SpeakWrite, LLC

Patent Trials and Appeals Board

Mar 30, 2021

2020000176 (P.T.A.B. Mar. 30, 2021)

UNITED STATES PATENT AND TRADEMARK OFFICE
UNITED STATES DEPARTMENT OF COMMERCE
United States Patent and Trademark Office
Address: COMMISSIONER FOR PATENTS
P.O. Box 1450
Alexandria, Virginia 22313-1450
www.uspto.gov
APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO.
15/479,695 04/05/2017 Richard Jackson 1730-702USPT 1032
58687 7590 03/30/2021
DUBOIS, BRYANT, & CAMPBELL, LLP
303 Colorado Street
Suite 2300
AUSTIN, TX 78701
EXAMINER
ROBERTS, SHAUN A
ART UNIT PAPER NUMBER
2657
NOTIFICATION DATE DELIVERY MODE
03/30/2021 ELECTRONIC
Please find below and/or attached an Office communication concerning this application or proceeding.
The time period for reply, if any, is set in the attached communication.
Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the
following e-mail address(es):
BWIESE@DBCLLP.COM
CHEUSMANN@DBCLLP.COM
SSTERLING@DBCLLP.COM
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
________________

BEFORE THE PATENT TRIAL AND APPEAL BOARD
________________

Ex parte RICHARD JACKSON
________________

Appeal 2020-000176
Application 15/479,695
Technology Center 2600
________________

Before JAMES R. HUGHES, JENNIFER L. McKEOWN, and
JASON J. CHUNG, Administrative Patent Judges.

CHUNG, Administrative Patent Judge.

DECISION ON APPEAL
Pursuant to 35 U.S.C. § 134(a), Appellant1 appeals the Final Rejection
of claims 1–13. We have jurisdiction under 35 U.S.C. § 6(b).
We AFFIRM.
INVENTION
The invention relates to enhancing security of payment transactions.
Spec. 2:11–12. Claim 1 is illustrative of the invention and is reproduced
below:
1. A method for transcribing multi-party
communication, comprising:

1 We use the word “Appellant” to refer to “applicant” as defined in
37 C.F.R. § 1.42. According to Appellant, Richard Jackson is the real party
in interest. Appeal Br. 2.
Appeal 2020-000176
Application 15/479,695

2
recording a plurality of speakers;
processing a first copy of the recording though a
diarisation process in which an audio stream is partitioned into
audio samples according to speaker identity to create a final
diarisation product;
processing a second copy of the recording through a
transcription process in which the recording is transcribed into
text to create a final transcription product;
using the final diarisation product to differentiate
individual speakers of the plurality of speakers in a final
transcript;
presenting the final transcript and audio samples of each
voice print identified through the diarisation process to a
reviewer to identify each of the differentiated individual
speakers; and
inserting the identity of each of the differentiated
individual speakers into the final transcript.
Appeal Br. 17 (Claims Appendix).

REJECTION
The Examiner rejects claims 1–13 under 35 U.S.C. § 103 as being
unpatentable over the combination of Ziv (US 2014/0074467 A1; published
Mar. 13, 2014) and Krishnaswamy (US 2010/0305945 A1; published Dec. 2,
2010). Final Act. 5–9.
ANALYSIS
I. Do Ziv and Krishnaswamy Teach Processing a Second Copy of the
Recording Through a Transcription Process?
The Examiner finds Ziv describes processing an audio file for
diarization independently from transcription and a transcription from an
audio file, which the Examiner maps to the limitation “processing a second
copy of the recording through a transcription process” recited in claim 1.
Appeal 2020-000176
Application 15/479,695

3
Ans. 6–7 (citing Ziv ¶¶ 11, 19, 43); Final Act. 6 (citing Ziv ¶¶ 4, 20–23, 43,
Fig. 1).
Appellant argues Ziv merely teaches one audio file is used in two
processes rather than the limitation “processing a second copy of the
recording through a transcription process” recited in claim 1. Appeal Br. 7–
9. We disagree with Appellant.
Ziv describes processing an audio file for diarization (i.e., first copy of
the recording) independently from transcription and a transcription from an
audio file (i.e., second copy), which teaches the limitation “processing a
second copy of the recording through a transcription process” recited in
claim 1. Ans. 6–7 (citing Ziv ¶¶ 11, 19, 43); Final Act. 6 (citing Ziv ¶¶ 4,
20–23, 43, Fig. 1).
Therefore, Appellant does not persuade us of error.
II. Do Ziv and Krishnaswamy Teach Using the Final Diarization Product
To Differentiate Individual Speakers of the Plurality of Speakers in the Final
Transcript?
The Examiner finds Ziv describes diarization that identifies individual
speakers; a separate diarization and transcription process, where the results
of each are used to create a final diarized transcript, which the Examiner
maps to the limitation “using the final diarization product to differentiate
individual speakers of the plurality of speakers in the final transcript” recited
in claim 1. Ans. 7–9 (citing Ziv ¶¶ 11, 22–28, 40, 43, 51, Fig. 1; Spec.
¶ 34); Final Act. 6 (citing Ziv ¶¶ 4, 25, 27–29, 40, Fig. 1).
Appellant argues Ziv merely teaches segmentation of an audio file
based upon signal entropy that seeks to identify segments of the audio data
that are likely to contain speech apart from segments that are likely to be
non-speech rather than the limitation “using the final diarization product to
Appeal 2020-000176
Application 15/479,695

