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 .
This Office Action is in response to correspondence filed 07 June 2026 in reference to application 19/287,882. Claims 1-20 are pending and have been examined.
Response to Amendment
The amendment filed 07 June 2026 has been accepted and considered in this office action. Claims 1-7 and 9-20 have been amended.
Response to Arguments
Applicant’s arguments, see Remarks, filed 07 June 2026, with respect to the Restriction Requirement have been fully considered and are persuasive. The Restriction Requirement of the claims has been withdrawn in light of the claim amendments.
Specification
The title of the invention is not descriptive of the claimed invention. A new title is required that is clearly indicative of the invention to which the claims are directed.
Claim Objections
Applicant is advised that should claims 4 and 6 be found allowable, claims 4 and 6 will be objected to under 37 CFR 1.75 as being a substantial duplicate thereof. When two claims in an application are duplicates or else are so close in content that they both cover the same thing, despite a slight difference in wording, it is proper after allowing one claim to object to the other as being a substantial duplicate of the allowed claim. See MPEP § 608.01(m).
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 8 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 8 contains the trademark/trade name Chrome. Where a trademark or trade name is used in a claim as a limitation to identify or describe a particular material or product, the claim does not comply with the requirements of 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph. See Ex parte Simpson, 218 USPQ 1020 (Bd. App. 1982). The claim scope is uncertain since the trademark or trade name cannot be used properly to identify any particular material or product. A trademark or trade name is used to identify a source of goods, and not the goods themselves. Thus, a trademark or trade name does not identify or describe the goods associated with the trademark or trade name. In the present case, the trademark/trade name is used to identify/describe a web browser and, accordingly, the identification/description is indefinite.
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.
Claim(s) 1-3, 5, 10, 13-16, 18, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Bladsy et al. (US PAP 2021/0241777) in view of Streat et al. (US Patent 10,629,192).
Consider claim 1, Bladsy teaches a system for assisting communication of a user having impaired or non-standard speech (abstract) comprising:
a) a microphone configured to receive impaired speech input from a user (0040, microphones receiving speech from user);
b) a speech processing module configured to process the speech input into processed speech input (0040, A/D conversion, filtering, acoustic feature extraction);
d) a recognition engine configured to compare the processed speech input against stored user-associated models and output a comparison (0045-50, section of alternative recognition model for identified atypical speech used to perform speech recognition);
e) an output generation module configured to generate intelligible text output based on the comparison (0051, generating canonical transcription of atypical speech); and,
(f) a communication interface configured to insert or display the intelligible text output within an application, communication sessions, documentation field, browser interface or messaging interface (0051, also figure 1, 0025-31, transcriptions generated and provided to user communication session screens).
Bladsy does not specifically teach
c) a database storing user-associated speech mappings, vocabulary associations, or speech interpretation data;
d) a recognition engine configured to compare the processed speech input against stored user-associated speech mappings, vocabulary associations, or speech interpretation data and output a comparison.
In the same field of processing atypical speech, Streat teaches
c) a database storing user-associated speech mappings, vocabulary associations, or speech interpretation data (figure 4, col 7 lines 1-col 8 lines 24, user-specific phonetic mappings stored in a datastore);
d) a recognition engine configured to compare the processed speech input against stored user-associated speech mappings, vocabulary associations, or speech interpretation data and output a comparison (col 11 lines 15-20 performing recognition based on user-associated phonetic mappings).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to use user-specific phonetic mappings as taught by Streat in the system of Bladsy in order to increase accuracy of speech recognition for a particular user (Streat Background).
Consider claim 2, Bladsy teaches the system method of claim 1, wherein the speech processing module performs filtering, conditioning or enhancement of the acoustic speech input prior to the comparison (0040, filtering performed before further ASR processing).
Consider claim 3, Streat teaches the system method of claim 1, wherein the user-associated speech mappings comprise personalized vocabulary entries associated with the user (figure 4, col 7 lines 1-col 8 lines 24, user-specific phonetic mappings stored in a datastore).
