Introduction
1. This office action is in response to Applicant’s submission filed on 12/31/2025. Claims 1-20 are pending in the application and have been examined.
Notice of Pre-AIA or AIA Status
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
3. The Amendment filed 12/31/2025 has been entered and fully considered. With regard to the rejection under 35 USC 101, the amendments and arguments are persuasive, and that rejection is overcome. With regard to the rejections under 35 USC 103, the arguments present are moot in view of the new rejections below based on U.S. Pat. App. Pub. No. 20160189713 (Liu).
Claim Rejections - 35 USC § 103
4. 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 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.
5. Claims 1-8, 13-17, and 19 are rejected under 35 U.S.C. 103 as unpatentable over U.S. Pat. App. Pub. No. 20230135071 (Eden et al., hereinafter “Eden”) in view of U.S. Pat. App. Pub. No. 20190378515 (Kim et al., hereinafter “Kim”) and U.S. Pat. App. Pub. No. 20160189713 (Liu).
With regard to Claim 1, Eden describes:
“A computer-implemented method comprising:
determining, from a set of sentences in a textual transcript of a dialogue, [[the set of sentences comprising textual content of the dialogue,]] a first sentence spoken by a first speaker and a second sentence spoken by a second speaker; (Paragraph 28 describes that a transcript is received which is divided into utterances spoken by different participants.)
generating, utilizing a language model [[and without using audio or voice features,]] a first feature representation for the first sentence of the textual transcript and a second feature representation for the second sentence of the textual transcript; (Paragraph 35 describes that the device creates a representation for each utterance.)
generating a name representation for a name spoken in at least one of the first sentence or the second sentence; and (Paragraph 35 describes that the device creates a representation for each utterance. Thus, any names spoken would have a corresponding representation.)
Eden does not explicitly describe:
“the set of sentences comprising textual content of the dialogue;
generating, utilizing a language model and without using audio or voice features;
comparing, using the language model, each of the first feature representation and the second feature representation with the name representation to determine a speaker name for at least one of the first sentence or the second sentence.”
However, Kim describes:
“comparing, using the language model, each of the first feature representation and the second feature representation with the name representation to determine a speaker name for at least one of the first sentence or the second sentence.”
Paragraph 793 of Kim describes that the device can identify speaker titles in the input utterance to identify a speaker of one of the utterances. Paragraph 235 describes that features are compared using a model.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker identification as described by Kim into the invention of Eden to allow the device to identify the participants and their relationships, as described in paragraph 793 of Kim.
Eden in view of Kim does not explicitly describe:
“the set of sentences comprising textual content of the dialogue;
generating, utilizing a language model and without using audio or voice features;”
However, Liu describes:
“the set of sentences comprising textual content of the dialogue;
generating, utilizing a language model and without using audio or voice features;”
Paragraph 48 describes that, in one of the disclosed embodiments, the device identifies speakers based on the text of the transcript created by the device. Further, as the text only is used, the identification is not based on audio or voice features.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker identification using text as described by Liu into the invention of Eden in view of Kim to allow the device to identify the participants and their relationships based only on text, as described in paragraph 48 of Liu.
With regard to Claim 2, Eden describes:
“determining, from the set of sentences in the textual transcript, a third sentence of the textual transcript spoken by a third speaker; (Paragraph 28 describes that a transcript is received which is divided into many utterances spoken by different participants.)
generating a third feature representation for the third sentence of the textual transcript.” (Paragraph 35 describes that the device creates a representation for each utterance.)
Eden does not explicitly describe:
“comparing the third feature representation with the name representation to determine whether the speaker name corresponds to the third sentence.”
However, Kim describes:
“comparing the third feature representation with the name representation to determine whether the speaker name corresponds to the third sentence.”
Paragraph 793 of Kim describes that the device can identify speaker titles in the input utterance to identify a speaker of one of the utterances.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker identification as described by Kim into the invention of Eden to allow the device to identify the participants and their relationships, as described in paragraph 793 of Kim.
