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 .
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they do not include the following reference signs mentioned in the description:
“1500” in paragraph 0056, line 8
“1501” in paragraph 0056, line 8
“1100” in paragraph 0056, line 8
“1101” in paragraph 0056, line 8
“110n” in paragraph 0056, line 8
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
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.
Claims 3, 10 and 17 are 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 3 recites the limitation "selecting an alternative text sample corresponding to the audio sample based on an encoding of allowable pronunciations for the alternative text sample, the alternative text sample including the correction text sample, and the correction text sample being based on the alternative text sample" in lines 1-4. This limitation is considered indefinite because the meaning of applying the limitations "the alternative text sample including the correction text sample" and "the correction text sample being based on the alternative text sample" is not clear. The alternative text sample including the correction text sample indicates that the alternative text sample is based on the correction text sample, making it unclear how the correction text sample is also based on the alternative text sample.
Claim 10 recites the limitation "select an alternative text sample corresponding to the audio sample based on an encoding of allowable pronunciations for the alternative text sample, the alternative text sample including the correction text sample, and the correction text sample being based on the alternative text sample" in lines 2-4. This limitation is considered indefinite because the meaning of applying the limitations "the alternative text sample including the correction text sample" and "the correction text sample being based on the alternative text sample" is not clear. The alternative text sample including the correction text sample indicates that the alternative text sample is based on the correction text sample, making it unclear how the correction text sample is also based on the alternative text sample.
Claim 17 recites the limitation "selecting an alternative text sample corresponding to the audio sample based on an encoding of allowable pronunciations for the alternative text sample, the alternative text sample including the correction text sample, and the correction text sample being based on the alternative text sample" in lines 2-5. This limitation is considered indefinite because the meaning of applying the limitations "the alternative text sample including the correction text sample" and "the correction text sample being based on the alternative text sample" is not clear. The alternative text sample including the correction text sample indicates that the alternative text sample is based on the correction text sample, making it unclear how the correction text sample is also based on the alternative text sample.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1 – 20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claim 1 is rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim recites a method for predicting pronunciation of a text sample, comprising: selecting, via processing circuitry, a predicted text sample corresponding to an audio sample; receiving, via the processing circuitry, a correction text sample corresponding to the audio sample; updating, via the processing circuitry, an encoding of allowable pronunciations of the correction text sample based on the predicted text sample and the audio sample, the updated encoding of allowable pronunciations of the correction text sample including a pronunciation of the predicted text sample; and predicting, via the processing circuitry, a pronunciation of the correction text sample based on the updated encoding of allowable pronunciations of the correction text sample.
The claim 1 limitations, under their broadest reasonable interpretation, cover performance of the limitations in the mind but for the recitation of generic computer components. That is, other than reciting “via processing circuitry”, nothing in the claim elements preclude the actions from practically being performed in the mind. For example, “selecting” in the context of this claim encompasses a person listening to audio of someone speaking, determining the words being spoken, and writing the words, “receiving” in the context of this claim encompasses a person reading text corrections written by the speaker, “updating” in the context of this claim encompasses a person writing phonetic symbols representing the pronunciation of the text, and “predicting” in the context of this claim encompasses a person determining the pronunciation of the text corrections. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites the additional element “processing circuitry”. The additional element amounts to no more than mere instructions to apply the exception using generic computer components. Examples of generic computer components can be found in paragraph 0057 of the specification, “The term "data processing apparatus" refers to data processing hardware and may encompass all kinds of apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers.”. Accordingly, the additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element amounts to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claim is not patent eligible.
Claims 2 – 6 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Claims 2 – 6 depend from claim 1, and thus recite the limitations of claim 1.
For the reasons discussed above for claim 1, the claim 1 limitations recite abstract ideas. The additional limitations of claims 2 – 6 do not preclude the steps of claim 1 from practically being performed in the mind. For example, a person using the method of claim 1 to identify similar documents could also perform the limitations of claims 2 – 6:
Claim 2: A person could determine words being spoken based on a pronunciation guide for words.
Claim 3: A person could determine words being spoken base on text correction provided by the speaker.
Claim 4: A person could write phonetic symbols representing the pronunciation of text transcribed from audio based on an acoustic similarity between a documented pronunciation of the words and the pronunciation of the words in the spoken audio.
Claim 5: A person could determine the pronunciation of corrected text sample using a grapheme to phoneme look-up table.
