Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
Response to Arguments
Applicant's arguments with respect to claims 1-20 have been considered but are moot in view of the new ground(s) of rejection. Applicant’s arguments are directed to the amended subject matter; new prior art is provided below.
Prior art US 20180293988 A1 HUANG; Jonathan J. et al. has been withdrawn and replaced with US 20220122614 A1 Pelecanos; Jason et al.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 20210043191 A1 Chao; Pu-sen et al. (hereinafter Chao) in view of US 20220122614 A1 Pelecanos; Jason et al. (hereinafter Pelecanos).
Re claim 1, Chao teaches
1. An electronic device comprising: at least one processor including processing circuitry; and memory storing instructions, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to: (fig. 1 and 5)
receive an utterance from a user; (input at fig. 2 e.g. user request)
perform speaker recognition on the utterance; (using a speaker recognition model to determine if a speaker is the person speaking and updated thereof as new inputs come in and are added to past inputs 0016… and for instance at the client device or other devices 0061-0063 using fig. 2-4, a user inputs a request as TD speech in, if it fails, then TI speech input, if that fails the system proceeds as a guest user and still obtain context/intent to handle a non-user model general/guest speech recognition operation 0082 and learning thereof to update the model 0012, false positives can occur between TD speech input and TI speech input, thereby learning takes place 0008-0009 with 0012)
However, while learning and model updates take place following false positive/rejection, as well as the ability to still process a speech query, Chao fails to teach:
when the speaker recognition on the utterance fails, detect a related event which is related to an action corresponding to an intent of the utterance for which the speaker recognition failed (Pelecanos the event is the action to be performed e.g. use command “what is next on my calendar?” as in fig. 1b where a false reject is established in context with a command that the system can process e.g. accessing a calendar and providing the results to a user e.g. intent 0035-0036)
output information corresponding to the related even related event being detected; and (Pelecanos although intent is established and a command can be processed as in fig. 1c, output information when a false reject is established would be “sorry, I could not verify your voice: the event is the action to be performed e.g. use command “what is next on my calendar?” as in fig. 1b where a false reject is established in context with a command that the system can process e.g. accessing a calendar and providing the results to a user e.g. intent 0035-0036 and also in fig. 1c evidencing the systems ability to understand intent)
obtain feedback from the user on the information corresponding to the related event, and (Pelecanos the second input by the user is a form of feedback e.g. repeating the command and slower… following the premise that although intent is established and a command can be processed as in fig. 1c, output information when a false reject is established would be “sorry, I could not verify your voice: the event is the action to be performed e.g. use command “what is next on my calendar?” as in fig. 1b where a false reject is established in context with a command that the system can process e.g. accessing a calendar and providing the results to a user e.g. intent 0035-0036 and also in fig. 1c evidencing the systems ability to understand intent)
wherein the feedback is used to update a speaker model for the utterance for which the speaker recognitio (Pelecanos updating a user model by the user re-enrolling such as due to false rejects e.g. 0040, based on false failures via subsequent inputs by the user is a form of feedback e.g. repeating the command and slower… following the premise that although intent is established and a command can be processed as in fig. 1c, output information when a false reject is established would be “sorry, I could not verify your voice: the event is the action to be performed e.g. use command “what is next on my calendar?” as in fig. 1b where a false reject is established in context with a command that the system can process e.g. accessing a calendar and providing the results to a user e.g. intent 0035-0036 and also in fig. 1c evidencing the systems ability to understand intent)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao to incorporate the above claim limitations as taught by Pelecanos to allow for a simple substitution of one known element such as direct user feedback through repetition and re-enrollment to update the existing speaker model of Chao, which allows for system to update the user's voice model with new, high-quality, or representative samples, which directly reduces the false rejection rate, such as when over time, a user's voice may change, or they may use different devices, causing the initial enrolment to become obsolete, where re-enrollment or repetition allows the model to adapt to these changes and also prevent false acceptance, in addition to accuracy and security.