With regard to Claim 3, Eden describes “determining the first sentence spoken by the first speaker and the second sentence spoken by the second speaker comprises determining that the first sentence is spoken before the second sentence.” Figure 5 of Eden shows that the device determines the speaker of many different sentences from the transcript, which includes the order of the utterances.
With regard to Claim 4, Eden describes “concatenating the first sentence and the second sentence into a text sequence; and generating the first feature representation for the first sentence and the second feature representation for the second sentence by processing the text sequence through a trained language model to determine word representations from the first sentence and the second sentence.”
Paragraph 35 of Eden describes that the device creates a representation for each utterance. An utterance may be a single word (i.e. “Hello”), or multiple sentences in a row. As Eden describes basing the representation on each utterance, multiple sentences can be concatenated together for the representation.
With regard to Claim 5, Eden does not explicitly describe this subject matter. However, Kim describes “comparing the first feature representation with the name representation comprises determining a probability score for the first feature representation indicating a probability that the speaker name belongs to the first speaker.” Paragraph 242 describes that the words in each utterance are identified based on a probability that the word in question is, for example, a title.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker identification as described by Kim into the invention of Eden to allow the device to identify the participants and their relationships, as described in paragraph 793 of Kim.
With regard to Claim 6, Eden describes “generating name representations for each of the multiple spoken names.” (Paragraph 35 describes that the device creates a representation for each utterance.)
Eden does not explicitly describe:
“determining that the at least one of the first sentence or the second sentence of the textual transcript comprises multiple spoken names; and
comparing each of the name representations with each of the first feature representation and the second feature representation to determine probability scores for each of the name representations, wherein the probability scores indicate probabilities that corresponding names of the multiple spoken names belong to the first speaker.”
However, Kim describes:
“determining that the at least one of the first sentence or the second sentence of the textual transcript comprises multiple spoken names; and (Paragraph 793 of Kim describes that the device can identify speaker titles in the input utterance to identify a speaker of one of the utterances. Any title spoken in each sentence would be identified.)
comparing each of the name representations with each of the first feature representation and the second feature representation to determine probability scores for each of the name representations, wherein the probability scores indicate probabilities that corresponding names of the multiple spoken names belong to the first speaker.” (Paragraph 242 describes that the words in each utterance are identified based on a probability that the word in question is, for example, a title.)
With regard to Claim 7, Eden describes:
“one or more memory devices comprising a language model and a textual transcript of a dialogue; and (Paragraph 25)
one or more processors (Paragraph 25) configured to cause the system to:
determine, from a set of sentences in the textual transcript, [[the set of sentences comprising textual content of the dialogue,]] a first sentence spoken by a first speaker, a second sentence spoken by a second speaker, and a third sentence spoken by a third speaker; (Paragraph 28 describes that a transcript is received which is divided into utterances spoken by different participants.)
generate, utilizing the language model [[and without using audio or voice features]], a first feature representation for the first sentence of the textual transcript, a second feature representation for the second sentence of the textual transcript, and a third feature representation for the third sentence of the textual transcript.” (Paragraph 35 describes that the device creates a representation for each utterance.)
Eden does not explicitly describe:
“the set of sentences comprising textual content of the dialogue;
generating, utilizing a language model and without using audio or voice features;
determine, using the language model, a speaker name for at least one of the first sentence, the second sentence, or the third sentence by comparing each of the first feature representation, the second feature representation, and the third feature representation with a name representation for a spoken name in at least one of the first sentence, the second sentence, or the third sentence.”
However, Kim describes:
“determine, using the language model, a speaker name for at least one of the first sentence, the second sentence, or the third sentence by comparing each of the first feature representation, the second feature representation, and the third feature representation with a name representation for a spoken name in at least one of the first sentence, the second sentence, or the third sentence.”
