DETAILED ACTION
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 .
Information Disclosure Statement
The information disclosure statement(s) (IDS) submitted on 14 May 2024 and 15 August 2025 is/are being considered by the examiner.
Specification
Applicant is reminded of the proper language and format for an abstract of the disclosure.
The abstract should be in narrative form and generally limited to a single paragraph on a separate sheet within the range of 50 to 150 words in length. The abstract should describe the disclosure sufficiently to assist readers in deciding whether there is a need for consulting the full patent text for details.
The language should be clear and concise and should not repeat information given in the title. It should avoid using phrases which can be implied, such as, “The disclosure concerns,” “The disclosure defined by this invention,” “The disclosure describes,” etc. In addition, the form and legal phraseology often used in patent claims, such as “means” and “said,” should be avoided.
The abstract of the disclosure is objected to because the abstract uses legal phraseology (e.g., “comprises”) and is in excess of the word limit.
A corrected abstract of the disclosure is required and must be presented on a separate sheet, apart from any other text. See MPEP § 608.01(b).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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 1-5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brems (U.S. Pat. No. 5,566,272, hereinafter Brems) in view of Lam (U.S. Pat. App. Pub. No. 2006/0074664, hereinafter Lam).
Regarding claim 1, Brems discloses A speech recognition device comprising (Systems and methods described with reference to the ASR system using a “dynamic user interface process”; Brems, ¶ Col. 2, lines 47-50): a speech reception unit for receiving speech information indicating a single command among a plurality of commands (“a user is prompted for a speech input in step 400”; Brems, ¶ Col. 6, lines 12-15); a speech recognition unit for performing speech recognition on the single command (“the ASR module 305 interprets the user’s utterance in step 401”; Brems, ¶ Col. 6, lines 15-17) on the basis of the speech information received by the speech reception unit (The user utterance is derived from the speech input.; Brems, ¶ Col. 6, lines 15-17), and calculating a reliability of a recognition result of the single command (“after the ASR module 305 interprets the user’s utterance in step 401, the confidence in the interpretation is determined in step 403,” for the single command.; Brems, ¶ Col. 6, lines 15-17); a condition storage unit for storing a plurality of conditions that are used to determine whether or not to execute a confirmation process on the recognition result … (Discloses a plurality of conditions related to, at least, a “serious operation” requiring a “very high confidence” threshold value and a standard operation requiring a “moderate confidence” threshold value, respectively, where “historical information needed to differentiate between various classes of users can be stored in database 309 of FIG. 4 and retrieved in response to an individual’s access to speech processing unit 301” It is noted that, though the examples are limited to two conditions/confidence levels, “more than two confidence levels can be used, and the definitions of the various levels can differ”; Brems, ¶ Col. 4, lines 24-29; Col. 6, lines 1-11; Col. 7, lines 62-65); a determination unit for determining whether or not to execute the confirmation process (“the confidence in the interpretation is determined in step 403, and then assessed in terms of three possible levels, and three different interactions with the user may then occur.”; Brems, ¶ Col. 6, lines 15-19) on the basis of one condition among the plurality of conditions stored in the condition storage unit and the reliability calculated by the speech recognition unit (The interactions are based on both a specific condition of a plurality of conditions (e.g., the classification of a command in light of the “consequence of misinterpretation” such as a command being related to a “serious operation” requiring a “very high confidence” threshold value, as opposed to a standard operation having a “moderate confidence” threshold value) and based on the “confidence in the interpretation”; Brems, ¶ Col. 5, line 65 - Col. 6, line 11; Col. 7, lines 45-56); and an output unit for outputting the recognition result without executing the confirmation process (“if the interpretation has a very high likelihood of being correct, a positive result is reached in step 405, and the ASR interpretation is accepted without explicit verification in step 407”; Brems, ¶ Col. 6, lines 19-23) when the determination unit determines that the confirmation process is not to be executed (The determination of a “positive result” based on a very high likelihood (e.g., being above a threshold), results in a determination that “explicit verification” is unnecessary.; Brems, ¶ Col. 6, lines 19-23). However, Brems fails to expressly recite respectively in association with the plurality of commands.