4
differentiate individual speakers of the plurality of speakers in the final
transcript” recited in claim 1. Appeal Br. 9–11. We disagree with
Appellant.
Paragraph 34 of the Specification states that the final transcription
product is compared to the final diarization product. Ans. 8 (citing Spec.
¶ 34). Similarly, Ziv describes diarization that identifies individual speakers
(i.e., differentiates individual speakers), as well as separate diarization and
transcription processes, where the results of the separate processes are used
to create a final diarized transcript (i.e., final transcript), which teaches the
limitation “using the final diarization product to differentiate individual
speakers of the plurality of speakers in the final transcript” recited in claim
1. Ans. 7–9 (citing Ziv ¶¶ 11, 22–28, 40, 43, 51, Fig. 1; Spec. ¶ 34); Final
Act. 6 (citing Ziv ¶¶ 4, 25, 27–29, 40, Fig. 1).
Therefore, Appellant does not persuade us of error.
III. Do Ziv and Krishnaswamy Teach Presenting the Final Transcript and
Audio Samples of each Voice Print Identified During the Diarization
Process To a Reviewer?
The Examiner finds Ziv describes a final diarized transcript and audio
samples of voices identified through a diarization process, which the
Examiner maps to the limitation “presenting the final transcript and audio
samples of each voice print identified during the diarization process” recited
in claim 1. Ans. 8–10 (citing Ziv ¶¶ 43, 51). The Examiner finds
Krishnaswamy, in a same field of endeavor, depicts transcription of a multi-
party conversation and audio samples of voice prints to further allow a user
to identify speakers to ensure the proper identities are provided
corresponding to the transcript, which the Examiner maps to the limitation
Appeal 2020-000176
Application 15/479,695

5
“to the reviewer” recited in claim 1. Ans. 9–11 (citing Krishnaswamy ¶¶ 21,
24); Final Act. 6 (citing Krishnaswamy ¶¶ 21, 24).
Appellant argues Krishnaswamy merely teaches that voice profiles
against which the pitch and characteristics of the utterances in the audio
samples are compared are obtained from training utterances previously input
into the system rather than the limitation “presenting the final transcript and
audio samples of each voice print identified during the diarization process to
a reviewer” recited in claim 1. Appeal Br. 11–12. Appellant argues the
combination of Ziv and Krishnaswamy ignores the limitation “identified
through the diarization process.” Id. at 12. We disagree with Appellant.
One cannot show nonobviousness “by attacking references
individually” where the rejections are based on combinations of references.
In re Merck & Co., 800 F.2d 1091, 1097 (Fed. Cir. 1986) (citing In re
Keller, 642 F.2d 413, 425 (CCPA 1981)). In this case, the Examiner relies
on the combined teachings of Ziv and Krishnaswamy to account for
limitation of claim 1. More specifically, Ziv teaches a final diarized
transcript (i.e., final transcript) and audio samples of voices identified
through a diarization process (the clustered speaker segments), which
teaches “the final transcript and audio samples of each voice print identified
during the diarization process” recited in claim 1. Ans. 8–10 (citing Ziv
¶¶ 22–27, 43, 51). In a similar field of endeavor, Krishnaswamy teaches
transcription of a multi-party conversation and audio samples of voice prints
to further allow a user (i.e., reviewer) to identify speakers to ensure the
proper identities are provided corresponding to the transcript, which teaches
“presenting . . . to the reviewer” recited in claim 1. Ans. 9–11 (citing
Krishnaswamy ¶¶ 21, 24); Final Act. 6 (citing Krishnaswamy ¶¶ 21, 24).
Appeal 2020-000176
Application 15/479,695