Paragraph 793 of Kim describes that the device can identify speaker titles in the input utterance to identify a speaker of one of the utterances.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker identification as described by Kim into the invention of Eden to allow the device to identify the participants and their relationships, as described in paragraph 793 of Kim.
Eden in view of Kim does not explicitly describe:
“the set of sentences comprising textual content of the dialogue;
generating, utilizing a language model and without using audio or voice features;”
However, Liu describes:
“the set of sentences comprising textual content of the dialogue;
generating, utilizing a language model and without using audio or voice features;”
Paragraph 48 describes that, in one of the disclosed embodiments, the device identifies speakers based on the text of the transcript created by the device. Further, as the text only is used, the identification is not based on audio or voice features.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker identification using text as described by Liu into the invention of Eden in view of Kim to allow the device to identify the participants and their relationships based only on text, as described in paragraph 48 of Liu.
With regard to Claim 8, Eden does not explicitly describe this subject matter. However, Kim describes “determine a first pair vector from the first feature representation and the name representation;
determine a second pair vector from the second feature representation and the name representation; and
determine a third pair vector from the third feature representation and the name representation.”
Paragraph 234 of Kim describes that the input is converted into a feature vector, i.e. a feature representation, and stored in memory. Paragraph 763 of Kim describes that the titles of all the speakers are also stored in memory. Thus, these can be considered “vectors” as they are all stored in memory together.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker identification as described by Kim into the invention of Eden to allow the device to identify the participants and their relationships, as described in paragraph 793 of Kim.
With regard to Claim 13, Eden describes “the one or more processors are further configured to cause the system to concatenate the name representation with the first feature representation to determine a first pair vector for the first sentence.”
Paragraph 35 of Eden describes that the device creates a representation for each utterance. An utterance may be a single word (i.e. “Hello”), or multiple sentences in a row. As Eden describes basing the representation on each utterance, multiple sentences can be concatenated together for the representation.
With regard to Claim 14, Eden describes “the one or more processors are configured to cause the system to determine the first sentence, the second sentence, and the third sentence by determining that the first speaker spoke the first sentence before the second speaker spoke the second sentence, and that the second speaker spoke the second sentence before the third speaker spoke the third sentence.”
Figure 5 of Eden shows that the device determines the speaker of many different sentences from the transcript, which includes the order of the utterances.
With regard to Claim 15, Eden describes “concatenate the first sentence, the second sentence, and the third sentence into a text sequence; and (Paragraph 35 of Eden describes that the device creates a representation for each utterance. An utterance may be a single word (i.e. “Hello”), or multiple sentences in a row. As Eden describes basing the representation on each utterance, multiple sentences can be concatenated together for the representation.)
generate each of the first feature representation for the first sentence, the second feature representation for the second sentence, and the third feature representation for the third sentence by processing the text sequence through the language model to determine word representations from the first sentence, the second sentence, and the third sentence.” (Paragraph 35 of Eden describes that the device creates a representation for each utterance. Paragraph 6 describes that the representations are created by the language model based on the utterances.)
With regard to Claim 16, Eden describes:
“A non-transitory computer-readable medium storing executable instructions that, when executed by a processing device, cause the processing device to perform operations comprising:
determining, from a set of sentences in a textual transcript of a dialogue, [[the set of sentences comprising textual content of the dialogue,]] a first sentence spoken by a first speaker and a second sentence spoken by a second speaker; (Paragraph 28 describes that a transcript is received which is divided into utterances spoken by different participants.)
generating, utilizing a language model [[and without using audio or voice features]], a first feature representation for the first sentence of the textual transcript of the dialogue and a second feature representation for the second sentence of the textual transcript of the dialogue; (Paragraph 35 describes that the device creates a representation for each utterance.)
Eden does not explicitly describe:
“the set of sentences comprising textual content of the dialogue;
generating, utilizing a language model and without using audio or voice features;
determining, using the language model, a speaker name for at least one of the first sentence or the second sentence by comparing each of the first feature representation and the second feature representation with a name representation for a name spoken in at least one of the first sentence or the second sentence.”