Consider claim 5, Bladsy teaches The system method of claim 1, wherein the communication interface is configured to insert intelligible text into a messaging application or electronic mail application (0051, also figure 1, 0025-31, transcriptions generated and provided to user communication session screens, i.e. a messaging application).
Consider claim 10, Bladsy teaches The system of claim [[8]] 1, wherein the intelligible text output is generated substantially in real time during a live communication session (Figure 1, 0025-38, text is output during a conversation as it happens).
Consider claim 13, Bladsy teaches The system of claim 1, wherein at least a portion of the speech processing module, recognition engine, or database is implemented on a remote computing system accessible through a communication network (0039, ASR may take place on remote computing system, which would require networking to access.).
Consider claim 14, Bladsy teaches the system of claim 1, wherein the intelligible text output is configured for display to a caregiver, clinician, therapist, or communication participant (0051, also figure 1, 0025-31, transcriptions generated and provided to user communication session screens)
Consider claim 15, Bladsy teaches computer-implemented method for assisting communication for users having impaired or non-standard speech (abstract) comprising:
a) receiving acoustic speech input from a user (0040, microphones receiving speech from user);
b) conditioning or processing the acoustic speech input (0040, A/D conversion, filtering, acoustic feature extraction);
c) comparing the processed speech input against stored speech interpretation data (0045-50, section of alternative recognition model for identified atypical speech used to perform speech recognition);
d) generating intelligible text output based on the comparison (0051, generating canonical transcription of atypical speech);
e) inserting, transmitting, or displaying the intelligible text output within a software application or communication interface (0051, also figure 1, 0025-31, transcriptions generated and provided to user communication session screens).
Bladsy does not specifically teach
c) comparing the processed speech input against stored speech interpretation data associated with the user.
In the same field of processing atypical speech, Streat teaches
c) comparing the processed speech input against stored speech interpretation data associated with the user (figure 4, col 7 lines 1-col 8 lines 24, user-specific phonetic mappings stored in a datastore, col 11 lines 15-20 performing recognition based on user-associated phonetic mappings).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to use user-specific phonetic mappings as taught by Streat in the system of Bladsy in order to increase accuracy of speech recognition for a particular user (Streat Background).
Consider claim 16, Streat teaches the method system of claim 15, wherein the stored speech interpretation data comprises user-specific speech patterns associated with impaired speech wherein the real time captioning includes speaker identification to distinguish multiple simultaneous speakers (figure 4, col 7 lines 1-col 8 lines 24, user-specific phonetic mappings stored in a datastore).
Consider claim 18, Bladsy teaches The method system of claim 15, wherein the intelligible text output is displayed within a communication session between the user and a third party (0051, also figure 1, 0025-31, transcriptions generated and provided to user communication session screens, i.e. a messaging application).
Consider claim 20, Bladsy teaches The method system of claim 15, further comprising generating intelligible text output during a therapeutic, accessibility-oriented, communication assistance, or speech rehabilitation session (0051, also figure 1, 0025-31, transcriptions generated and provided to user communication session screens, i.e. a messaging application).
Claim(s) 4, 6 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Bladsy and Streat as applied to claims 1 above, and further in view of Schaedler et al. (US Patent 8,060,371).
Consider claim 4, Bladsy and Streat teach the system method of claim 1, but does not specifically teach wherein the communication interface is configured to insert intelligible text into a text entry field within a browser-based application.
In the same field of speech to text conversion, Schaedler teaches wherein the communication interface is configured to insert intelligible text into a text entry field within a browser-based application (col 4 lines 35-52, using speech recognition results to fill in forms within a web-browser.).
IT would have been obvious to one of ordinary skill in art at the time of effective filing to to use speech form filling as taught by Schaedler as in the system of Bladsy and Streat in order to increase user conveniences in interacting with webpages do not have explicit voice support (Schaedler background).
Claim 6 contains the same limitations as claim 4 and therefore is rejected for the same reasons.
Consider claim 19, Bladsy and Streat teach the method system of claim 15, but does not specifically teach wherein the software application comprises a documentation interface or form-entry interface.