Lam teaches systems and methods for “automated utterance verification (UV).” (Lam, ¶ [0003]). Regarding claim 1, Lam teaches a condition storage unit for storing a plurality of conditions that are used to determine whether or not to execute a confirmation process on the recognition result respectively in association with the plurality of commands (Discloses a system including “Decision threshold setting… used to reject/accept the keyword hypothesis...using a dynamic threshold for all words so that each individual word has a different threshold” which includes “setting individual thresholds for each hypothesized keyword”; Lam, ¶ [0032]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the dynamic user interface for ASR processing of Brems to incorporate the teachings of Lam to include respectively in association with the plurality of commands. Brems teaches the overall method of receiving a command, calculating confidence, and conditionally asking for confidence if the confidence is below a set condition (a confidence threshold), and then applies these conditions based on a plurality of broad categories and adapts those conditions based on user history. Lam teaches storing conditions (thresholds) respectively in association with each command to improve precision. A person having ordinary skill in the art would have known to combine the ASR systems of Brems with the individual conditions of Lam to improve the accuracy of Brems’ verification decision by accounting for the phonetic difficulty of specific words, as recognized by Lam. (Lam, ¶ [0019]).
Regarding claim 2, the rejection of claim 1 is incorporated. Brems and Lam disclose all of the elements of the current invention as stated above. Brems further discloses further comprising an updating unit for updating the one condition corresponding to the single command (“In accordance with the present invention, historical details, such as a success measure associated with previous verification attempts of the same user, can be used to dynamically alter or adapt the ASR process” where for users with “consistently... high confidence scores and/or who consistently succeed” the “verification step can be dispensed with, even if the confidence level is not ‘very high’ on some occasions.” Though described in Brems as being a confidence threshold adjustment corresponding to a category of commands, in light of a specified user, said confidence threshold adjustments corresponding to categories of commands necessarily corresponds to each individual command within each category.; Brems, ¶ Col. 7, lines 13-56) on the basis of acceptance information indicating acceptance or rejection of the recognition result (The “success measure associated with previous verification attempts of the same user” is derived from verified user acceptance (e.g., System: “Did you say [X]?” User: “Yes”) or rejection. Where, [X] in “Did you say [X]?” is the presentation of the recognition result for acceptance or rejection.; Brems, ¶ Col. 7, lines 33-44; Col. 8, lines 35-48), the acceptance information being received by the speech reception unit in the confirmation process (“the user is asked to explicitly verify (or dis-verify){...in the confirmation process} the result in step 413” {acceptance information being received...} where the response may be received “by voice or otherwise,” where “by voice” indicates that the response may be received by speech {the speech reception unit}; Brems, ¶ Col. 6, lines 24-28).
Regarding claim 3, the rejection of claim 2 is incorporated. Brems and Lam disclose all of the elements of the current invention as stated above. Brems further discloses wherein the one condition is a threshold (The conditions are the confidence threshold values (e.g., “very high confidence”, “moderate confidence”, etc.) in light of the operation types.; Brems, ¶ Col. 4, lines 20-29), and when the speech reception unit receives the acceptance information indicating acceptance in the confirmation process (As stated above, the “success measure associated with previous verification attempts of the same user, can be used to dynamically alter or adapt the ASR process”, specifically adapting by affecting (e.g., increase/reduce) the threshold requirement, where the “success measure associated with previous verification attempts of the same user” is derived from verified user acceptance (e.g., System: “Did you say [X]” User: “Yes”) or rejection, and “dynamically alter or adapt” indicates in real time or in response to real time information.; Brems, ¶ Col. 7, lines 13-44; Col. 8, lines 35-48), the updating unit updates the threshold corresponding to the single command to be smaller (for users with “consistently... high confidence scores and/or who consistently succeed” the “verification step can be dispensed with, even if the confidence level is not ‘very high’ on some occasions,” where dispensing with the verification is an updating of the threshold to be smaller.; Brems, ¶ Col. 7, lines 13-56).
Regarding claim 4, the rejection of claim 2 is incorporated. Brems and Lam disclose all of the elements of the current invention as stated above. Brems further discloses wherein the updating unit also updates the one condition (As stated above, the “success measure associated with previous verification attempts of the same user, can be used to dynamically alter or adapt the ASR process”, specifically adapting by affecting (e.g., increase/reduce) the threshold requirement, where the “success measure associated with previous verification attempts of the same user” is derived from verified user acceptance (e.g., System: “Did you say [X]” User: “Yes”) or rejection, and “dynamically alter or adapt” indicates in real time or in response to real time information.; Brems, ¶ Col. 7, lines 13-44; Col. 8, lines 35-48) on the basis of a reception history of the acceptance information received by the speech reception unit and/or system information (The “success measure associated with previous verification attempts of the same user” is derived from verified user acceptance (e.g., System: “Did you say [X]” User: “Yes”) or rejection, and is incorporated into the “historical ‘success measure’”, which is used for “dynamically” updating the confidence score threshold based on how often recognition is successful. Where, [X] in “Did you say [X]” is the presentation of the recognition result for acceptance or rejection.; Brems, ¶ Col. 7, lines 33-56; Col. 8, lines 35-48).
