최소 단어 이상 선택하여야 합니다.
최대 10 단어까지만 선택 가능합니다.
다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
NTIS 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
DataON 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
Edison 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
Kafe 바로가기국가/구분 | United States(US) Patent 등록 |
---|---|
국제특허분류(IPC7판) |
|
출원번호 | US-0053144 (2011-03-21) |
등록번호 | US-9262612 (2016-02-16) |
발명자 / 주소 |
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 | 피인용 횟수 : 50 인용 특허 : 1851 |
A device can be configured to receive speech input from a user. The speech input can include a command for accessing a restricted feature of the device. The speech input can be compared to a voiceprint (e.g., text-independent voiceprint) of the user's voice to authenticate the user to the device. Re
A device can be configured to receive speech input from a user. The speech input can include a command for accessing a restricted feature of the device. The speech input can be compared to a voiceprint (e.g., text-independent voiceprint) of the user's voice to authenticate the user to the device. Responsive to successful authentication of the user to the device, the user is allowed access to the restricted feature without the user having to perform additional authentication steps or speaking the command again. If the user is not successfully authenticated to the device, additional authentication steps can be request by the device (e.g., request a password).
1. A method comprising: at an electronic device: while the device is in a locked state, receiving non-voice authentication information from a user to put the device into an unlocked state;receiving a first speech input from the user;in response to authenticating that the user is an authorized user o
1. A method comprising: at an electronic device: while the device is in a locked state, receiving non-voice authentication information from a user to put the device into an unlocked state;receiving a first speech input from the user;in response to authenticating that the user is an authorized user of the device, transmitting the first speech input to a voiceprint service for generating a voiceprint based on the first speech input;receiving a second speech input at the device while the device is in a locked state, the second speech input including a command associated with a restricted feature of the device;determining whether the second speech input was spoken by an authorized user of the device, the determining including comparing the second speech input to the generated voiceprint;while comparing the second speech input to the voiceprint, processing the second speech input to identify the command; andupon determining that the second speech input was spoken by the authorized user, providing access to the restricted feature of the device according to the command included in the second speech input, where the method is performed by one or more processors of the device. 2. The method of claim 1, further comprising: upon determining that the second speech input was not spoken by the authorized user, denying access to the restricted feature of the device. 3. The method of claim 1, further comprising: receiving the voiceprint from the voiceprint service through a network interface of the device. 4. The method of claim 1, wherein the device is a mobile device. 5. The method of claim 4, wherein the mobile device is a handheld device. 6. The method of claim 1, wherein the voiceprint is a text-independent voiceprint. 7. The method of claim 1, wherein the command is not an unlock command. 8. The method of claim 1, further comprising, upon determining that the second speech input was spoken by the authorized user, providing access to the restricted feature of the device according to the command while the device remains in the locked state. 9. The method of claim 1, further comprising: upon determining that the second speech input was spoken by the authorized user, unlocking the device;receiving a subsequent speech input at the device, the subsequent speech input including a subsequent command associated with the restricted feature of the device; andproviding access to the restricted feature of the device according to the subsequent command without determining whether the subsequent speech input was spoken by the authorized user of the device. 10. A method comprising: while a device is in a locked state: receiving a speech input at the device, the speech input including a command associated with a restricted feature of the device;authenticating, using the speech input, whether the speech input is spoken by an authorized user of the device, wherein the authenticating includes comparing the speech input to a previously generated voiceprint;in response to authenticating that the speech input is spoken by an authorized user of the device, executing the command identified in the speech input to invoke the restricted feature of the device; andin response to not authenticating that the speech input is spoken by an authorized user of the device, forgo executing the command identified in the speech input to invoke the restricted feature of the device; where the method is performed by one or more processors of the device. 11. The method of claim 10, further comprising: processing the speech input to identify the command while the device is in a locked state. 12. The method of claim 10, further comprising: in response to failing to authenticate that the speech input is spoken by an authorized user of the device, outputting an error indication. 13. A method comprising: receiving, at a device, a first speech input from a user;generating a voice sample based on the first speech input;in response to authenticating that the user is an authorized user of the device, transmitting the voice sample to a voiceprint service for generating a text-independent voiceprint based on the voice sample, wherein the text-independent voiceprint is configured to be compared to subsequent speech inputs received at the device; andwhile the device is in a locked state: receiving a second speech input at the device, the second speech input including a command associated with a restricted feature of the device;authenticating, using the second speech input, whether the second speech input is spoken by an authorized user of the device, wherein the authenticating includes comparing the second speech input to the text-independent voiceprint;in response to authenticating that the second speech input is spoken by an authorized user of the device, executing the command identified in the speech input to invoke the restricted feature of the device; andin response to not authenticating that the speech input is spoken by an authorized user of the device, forgo executing the command identified in the speech input to invoke the restricted feature of the device, where the method is performed by one or more processors of the device. 