Re claim 13, this claim has been rejected for teaching a broader, or narrower claim based on general inclusion of hardware alone (e.g. processor, memory, instructions), representation of claim 1 omitting/including hardware for instance, otherwise amounting to a virtually identical scope
Re claim 14, this claim has been rejected for teaching a broader, or narrower claim based on general inclusion of hardware alone (e.g. processor, memory, instructions), representation of claim 1 omitting/including hardware for instance, otherwise amounting to a virtually identical scope.
For instance, fig. 1 and fig. 5 of Chao.
Re claims 2 and 15, Chao teaches
2. The electronic device of claim 1, wherein the utterance for which the speaker recognition has failed is an utterance for which intent recognition is successful. (for instance at the client device or other devices 0061-0063using fig. 2-4, a user inputs a request as TD speech in, if it fails, then TI speech input, if that fails the system proceeds as a guest user and still obtain context/intent to handle a non-user model general/guest speech recognition operation 0082 and learning thereof to update the model 0012, false positives can occur between TD speech input and TI speech input, thereby learning takes place 0008-0009 with 0012)
Re claims 3 and 16, while learning and model updates take place following false positive/rejection, as well as the ability to still process a speech query, Chao fails to teach:
3. The electronic device of claim 1, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to generate a detection event corresponding to the related event, in response to the related event is detecteaction to be performed e.g. use command “what is next on my calendar?” as in fig. 1b where a false reject is established in context with a command that the system can process e.g. accessing a calendar and providing the results to a user e.g. intent 0035-0036 and also in fig. 1c evidencing the systems ability to understand intent)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao to incorporate the above claim limitations as taught by Pelecanos to allow for a simple substitution of one known element such as direct user feedback through repetition and re-enrollment to update the existing speaker model of Chao, which allows for system to update the user's voice model with new, high-quality, or representative samples, which directly reduces the false rejection rate, such as when over time, a user's voice may change, or they may use different devices, causing the initial enrolment to become obsolete, where re-enrollment or repetition allows the model to adapt to these changes and also prevent false acceptance, in addition to accuracy and security.
Re claims 4 and 17, while learning and model updates take place following false positive/rejection, as well as the ability to still process a speech query, Chao fails to teach:
4. The electronic device of claim 1, wherein the detection event comprises an event for detecting input which comprises the action corresponding to the intent of the utterance for which the speaker recognition failed, wherein the user input is received after the utterance
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao to incorporate the above claim limitations as taught by Pelecanos to allow for a simple substitution of one known element such as direct user feedback through repetition and re-enrollment to update the existing speaker model of Chao, which allows for system to update the user's voice model with new, high-quality, or representative samples, which directly reduces the false rejection rate, such as when over time, a user's voice may change, or they may use different devices, causing the initial enrolment to become obsolete, where re-enrollment or repetition allows the model to adapt to these changes and also prevent false acceptance, in addition to accuracy and security.
Re claim 5, Chao teaches
5. The electronic device of claim 1, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic devicedetection event based on an occurrence time of the utterance for which the speaker recognition has failed and an intent of the utterance for which the speaker recognition has failed. (when there is failure, intent can be included, using time as a factor in analysis 0085, for instance at the client device or other devices 0061-0063using fig. 2-4, a user inputs a request as TD speech in, if it fails, then TI speech input, if that fails the system proceeds as a guest user and still obtain context/intent to handle a non-user model general/guest speech recognition operation 0082 and learning thereof to update the model 0012, false positives can occur between TD speech input and TI speech input, thereby learning takes place 0008-0009 with 0012)
Re claims 6 and 18, Chao teaches
6. The electronic device of claim 1, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device0063using fig. 2-4, a user inputs a request as TD speech in, if it fails, then TI speech input, if that fails the system proceeds as a guest user and still obtain context/intent to handle a non-user model general/guest speech recognition operation 0082 and learning thereof to update the model 0012, false positives can occur between TD speech input and TI speech input, thereby learning takes place 0008-0009 with 0012)
Re claims 7 and 19, Chao teaches
7. The electronic device of claim 1, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device
Re claims 8 and 20, Chao teaches
8. The electronic device of claim 7, wherein the user interface is configured to perform at least one of: output an audio signal of the utterance for which the speaker recognitio
