IP Library Granted Patent US 12,306,917
Granted Patent B2
US 12,306,917 · App. 17/275,076 · Granted May 20, 2025

Information processing apparatus, user authentication network system, and user authentication method

Inventors: Sadao Tsuruga (Kyoto, JP); Yasunobu Hashimoto (Kyoto, JP); Kazuhiko Yoshizawa (Kyoto, JP); Yoshinori Okada (Kyoto, JP)
Assignee: MAXELL, LTD.
G06F21/32G06F3/16G10L17/06G10L25/51G10L25/78
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,306,917
App. No.
17/275,076
Granted
May 20, 2025
Kind
B2
Abstract

An information processing apparatus includes a voice input processing unit, a memory, and a controller. The voice input processing unit takes in voice of a user of the information processing apparatus to convert the voice into a first voice signal. The controller extracts a first voice feature from the first voice signal to compare it with voice features registered in the memory. When the first voice feature is not matched with any voice features, the controller executes a process for storing the first voice feature in the memory to be associated with the registration target user, a process for generating a voice password based on the first voice feature, and a process for storing the voice password in the memory. The controller executes user authentication processing for an authentication target user by using the voice password in the memory by the user registering process.

Claims (38)

1. An information processing apparatus comprising:

a microphone;

a memory; and

a Central Processing Unit (CPU),

wherein the microphone is configured to take in a first voice uttered by a user of the information processing apparatus to convert the first voice into a first voice signal,

wherein the memory is configured to store programs that, when executed by the CPU, cause the CPU to:

extract a first voice feature from the first voice signal to compare the first voice feature with a voice feature of an already-registered user that has already been stored in the memory,

in a case where the first voice feature does not match the voice feature of the already-registered user with a degree of similarity exceeding a first threshold value, execute a process for storing the first voice feature in the memory so as to be associated with the user of the information processing apparatus, a process for generating a plurality of voice passwords based on the first voice feature, and a process for storing the plurality of voice passwords in the memory,

in a case where the first voice feature matches the voice feature of the already-registered user with the degree of similarity exceeding the first threshold value, execute a process for selecting a voice password from the plurality of voice passwords stored in the memory to present the selected voice password to the user of the information processing apparatus,

in response to that the microphone takes in a second voice uttered by the user of the information processing apparatus to convert the second voice into a second voice signal, execute a process for extracting a password from the second voice signal to compare the selected voice password with the extracted password,

in a case where the selected voice password matches the extracted password, execute a process for extracting a second voice feature from the second voice signal to compare the second voice feature with the voice feature of the already-registered user that has been stored in the memory,

in a case where the second voice feature matches the voice feature of the already-registered user with the degree of similarity exceeding a second threshold value, execute a process for notifying the user of the information processing apparatus that a user authentication processing is completed,

wherein the second threshold value is different from the first threshold value, and

wherein the CPU is configured to:

stop the user authentication processing in a case where the microphone does not take in a voice uttered by the user of the information processing apparatus within a predetermined time after presenting the selected voice password to the user of the information processing apparatus.

2. The information processing apparatus according to claim 1 ,

wherein the CPU is configured to select the voice password randomly from the plurality of voice passwords stored in the memory to present the selected voice password to the user of the information processing apparatus.

3. The information processing apparatus according to claim 1 ,

wherein the CPU is configured to update the voice feature of the already-registered user based on the second voice feature, generate a new voice password based on the updated voice feature, and store the updated voice feature and the new voice password.

4. The information processing apparatus according to claim 1 , wherein the second threshold value is set to be narrower than the first threshold value.

5. A user authentication method by an information processing apparatus, the information processing apparatus comprising a voice input processing unit, a memory, and a controller, the user authentication method comprising:

taking in, by the voice input processing unit, a first voice uttered by a user of the information processing apparatus to convert the first voice into a first voice signal;

extracting, by the controller, a first voice feature from the first voice signal;

comparing, by the controller, the first voice feature with a voice feature of an already-registered user that has already been stored in the memory;

storing, by the controller, the first voice feature in the memory so as to be associated with the user of the information processing apparatus to generate a plurality of voice passwords based on the first voice feature in a case where the first voice feature does not match the voice features of the already-registered user with a degree of similarity exceeding a first threshold value;

storing the plurality of the voice passwords in the memory;

selecting, by the controller, a voice password from the plurality of voice passwords stored in the memory in a case where the first voice feature matches the voice feature of the already-registered user with the degree of similarity exceeding the first threshold value;

presenting, by the controller, the selected voice password to the user of the information processing apparatus;

taking in, by the voice input processing unit, a second voice uttered by the user of the information processing apparatus to convert the second voice into a second voice signal;