In the same field of speech to text conversion, Schaedler teaches wherein the software application comprises a documentation interface or form-entry interface (col 4 lines 35-52, using speech recognition results to fill in forms within a web-browser.).
IT would have been obvious to one of ordinary skill in art at the time of effective filing to to use speech form filling as taught by Schaedler as in the system of Bladsy and Streat in order to increase user conveniences in interacting with webpages do not have explicit voice support (Schaedler background).
Claim(s) 7, 9, 11, 12, and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Bladsy and Streat as applied to claims 1 above, and further in view of Eakin et al. (US Patent 11,211,058).
Consider claim 7, Bladsy and Streat teach the system of claim 1, but does not specifically teach wherein the database is updateable using additional speech samples obtained from the user to improve future speech interpretation accuracy.
In the same field of user specific models, Eakin teaches wherein the database is updateable using additional speech samples obtained from the user to improve future speech interpretation accuracy (col 4 lines 5-30, 55-67, col 41 lines 41-54, speech and correct transcriptions may be used to update models).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to update user models as taught by Eakin in the system of Bladsy and Streat in order to increase speech recognition accuracy.
Consider claim 9, Bladsy and Streat teach the system of claim 1, but does not specifically teach wherein the recognition engine utilizes previously interpreted utterances associated with the user to improve future speech interpretation accuracy.
In the same field of user specific models, Eakin teaches wherein the recognition engine utilizes previously interpreted utterances associated with the user to improve future speech interpretation accuracy (col 4 lines 5-30, 55-67, col 41 lines 41-54, speech and correct transcriptions may be used to update models).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to update user models as taught by Eakin in the system of Bladsy and Streat in order to increase speech recognition accuracy.
Consider claim 11, Bladsy and Streat teach the system of claim 1, but does not specifically teach wherein the database is updateable based on additional speech samples obtained from the user.
In the same field of user specific models, Eakin teaches wherein the database is updateable based on additional speech samples obtained from the user (col 4 lines 5-30, 55-67, col 41 lines 41-54, speech and correct transcriptions may be used to update models).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to update user models as taught by Eakin in the system of Bladsy and Streat in order to increase speech recognition accuracy.
Consider claim 12, Bladsy and Streat teach the system of claim 1, but does not specifically teach wherein the recognition engine utilizes stored prior utterances associated with the user to improve speech interpretation accuracy.
In the same field of user specific models, Eakin teaches wherein the recognition engine utilizes stored prior utterances associated with the user to improve speech interpretation accuracy (col 4 lines 5-30, 55-67, col 41 lines 41-54, speech and correct transcriptions may be used to update models).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to update user models as taught by Eakin in the system of Bladsy and Streat in order to increase speech recognition accuracy.
Consider claim 17, Bladsy and Streat teach the method of claim 15, but does not specifically teach further comprising incorporating corrective user input into stored speech interpretation data for use in subsequent speech interpretation processing.
In the same field of user specific models, Eakin teaches further comprising incorporating corrective user input into stored speech interpretation data for use in subsequent speech interpretation processing (col 4 lines 5-30, 55-67, col 41 lines 41-54, speech and correct transcriptions may be used to update models).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to update user models as taught by Eakin in the system of Bladsy and Streat in order to increase speech recognition accuracy.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Bladsy in view of Schaedler in view of Streat and further in view of Wang et al (US PAP 2012/0323574).
Consider claim 8, Bladsy teaches A cloud-based speech rehabilitation system for mobile and web-based platforms (abstract, 0039, remote computing system and user portable device) comprising:
a) an application executable on client devices including mobile and desktop, said application providing a platform for rehabilitating impaired speech audio without rehabilitating the speaker (0045-50, section of alternative recognition model for identified atypical speech used to perform speech recognition, 0039, ASR may be performed at remote computer, 0026, recognizer trained on utterances of users with atypical speech);
b) an extension providing persistent speech rehabilitation capabilities configured for users with speech disabilities requiring accessibility accommodations (0045-50, section of alternative recognition model for identified atypical speech used to perform speech recognition, 0039, ASR may be performed at remote computer and provided to local device)
c) cloud server infrastructure configured to receive and process impaired speech audio transmitted from client devices over a network, wherein the processing occurs via non-local hardware using artificial intelligence training on user voice samples (0045-50, section of alternative recognition model for identified atypical speech used to perform speech recognition, 0039, ASR may be performed at remote computer, 0026, recognizer trained on utterances of users with atypical speech);
f) real-time processing capabilities that convert impaired speech into both intelligible text and synthesized speech output (0051, 0052, generating canonical transcript and synthesized canonical speech).