output a question about the use
Re claim 9, while learning and model updates take place following false positive/rejection, as well as the ability to still process a speech query, Chao fails to teach:
9. The electronic device of claim 1, wherein the feedback is for determining whether the utterance for which the speaker recognition has failed is false-rejected. (Pelecanos updating a user model by the user re-enrolling such as due to false rejects e.g. 0040, based on false failures via subsequent inputs by the user is a form of feedback e.g. repeating the command and slower… following the premise that although intent is established and a command can be processed as in fig. 1c, output information when a false reject is established would be “sorry, I could not verify your voice: the event is the action to be performed e.g. use command “what is next on my calendar?” as in fig. 1b where a false reject is established in context with a command that the system can process e.g. accessing a calendar and providing the results to a user e.g. intent 0035-0036 and also in fig. 1c evidencing the systems ability to understand intent)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao to incorporate the above claim limitations as taught by Pelecanos to allow for a simple substitution of one known element such as direct user feedback through repetition and re-enrollment to update the existing speaker model of Chao, which allows for system to update the user's voice model with new, high-quality, or representative samples, which directly reduces the false rejection rate, such as when over time, a user's voice may change, or they may use different devices, causing the initial enrolment to become obsolete, where re-enrollment or repetition allows the model to adapt to these changes and also prevent false acceptance, in addition to accuracy and security.
Re claim 10, while learning and model updates take place following false positive/rejection, as well as the ability to still process a speech query, Chao fails to teach:
10. The electronic device of claim 1, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device“what is next on my calendar?” as in fig. 1b where a false reject is established in context with a command that the system can process e.g. accessing a calendar and providing the results to a user e.g. intent 0035-0036 and also in fig. 1c evidencing the systems ability to understand intent)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao to incorporate the above claim limitations as taught by Pelecanos to allow for a simple substitution of one known element such as direct user feedback through repetition and re-enrollment to update the existing speaker model of Chao, which allows for system to update the user's voice model with new, high-quality, or representative samples, which directly reduces the false rejection rate, such as when over time, a user's voice may change, or they may use different devices, causing the initial enrolment to become obsolete, where re-enrollment or repetition allows the model to adapt to these changes and also prevent false acceptance, in addition to accuracy and security.
Re claim 11, Chao teaches
11. The electronic device of claim 10, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device
Re claim 12, while learning and model updates take place following false positive/rejection, as well as the ability to still process a speech query, Chao fails to teach:
12. The electronic device of claim 1, wherein the speaker model is updated based on the utterance for which the speaker recognition has failed. (Pelecanos updating a user model by the user re-enrolling such as due to false rejects e.g. 0040, based on false failures via subsequent inputs by the user is a form of feedback e.g. repeating the command and slower… following the premise that although intent is established and a command can be processed as in fig. 1c, output information when a false reject is established would be “sorry, I could not verify your voice: the event is the action to be performed e.g. use command “what is next on my calendar?” as in fig. 1b where a false reject is established in context with a command that the system can process e.g. accessing a calendar and providing the results to a user e.g. intent 0035-0036 and also in fig. 1c evidencing the systems ability to understand intent)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chao to incorporate the above claim limitations as taught by Pelecanos to allow for a simple substitution of one known element such as direct user feedback through repetition and re-enrollment to update the existing speaker model of Chao, which allows for system to update the user's voice model with new, high-quality, or representative samples, which directly reduces the false rejection rate, such as when over time, a user's voice may change, or they may use different devices, causing the initial enrolment to become obsolete, where re-enrollment or repetition allows the model to adapt to these changes and also prevent false acceptance, in addition to accuracy and security.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20180374486 A1 CHEN Z et al.
Speaker recognition training
US 20110054899 A1 Phillips; Michael S. et al.
Model updates
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL COLUCCI whose telephone number is (571)270-1847. The examiner can normally be reached on M-F 9 AM - 7 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Flanders can be reached at (571)272-7516. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/MICHAEL COLUCCI/Primary Examiner, Art Unit 2655 (571)-270-1847
Examiner FAX: (571)-270-2847
Michael.Colucci@uspto.gov