14. The method of claim 13, further comprising: generating a plurality of voice samples based on the first speech input, the plurality of voice samples including the voice sample;storing the plurality of voice samples on the device; andtransmitting the stored plurality of voice samples to the voiceprint service for generating the text-independent voiceprint based on the plurality of voice samples. 15. The method of claim 14, further comprising: receiving the text-independent voiceprint from the voiceprint service through a network interface of the device. 16. The method of claim 13, further comprising: in response to failing to authenticate that the second speech input is spoken by an authorized user of the device, outputting an error indication. 17. The method of claim 13, wherein the text-independent voiceprint is generated without a training step. 18. A non-transitory computer-readable medium including one or more sequences of instructions which, when executed by one or more processors, causes: while a device is in a locked state, receiving non-voice authentication information from a user to put the device into an unlocked state;receiving, at the device, a first speech input from the user;in response to authenticating that the user is an authorized user of the device, transmitting the first speech input to a voiceprint service for generating a voiceprint based on the first speech input;receiving a second speech input at the device while the device is in a locked state, the second speech input including a command associated with a restricted feature of the device;determining whether the second speech input was spoken by an authorized user of the device, the determining including comparing the second speech input to the generated voiceprint;while comparing the second speech input to the voiceprint, processing the second speech input to identify the command; andupon determining that the second speech input was spoken by the authorized user, providing access to the restricted feature of the device according to the command included in the second speech input. 19. The non-transitory computer-readable medium of claim 18, wherein the voiceprint is a text-independent voiceprint. 20. A system comprising: at least one processor;memory storing a voiceprint; anda computer-readable medium including instructions which, when executed by the at least one processor, causes: while a device is in a locked state, receiving non-voice authentication information from a user to put the device into an unlocked state;receiving, at the device, a first speech input from the user;in response to authenticating that the user is an authorized user of the device, transmitting the first speech input to a voiceprint service for generating a voiceprint based on the first speech input;receiving a second speech input at the device while the device is in a locked state, the second speech input including a command associated with a restricted feature of the device;determining whether the second speech input was spoken by an authorized user of the device, the determining including comparing the second speech input to the generated voiceprint;while comparing the second speech input to the voiceprint, processing the second speech input to identify the command; andupon determining that the second speech input was spoken by the authorized user, providing access to the restricted feature of the device according to the command included in the second speech input. 21. The system of claim 20, wherein the voiceprint is a text-independent voiceprint. 22. A non-transitory computer-readable medium including one or more sequences of instructions which, when executed by one or more processors, causes: while a device is in a locked state: receiving a speech input at the device, the speech input including a command associated with a restricted feature of the device;authenticating, using the speech input, whether the speech input is spoken by an authorized user of the device, wherein the authenticating includes comparing the speech input to a previously generated voiceprint;in response to authenticating that the speech input is spoken by an authorized user of the device, executing the command identified in the speech input to invoke the restricted feature of the device; andin response to not authenticating that the speech input is spoken by an authorized user of the device, forgo executing the command identified in the speech input to invoke the restricted feature of the device. 23. A method comprising: at an electronic device: receiving a plurality of voice commands from a user;generating a plurality of voice samples of the user from the plurality of voice commands;while the device is in a locked state, receiving non-voice authentication information from the user to put the device into an unlocked state;in response to authenticating that the user is an authorized user of the device, transmitting the plurality of voice samples to a voiceprint service for generating a voiceprint based on the plurality of voice samples;receiving a speech input, the speech input including a command associated with a restricted feature of the device;determining whether the speech input was spoken by an authorized user of the device, the determining including comparing the speech input to the generated voiceprint;processing the speech input to identify the command; andupon determining that the second speech input was spoken by the authorized user, providing access to the restricted feature of the device according to the command, where the method is performed by one or more processors of the device. 24. The method of claim 23, wherein the plurality of voice samples are transmitted in batches to the voiceprint service in response to the device experiencing low resource usage. 25. The method of claim 23, wherein the plurality of voice samples are transmitted in batches to the voiceprint service in response to the device being in an idle state.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.