6
Therefore, Appellant does not persuade us of error.
IV. Do Ziv and Krishnaswamy Teach Inserting the Identity of each of the
Differentiated Individual Speakers Into the Final Transcript?
The Examiner finds Ziv specifies identifying the speakers as speaker 1
and speaker 2 and Krishnaswamy details inserting speaker identifiers into a
transcript wherein Krishnaswamy identifies speakers using the sounds of the
speakers’ voices, which the Examiner maps to the limitation “inserting the
identity of each of the differentiated individual speakers into the final
transcript” recited in claim 1. Ans. 8, 11–12 (citing Ziv ¶¶ 22–28;
Krishnaswamy ¶¶ 24, 26; Spec. ¶ 37); Final Act. 6 (citing Ziv ¶¶ 25, 27–29,
40; Krishnaswamy ¶ 24).
Appellant argues when interpreting claims using the broadest
reasonable interpretation consistent with the Specification, a person having
ordinary skill in the art at the time of the invention would understand that an
identity of a speaker means inserting the name of the speaker into the
transcript. Appeal Br. 14 (citing Spec. ¶ 36). Furthermore, Appellant argues
the combination of Ziv and Krishnaswamy merely teaches speaker identities
as “speaker 1” and “speaker 2” rather than the limitation “presenting the
final transcript and audio samples of each voice print identified during the
diarization process to a reviewer” recited in claim 1. Appeal Br. 13–15.
Appellant argues the combination of Ziv and Krishnaswamy ignores the
limitation “identified through the diarization process.” Id. at 12. We
disagree with Appellant.
As an initial matter, we note that paragraph 36 of the Specification
uses open ended terms in stating
[t]he reviewer can listen to the audio samples and assign an
identity, such as a name, to each voice print, thereby identifying
Appeal 2020-000176
Application 15/479,695

7
each speaker 403. For example, the reviewer can listen to a
sample of the audio attributed to “Speaker 1” and identify the
audio as corresponding to a specific individual.
Spec. ¶ 36 (emphases added).
Furthermore, paragraph 37 of the Specification states “[u]sing the
input of these names or other identities from the reviewer, the final
completed transcript is compared to the diarisation and voiceprint results.”
Ans. 12 (citing Spec. ¶ 37) (emphasis added). Appellant’s Specification,
therefore, describes the identities including names using open ended and
non-limiting terms. Spec. ¶¶ 36–37. We, therefore, do not interpret the
claimed “identity” to mean “name” and, accordingly, Appellant’s claim does
not require inserting the speaker’s name into the transcript. “[A]ppellant’s
arguments fail from the outset because . . . they are not based on limitations
appearing in the claims.” See In re Self, 671 F.2d at 1348 (CCPA 1982).
Additionally, Ziv teaches identifying the speakers as speaker 1 and
speaker 2 (i.e., identity of each of the differentiated individual speakers) in a
final diarized transcript (i.e., final transcript), which teaches “identit[ifying]
each of the differentiated individual speakers [in] the final transcript” recited
in claim 1. Ans. 8–9, 11–12 (citing Ziv ¶¶ 22–28, 43, 51); Final Act. 6
(citing Ziv ¶¶ 25, 27–29, 40). Moreover, Krishnaswamy teaches inserting
speaker identifiers into a transcript wherein speakers are identified using the
sounds of the speakers’ voices, which teaches “inserting the identity of each
of the differentiated individual speakers into the final transcript” recited in
claim 1. Ans. 11–12 (citing Krishnaswamy ¶¶ 24, 26); Final Act. 6 (citing
Krishnaswamy ¶ 24).
Appellant does not argue claims 1–13 separately with particularity.
Appeal Br. 7–16. Accordingly, we sustain the Examiner’s rejection of:
Appeal 2020-000176
Application 15/479,695

8
(1) independent claims 1 and 8; and (2) dependent claims 2–7 and 9–13
under 35 U.S.C. § 103.
We have only considered those arguments that Appellant actually
raised in the Briefs. Arguments Appellant could have made, but chose not to
make, in the Briefs have not been considered and are deemed to be waived.
See 37 C.F.R. § 41.37(c)(1)(iv).

CONCLUSION

In summary:

No time period for taking any subsequent action in connection with
this appeal may be extended under 37 C.F.R. § 1.136(a)(1)(iv). See
37 C.F.R. § 1.136(a)(1)(iv).

AFFIRMED

Claim(s)
Rejected
35 U.S.C. § Reference(s)/Basis Affirmed Reversed
1–13 103 Ziv, Krishnaswamy 1–13