However, Kim describes:
“determining, using the language model, a speaker name for at least one of the first sentence or the second sentence by comparing each of the first feature representation and the second feature representation with a name representation for a name spoken in at least one of the first sentence or the second sentence.”
Paragraph 793 of Kim describes that the device can identify speaker titles in the input utterance to identify a speaker of one of the utterances.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker identification as described by Kim into the invention of Eden to allow the device to identify the participants and their relationships, as described in paragraph 793 of Kim.
Eden in view of Kim does not explicitly describe:
“the set of sentences comprising textual content of the dialogue;
generating, utilizing a language model and without using audio or voice features;”
However, Liu describes:
“the set of sentences comprising textual content of the dialogue;
generating, utilizing a language model and without using audio or voice features;”
Paragraph 48 describes that, in one of the disclosed embodiments, the device identifies speakers based on the text of the transcript created by the device. Further, as the text only is used, the identification is not based on audio or voice features.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker identification using text as described by Liu into the invention of Eden in view of Kim to allow the device to identify the participants and their relationships based only on text, as described in paragraph 48 of Liu.
With regard to Claim 17, Eden does not explicitly describe this subject matter. However, Kim describes:
“comparing the first feature representation with the name representation by determining a probability score for the first feature representation indicating a first probability that the speaker name belongs to the first speaker; and
comparing the second feature representation with the name representation by determining a probability score for the second feature representation indicating a second probability that the speaker name belongs to the second speaker.”
Paragraph 793 of Kim describes that the device can identify speaker titles in each input utterance to identify a speaker of one of the utterances. Paragraph 242 describes that the words in each utterance are identified based on a probability that the word in question is, for example, a title.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker identification as described by Kim into the invention of Eden to allow the device to identify the participants and their relationships, as described in paragraph 793 of Kim.
With respect to Claim 19, Eden describes “concatenating the name representation with the first feature representation to determine a [[pair]] vector for the first sentence.”
Paragraph 35 of Eden describes that the device creates a representation for each utterance. An utterance may be a single word (i.e. “Hello”), or multiple sentences in a row. As Eden describes basing the representation on each utterance, multiple sentences can be concatenated together for the representation.
Eden does not explicitly describe “determining, from the pair vector for the first sentence, a probability score indicating a probability that the name belongs to the first speaker.”
However, Kim describes “determining, from the pair vector for the first sentence, a probability score indicating a probability that the name belongs to the first speaker.”
Paragraph 234 of Kim describes that the input is converted into a feature vector, i.e. a feature representation, and stored in memory. Paragraph 763 of Kim describes that the titles of all the speakers are also stored in memory. Thus, these can be considered “vectors” as they are all stored in memory together. Paragraph 793 of Kim describes that the device can identify speaker titles in the input utterance to identify a speaker of one of the utterances.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker identification as described by Kim into the invention of Eden to allow the device to identify the participants and their relationships, as described in paragraph 793 of Kim.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker identification as described by Kim into the invention of Eden to allow the device to identify the participants and their relationships, as described in paragraph 793 of Kim.
6. Claims 9-11 are rejected under 35 U.S.C. 103 as unpatentable over Eden in view of Kim and Liu and further in view of U.S. Pat. App. Pub. No. 20240070401 (Qian et al., hereinafter “Qian”).
Eden does not explicitly describe the subject matter of Claim 9.
However, Kim describes: “determine, from the first pair vector utilizing a [[feed-forward]] network of the language model, a first probability score for the spoken name;
determine, from the second pair vector utilizing the [[feed-forward]] network of the language model, a second probability score for the spoken name; and
determine, from the third pair vector utilizing the [[feed-forward]] network of the language model, a third probability score for the spoken name.”
Paragraph 242 describes that the words in each utterance are identified based on a probability that the word in question is, for example, a title.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker identification as described by Kim into the invention of Eden to allow the device to identify the participants and their relationships, as described in paragraph 793 of Kim.
