authentication.

14. The voice recognition apparatus of claim 9 , wherein the processor receives, from a network, downlink control information (DCI) used to schedule transmission of data of the voice acquired from a microphone included in the voice recognition apparatus through the communication module, and transmits the voice data to the network through the communication module based on the DCI.

15. The voice recognition apparatus of claim 14 , wherein the processor performs an initial access procedure with the network based on a synchronization signal block (SSB) through the communication module, and transmits the voice data to the network through a physical uplink shared channel (PUSCH),
wherein the SSB and a demodulation reference signal (DM-RS) of the PUSCH are quasi-co-located (QCLed) for QCL type D.

16. The voice recognition apparatus of claim 14 , wherein the processor controls the communication module to transmit the voice data to an artificial intelligence (AI) processor included in the network and controls the communication module to receive AI-processed information from the AI processor,
wherein the AI-processed information is information representing an authentication probability for the user recognized through the voice data.

17. A non-transitory computer-readable recording me

Assignees

• Lg Electronics Inc

Inventors

• Kang Shinjae
• Kim Sungjin
• Lee Jungsu

Classifications

• H04W74/0833

  Random access procedures, e.g. with 4-step access · CPC title

• G10L25/78

  Detection of presence or absence of voice signals (switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10) · CPC title

• G10L17/04

  Training, enrolment or model building · CPC title

• H04W72/23

  in the downlink direction of a wireless link, i.e. towards a terminal · CPC title

• H04W56/001

  Synchronization between nodes · CPC title