extracting, by the controller, a password from the second voice signal to compare the selected voice password with the extracted password;

extracting, by the controller, a second voice feature from the second voice signal to compare the second voice feature with the voice feature of the already-registered user that has been stored in the memory in a case where the selected voice password matches the extracted password; and

notifying, by the controller, the user of the information processing apparatus that user authentication processing is completed in a case where the second voice feature matches the voice feature of the already-registered user with the degree of similarity exceeding a second threshold value,

wherein the second threshold value is different from the first threshold value, and

wherein the controller is configured to:

stop the user authentication processing in a case where a microphone of the information processing apparatus does not take in a voice uttered by the user of the information processing apparatus within a predetermined time after presenting the selected voice password to the user of the information processing apparatus.

6. The user authentication method according to claim 5 , further comprising:

stopping, by the controller, the user authentication processing in a case where the voice input processing unit does not take in a voice uttered by the user of the information processing apparatus within a predetermined time after presenting the selected voice password to the user of the information processing apparatus.

7. The user authentication method according to claim 5 , wherein the second threshold value is set to be narrower than the first threshold value.

Assignments (3)
CHANGE OF NAME Recorded Dec 3, 2021
From: MAXELL HOLDINGS, LTD.
To: MAXELL, LTD.
Reel/Frame 058666/0407 →
MERGER Recorded Nov 29, 2021
From: MAXELL, LTD.
To: MAXELL HOLDINGS, LTD.
Reel/Frame 058255/0579 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 26, 2021
From: TSURUGA, SADAO; HASHIMOTO, YASUNOBU; YOSHIZAWA, KAZUHIKO; OKADA, YOSHINORI
To: MAXELL, LTD.
Reel/Frame 055731/0756 →
Continuity (1)
Related Publication 20210256104A1 · Aug 19, 2021
References Cited (32)
US 6941269B1 · Cohen · 2005 [cited by examiner]
US 8369495B1 · Mallenahally Channakeshava · 2013 [cited by examiner]
US 20050089172A1 · Fujimoto · 2005 [cited by examiner]
US 20070129944A1 · Luan · 2007 [cited by examiner]
US 20090254757A1 · Toyama · 2009 [cited by examiner]
US 20100017209A1 · Yu · 2010 [cited by examiner]
US 20130132091A1 · Skerpac · 2013 [cited by examiner]
US 20130298213A1 · Macwan · 2013 [cited by examiner]
US 20140343943A1 · Al-Telmissani · 2014 [cited by examiner]
US 20150161370A1 · North · 2015 [cited by examiner]
US 20150301733A1 · Acevedo · 2015 [cited by examiner]
US 20160035350A1 · Jung et al. · 2016 [cited by applicant]
US 20170244701A1 · Su · 2017 [cited by examiner]
US 20180130475A1 · Page · 2018 [cited by examiner]
US 20190035407A1 · Keret · 2019 [cited by examiner]
US 20190349366A1 · Dewan · 2019 [cited by examiner]
US 20190378520A1 · Chiu · 2019 [cited by examiner]
JP 1020883A · 1998 [cited by applicant]
JP 10173644A · 1998 [cited by applicant]
JP 2001318692A · 2001 [cited by applicant]
JP 2003066985A · 2003 [cited by applicant]
JP 2003337801A · 2003 [cited by applicant]
JP 2005128307A · 2005 [cited by applicant]
JP 2009093256A · 2009 [cited by applicant]
JP 2016136299A · 2016 [cited by applicant]
JP 2017003611A · 2017 [cited by applicant]
Huan Feng et al., Continuous Authentication for Voice Assistants, Oct. 4, 2017, ACM, pp. 343-355. (Year: 2017). [cited by examiner]
Linghan Zhang et al., Hearing Your Voice is Not Enough: An Articulatory Gesture Based Liveness Detection for Voice Authentication, Oct. 30, 2017, ACM, pp. 57-71. (Year: 2017). [cited by examiner]
Fidalizia Pyrtuh et al., Comparative Evaluation of Feature Normalization Techniques for Voice Password based Speaker Verification , Mar. 20, 2014, IEEE, pp. 1-4. (Year: 2014). [cited by examiner]
Martha Birnbaum et al., A Voice Password System for Access Security, Sep.-Oct. 1986, ACM, vol. 65, Issue: 5, pp. 68-74. (Year: 1986). [cited by examiner]
The Extended European Search Report Issue in corresponding EP Application No. 18932980.8, dated Mar. 23, 2022. [cited by applicant]
International Search Report issued in corresponding International Patent Application No. PCT/JP2018/033885, dated Dec. 11, 2018, with English translation. [cited by applicant]