Claim 6: A person could determine the pronunciation of corrected text sample based on the pronunciation of the words in the spoken audio.
The claims do not integrate the judicial exception into a practical application. For the reasons discussed above for claim 1, the additional element amounts to no more than mere instructions to apply the exception using generic computer components. Accordingly, this element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. For the reasons discussed above for claim 1, mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claims are not patent eligible.
Claim 7 is rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim recites a device comprising: processing circuitry configured to select a predicted text sample corresponding to an audio sample, receive a correction text sample corresponding to the audio sample and based on the predicted text sample, update an encoding of allowable pronunciations of the correction text sample based on the predicted text sample and the audio sample, the updated encoding of allowable pronunciations of the correction text sample including a pronunciation of the predicted text sample, and predict a pronunciation of the correction text sample based on the updated encoding of allowable pronunciations of the correction text sample.
The claim 7 limitations, under their broadest reasonable interpretation, cover performance of the limitations in the mind but for the recitation of generic computer components. That is, other than reciting “a device” and “processing circuitry”, nothing in the claim elements preclude the actions from practically being performed in the mind. For example, “select” in the context of this claim encompasses a person listening to audio of someone speaking, determining the words being spoken, and writing the words, “receive” in the context of this claim encompasses a person reading text corrections written by the speaker, “update” in the context of this claim encompasses a person writing phonetic symbols representing the pronunciation of the text, and “predict” in the context of this claim encompasses a person determining the pronunciation of the text corrections. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites the additional elements “a device” and “processing circuitry”. The additional elements amount to no more than mere instructions to apply the exception using generic computer components. Examples of generic computer components can be found in paragraph 0057 of the specification, “The term "data processing apparatus" refers to data processing hardware and may encompass all kinds of apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers.”. Accordingly, the additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements amount to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claim is not patent eligible.
Claim 8 is rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Claim 8 depends from claim 7, and thus recite the limitations of claim 7.
For the reasons discussed above for claim 7, the claim 7 limitations recite abstract ideas. The additional limitation of claim 8 of receiving the audio sample from a second device is insignificant pre-solution activity that is well-understood and conventional. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components and insignificant extra-solution activity, then it falls within the “Mental Processes” grouping of abstract ideas.
The claim does not integrate the judicial exception into a practical application. The additional elements amount to no more than mere instructions to apply the exception using generic computer components and insignificant extra-solution activity. Accordingly, these elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. Mere instructions to apply an exception using generic computer components and insignificant extra-solution activity cannot provide an inventive concept. The claim is not patent eligible.
Claims 9 – 13 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Claims 9 – 13 depend from claim 7, and thus recite the limitations of claim 7.
For the reasons discussed above for claim 7, the claim 7 limitations recite abstract ideas. The additional limitations of claims 9 – 13 do not preclude the steps of claim 7 from practically being performed in the mind. For example, a person using the method of claim 7 to identify similar documents could also perform the limitations of claims 9 – 13:
Claim 9: A person could determine words being spoken based on a pronunciation guide for words.
Claim 10: A person could determine words being spoken base on text correction provided by the speaker.
Claim 11: A person could write phonetic symbols representing the pronunciation of text transcribed from audio based on an acoustic similarity between a documented pronunciation of the words and the pronunciation of the words in the spoken audio.
Claim 12: A person could determine the pronunciation of corrected text sample using a grapheme to phoneme look-up table.
Claim 13: A person could determine the pronunciation of corrected text sample based on the pronunciation of the words in the spoken audio.
The claims do not integrate the judicial exception into a practical application. For the reasons discussed above for claim 7, the additional elements amount to no more than mere instructions to apply the exception using generic computer components. Accordingly, these elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. For the reasons discussed above for claim 7, mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claims are not patent eligible.
Claim 14 is rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim recites a non-transitory computer-readable storage medium for storing computer-readable instructions that, when executed by a computer, cause the computer to perform a method, the method comprising: selecting a predicted text sample corresponding to an audio sample; receiving a correction text sample corresponding to the audio sample and based on the predicted text sample; updating an encoding of allowable pronunciations of the correction text sample based on the predicted text sample and the audio sample, the updated encoding of allowable pronunciations of the correction text sample including a pronunciation of the predicted text sample; and predicting a pronunciation of the correction text sample based on the updated encoding of allowable pronunciations of the correction text sample.