Eden in view of Kim and Liu does not explicitly describe a feed-forward network.
However, paragraph 14 of Qian describes a model that applies a feed-forward network to word vectors.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the feed-forward as described by Qian into the invention of Eden in view of Kim and Liu to generate a more accurate model, as described in paragraph 14 of Qian.
With regard to Claim 10, Eden does not explicitly describe this subject matter. However, Kim describes “compare the first probability score, the second probability score, and the third probability score to determine a match between the spoken name and at least one of the first speaker, the second speaker, or the third speaker.”
Paragraph 242 of Kim describes that the words in each utterance are identified based on a probability that the word in question is, for example, a title.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the speaker identification as described by Kim into the invention of Eden to allow the device to identify the participants and their relationships, as described in paragraph 793 of Kim.
Eden in view of Kim and Liu does not explicitly describe the subject matter of Claim 11. However, Qian describes “cause the system to generate the name representation for the spoken name by averaging feature vectors for each word in the spoken name.” Paragraph 12 of Qian describes averaging feature vectors across words.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the vector averaging as described by Qian into the invention of Eden in view of Kim and Liu to more accurately train the model, as described in paragraph 12 of Qian.
7. Claims 12 and 18 are rejected under 35 U.S.C. 103 as unpatentable over Eden in view of Kim, Liu, and Qian and further in view of U.S. Pat. App. Pub. No. 20210342551 (Yang et al., hereinafter “Yang”).
Eden in view of Kim, Liu, and Qian does not explicitly describe the subject matter of Claim 12.
However, Yang describes “generate the first feature representation for the first sentence by averaging word representations for each word in the first sentence.”
Paragraph 138 of Yang describes averaging word representations for each word.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the averaging word representations as described by Yang into the invention of Eden in view of Kim, Liu, and Qian to generate a word level embedding, as described in paragraph 138 of Yang.
Eden in view of Kim and Liu does not explicitly describe the subject matter of Claim 18.
However, Qian describes “generating the name representation for the name by averaging feature vectors for each word in the name.”
Paragraph 12 of Qian describes averaging feature vectors across words.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the vector averaging as described by Qian into the invention of Eden in view of Kim and Liu to more accurately train the model, as described in paragraph 12 of Qian.
Eden in view of Kim, Liu, and Qian do not explicitly describe “generating the first feature representation for the first sentence by averaging word representations for each word in the first sentence.”
However, Yang describes “generating the first feature representation for the first sentence by averaging word representations for each word in the first sentence.”
Paragraph 138 of Yang describes averaging word representations for each word.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the averaging word representations as described by Yang into the invention of Eden in view of Kim, Liu, and Qian to generate a word level embedding, as described in paragraph 138 of Yang.
Allowable Subject Matter
8. Claim 20 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Claim 20 would be allowable as the art of record does not disclose or suggest:
“identifying speaker names in a dialogue transcript;
anonymizing the speaker names by replacing the speaker names with generic speaker identities;
identifying spoken names within sentences of the dialogue transcript; and
mapping at least a subset of the spoken names to one or more of the generic speaker identities based on the speaker names.”
Conclusion
9. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
U.S. Pat. App. Pub. No. 20230223030 (Dutta et al.) also describes determining names of speakers from transcripts.
10. 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 nonprovisional extension fee (37 CFR 1.17(a)) 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 mailing date of this final action.
11. Any inquiry concerning this communication or earlier communications from the examiner should be directed to EDWARD TRACY whose telephone number is (571)272-8332. The examiner can normally be reached Monday-Friday 9 AM- 5PM.
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, Bhavesh Mehta can be reached on 571-272-7453. 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.
/EDWARD TRACY JR./Examiner, Art Unit 2656
/BHAVESH M MEHTA/Supervisory Patent Examiner, Art Unit 2656
Prosecution Insights