Bladsy does not specifically teach
a) the application is a web-based application executable on client devices including mobile and desktop browsers, said application providing a Software-as-a-Service platform;
b) a downloadable browser extension installable in Chrome browsers, said extension accessible from any website.
In the same field of speech to text conversion, Schaedler teaches
a) the application is a web-based application executable on client devices including mobile and desktop browsers, said application providing a Software-as-a-Service platform (figure 3a-3b, form filling on webpages using server based services and provided to client via plug in);
b) a downloadable browser extension installable in Chrome browsers, said extension accessible from any website (col 2 lines 38-56, providing a browser plug in).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to provide a browser plug in and an SaaS architecture as taught by Schaedler in the system of Bladsy in order to allow the methods to be implemented without installing large applications on the user device.
Bladsy and Schaedler do not specifically teach
d) personalized speech rehabilitation models stored in the cloud, each model fine-tuned using machine learning algorithms trained on user-specific speech input recorded during a personalized training phase;
converting impaired speech into both intelligible text and synthesized speech output based on pre-trained user models.
In the same field of processing atypical speech, Streat teaches
d) personalized speech rehabilitation models stored in the cloud, each model fine-tuned using machine learning algorithms trained on user-specific speech input recorded during a personalized training phase (figure 4, col 7 lines 1-col 8 lines 24, user-specific phonetic mappings stored in a datastore);
converting impaired speech into both intelligible text and synthesized speech output based on pre-trained user models (col 11 lines 15-20 performing recognition based on user-associated phonetic mappings. In combination with Bladsy, both a transcription and synthesized speech might be generated as described above).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to use user-specific phonetic mappings as taught by Streat in the system of Bladsy and Schaedler in order to increase accuracy of speech recognition for a particular user (Streat Background).
Bladsy, Schaedler and Streat do not specifically teach
e) website integration capabilities enabling the extension to detect active text input fields on telehealth platforms, medical documentation systems, and web-based applications, inject rehabilitated speech-to-text transcription directly into said input fields, and operate across diverse platforms including healthcare portals, accessibility tools, and medical record systems; and
enabling accessibility for users with speech impairments in medical and professional environments.
In the same field of speech to text conversion, Wang teaches
e) website integration capabilities enabling the extension to detect active text input fields on telehealth platforms, medical documentation systems, and web-based applications, inject rehabilitated speech-to-text transcription directly into said input fields, and operate across diverse platforms including healthcare portals, accessibility tools, and medical record systems (0021, 0038, 0041, 0079, 0080-87, 0096, filling in various medical forms and records using speech, which may account for accents etc, and be implemented by web-browsers ); and
enabling accessibility for users with speech impairments in medical and professional environments (0021, 0038, 0041, 0079, 0080-87, 0096, accented speech can be processed for use in medical environment).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to apply form filling to medical environments as taught by Wang in the system of Bladsy, Schaedler and Streat in order to provide convenience and increase accuracy in medical forms.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Malkin et al. ( US Patent 8,682,678) Cote et al. (US PAP 2005/0165602) and Paulik (US PAP 2018/0330737) teach different methods of customizing speech processing for users with different types of speech including atypical speech.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DOUGLAS C GODBOLD whose telephone number is (571)270-1451. The examiner can normally be reached 6:30am-5pm Monday-Thursday.
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, 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 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.
DOUGLAS GODBOLD
Examiner
Art Unit 2655
/DOUGLAS GODBOLD/ Primary Examiner, Art Unit 2655
Prosecution Insights