The claim 14 limitations, under their broadest reasonable interpretation, cover performance of the limitations in the mind but for the recitation of generic computer components. That is, other than reciting “a non-transitory computer-readable storage medium” and “a computer”, nothing in the claim elements preclude the actions from practically being performed in the mind. For example, “selecting” in the context of this claim encompasses a person listening to audio of someone speaking, determining the words being spoken, and writing the words, “receiving” in the context of this claim encompasses a person reading text corrections written by the speaker, “updating” in the context of this claim encompasses a person writing phonetic symbols representing the pronunciation of the text, and “predicting” in the context of this claim encompasses a person determining the pronunciation of the text corrections. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites the additional elements “a non-transitory computer-readable storage medium” and “a computer”. The additional elements amount to no more than mere instructions to apply the exception using generic computer components. Examples of generic computer components can be found in paragraph 0057 of the specification, “The term "data processing apparatus" refers to data processing hardware and may encompass all kinds of apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers.”. Accordingly, the additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements amount to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claim is not patent eligible.
Claim 15 is rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Claim 15 depends from claim 14, and thus recite the limitations of claim 14.
For the reasons discussed above for claim 14, the claim 14 limitations recite abstract ideas. The additional limitation of claim 15 of receiving the audio sample from a device is insignificant pre-solution activity that is well-understood and conventional. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components and insignificant extra-solution activity, then it falls within the “Mental Processes” grouping of abstract ideas.
The claim does not integrate the judicial exception into a practical application. The additional elements amount to no more than mere instructions to apply the exception using generic computer components and insignificant extra-solution activity. Accordingly, these elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. Mere instructions to apply an exception using generic computer components and insignificant extra-solution activity cannot provide an inventive concept. The claim is not patent eligible.
Claims 16 – 20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Claims 16 – 20 depend from claim 14, and thus recite the limitations of claim 14.
For the reasons discussed above for claim 14, the claim 14 limitations recite abstract ideas. The additional limitations of claims 16 – 20 do not preclude the steps of claim 14 from practically being performed in the mind. For example, a person using the method of claim 14 to identify similar documents could also perform the limitations of claims 16 – 20:
Claim 16: A person could determine words being spoken based on a pronunciation guide for words.
Claim 17: A person could determine words being spoken base on text correction provided by the speaker.
Claim 18: A person could write phonetic symbols representing the pronunciation of text transcribed from audio based on an acoustic similarity between a documented pronunciation of the words and the pronunciation of the words in the spoken audio.
Claim 19: A person could determine the pronunciation of corrected text sample using a grapheme to phoneme look-up table.
Claim 20: A person could determine the pronunciation of corrected text sample based on the pronunciation of the words in the spoken audio.
The claims do not integrate the judicial exception into a practical application. For the reasons discussed above for claim 14, the additional elements amount to no more than mere instructions to apply the exception using generic computer components. Accordingly, these elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. For the reasons discussed above for claim 14, mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claims are not patent eligible.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1 – 4, 6 – 11, 13 – 18 and 20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Bruguier et al. (US Patent No. 10,152,965), hereinafter Bruguier.