Regarding claim 5, Brems discloses A computer-readable storage medium storing commands for causing a computer to execute (Systems and methods described with reference to the “dynamic user interface process” which “operates under the control of stored programs contained in a memory such as database 309”; Brems, ¶ Col. 2, lines 47-50; Col. 5, lines 27-31): receiving speech information indicating a single command among a plurality of commands (“a user is prompted for a speech input in step 400”; Brems, ¶ Col. 6, lines 12-15); performing speech recognition on the single command on the basis of the received speech information (“the ASR module 305 interprets the user’s utterance in step 401” where the user utterance is derived from the speech input.; Brems, ¶ Col. 6, lines 15-17), and calculating a reliability of a recognition result of the single command (“after the ASR module 305 interprets the user’s utterance in step 401, the confidence in the interpretation is determined in step 403,” for the single command.; Brems, ¶ Col. 6, lines 15-17); determining whether or not to execute a confirmation process on the basis of one condition among a plurality of conditions that are used to determine whether or not to execute the confirmation process on the recognition result (Discloses a plurality of conditions related to, at least, a “serious operation” requiring a “very high confidence” threshold value and a standard operation requiring a “moderate confidence” threshold value, respectively, where “historical information needed to differentiate between various classes of users can be stored in database 309 of FIG. 4 and retrieved in response to an individual’s access to speech processing unit 301” It is noted that, though the examples are limited to two conditions/confidence levels, “more than two confidence levels can be used, and the definitions of the various levels can differ”; Brems, ¶ Col. 4, lines 24-29; Col. 6, lines 1-11; Col. 7, lines 62-65), the plurality of conditions being stored..., and the calculated reliability (Discloses a plurality of conditions related to, at least, a “serious operation” requiring a “very high confidence” threshold value and a standard operation requiring a “moderate confidence” threshold value, respectively, where “historical information needed to differentiate between various classes of users can be stored in database 309 of FIG. 4 and retrieved in response to an individual’s access to speech processing unit 301” It is noted that, though the examples are limited to two conditions/confidence levels, “more than two confidence levels can be used, and the definitions of the various levels can differ”; Brems, ¶ Col. 4, lines 24-29; Col. 6, lines 1-11; Col. 7, lines 62-65); and outputting the recognition result without executing the confirmation process (“if the interpretation has a very high likelihood of being correct, a positive result is reached in step 405, and the ASR interpretation is accepted without explicit verification in step 407”; Brems, ¶ Col. 6, lines 19-23) when it is determined that the confirmation process is not to be executed (The determination of a “positive result” based on a very high likelihood (e.g., being above a threshold), results in a determination that “explicit verification” is unnecessary.; Brems, ¶ Col. 6, lines 19-23). However, Brems fails to expressly recite the plurality of conditions being stored respectively in association with the plurality of commands.
The relevance of Lam is described above with relation to claim 1. Regarding claim 5, Lam teaches the plurality of conditions being stored respectively in association with the plurality of commands (Discloses “decision threshold setting is used to reject/accept the keyword hypothesis...using a dynamic threshold for all words so that each individual word has a different threshold” which includes “setting individual thresholds for each hypothesized keyword” which may be stored in a “storage device or mass storage 307”; Lam, ¶ [0032], [0034]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the dynamic user interface for ASR processing of Brems to incorporate the teachings of Lam to include the plurality of conditions being stored respectively in association with the plurality of commands. Brems teaches the overall method of receiving a command, calculating confidence, and conditionally asking for confidence if the confidence is below a set condition (a confidence threshold), and then applies these conditions based on a plurality of broad categories and adapts those conditions based on user history. Lam teaches storing conditions (thresholds) respectively in association with each command to improve precision. A person having ordinary skill in the art would have known to combine the ASR systems of Brems with the individual conditions of Lam to improve the accuracy of Brems’ verification decision by accounting for the phonetic difficulty of specific words, as recognized by Lam. (Lam, ¶ [0019]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Setlur (U.S. Pat. No. 5717826) discloses a speech recognition method and apparatus which has a first stage to provide keyword hypotheses and a second stage to provide testing of those hypotheses by utterance verification.
Dolfing (U.S. Pat. No. 6421640) discloses a method of automatically recognizing speech utterances, in which a recognition result is evaluated by means of a first confidence measure and a plurality of second confidence measures determined for a recognition result.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Sean E. Serraguard whose telephone number is (313)446-6627. The examiner can normally be reached 07:00-17:00 M-F.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Daniel C. Washburn can be reached at (571) 272-5551. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Sean E Serraguard/Patent Examiner, Art Unit 2657