Regarding claim 1, Bruguier discloses a method for predicting pronunciation of a text sample, comprising:
selecting, via processing circuitry, a predicted text sample corresponding to an audio sample (Column 11, lines 6-18, "The process 200 may begin with a server 230 receiving 202 an utterance from a user 100 that includes a command and an entity. The utterance may be in the form of a set of audio signals. The server 230 may forward the received utterance to an automated speech recognizer that extracts 204 a portion of the utterance that is associated with the entity name. The extracted portion of the utterance corresponding to the entity name may then be associated with a timestamp, and stored in the memory associated with the server 230. The automated speech recognizer may generate 206 an initial transcription of the extracted portion of the audio signals."; Generating an initial transcription of an extracted portion of an audio signal reads on selecting a predicted text sample corresponding to an audio sample.);
receiving, via the processing circuitry, a correction text sample corresponding to the audio sample (Column 11, lines 43-46, "In some implementations, the server may obtain a correct transcription for the extracted portion of the audio signal at 208. The correct transcription may be based on, for example, feedback received from the user 100."; Obtaining a correct transcription for the extracted portion of the audio signal reads on receiving a correction text sample corresponding to the audio sample.);
updating, via the processing circuitry, an encoding of allowable pronunciations of the correction text sample based on the predicted text sample and the audio sample, the updated encoding of allowable pronunciations of the correction text sample including a pronunciation of the predicted text sample (Column 12, lines 8-22, "The server 230 may receive the correct transcription, and forward the correct transcription to the automated speech recognizer. The automated speech recognizer may obtain the extraction portion of the user's 100 audio signals that were previously stored based on timestamp. For instance, the automated speech recognizer may retrieve the extracted portion of the user's 100 audio signals that were associated with the most recent time stamp. The automated speech recognizer may then generate a phonetic pronunciation that corresponds to the extracted portion of the user's audio signals, as described above. Then, the automated speech recognizer may associate 210 the generated phonetic pronunciation with the received correct transcription. The generated phonetic pronunciation may correspond to the user's 100 unique pronunciation of an entity name."; Generating a phonetic pronunciation that corresponds to an extracted portion of a user's audio signals and associating the generated phonetic pronunciation with a received correct transcription reads on updating an encoding of allowable pronunciations of the correction text sample based on the predicted text sample and the audio sample, where the updated encoding of allowable pronunciations of the correction text sample including a pronunciation of the predicted text sample.);
and predicting, via the processing circuitry, a pronunciation of the correction text sample based on the updated encoding of allowable pronunciations of the correction text sample (Column 12, lines 23-35, "The automated speech recognizer may then update 212 an entry in the personalized pronunciation dictionary that includes an entity name that corresponds to the correct transcription based on the generated phonetic pronunciation. In some implementations, updating an entry in the personalized pronunciation dictionary may include replacing an initial pronunciation of an entity name with a user's unique pronunciation of the entity name by storing the generated phonetic pronunciation in the personalized pronunciation dictionary in place of the initial pronunciation of the entity name. This may include, for example, deleting the initial pronunciation of the entity name from the personalized pronunciation dictionary."; Updating an entry in a personalized pronunciation dictionary that includes an entity name that corresponds to a correct transcription based on a generated phonetic pronunciation reads on predicting a pronunciation of the correction text sample based on the updated encoding of allowable pronunciations of the correction text sample.).
Regarding claim 2, Bruguier discloses the method as claimed in claim 1.
Bruguier further discloses:
wherein the predicted text sample is selected based on an encoding of allowable pronunciations of the predicted text sample (Column 11, lines 16-33, "The automated speech recognizer may generate 206 an initial transcription of the extracted portion of the audio signals. An initial transcription of the extracted portion of the audio signals may be generated by implementing a series of one or more stages. For instance, the automated speech recognizer may use a model such as an acoustic model in order to identify a set of phonemes that may be associated with the extracted portion of the audio signals. Then, the phonemes may be mapped to a phonetic pronunciation that corresponds to the extracted portion of the audio signals. The phonetic pronunciation may then be used to retrieve an entity name from a user's personalized pronunciation dictionary. To the extent that an entry of the user's personalized pronunciation dictionary that is associated with a phonetic pronunciation that sufficiently matches the generated phonetic pronunciation cannot found, the automated search recognition unit may pick the closest match available to be utilized as the initial transcription."; Generating an initial transcription of an extracted portion of an audio signal, where the automated speech recognizer may use a model such as an acoustic model in order to identify a set of phonemes that may be associated with the extracted portion of the audio signals, reads on the predicted text sample being selected based on an encoding of allowable pronunciations of the predicted text sample.).
Regarding claim 3, as best understood based on the 35 U.S.C. 112(b) issues identified above, Bruguier discloses the method as claimed in claim 1.
Bruguier further discloses:
further comprising selecting an alternative text sample corresponding to the audio sample based on an encoding of allowable pronunciations for the alternative text sample, the alternative text sample including the correction text sample, and the correction text sample being based on the alternative text sample (Column 6, line 61 - Column 7, line 26, "In response to a receipt of the transcription 116 “Fortune,” and the additional information transmitted along with transcription 116, the mobile device 120 may prompt 124 the user 100 for feedback information related to the transcription 116. The mobile device 120 may generate the prompt 124, for example, in response to determining that the received transcription 116 was associated with an indication that the user's 100 personal pronunciation dictionary 152 in stage “A” did not include any entries that corresponded to the transcription “Fortune.” The prompt 124 may, for example, provide a list of one or more contact names that were stored in the user's 100 personal pronunciation dictionary 152 in stage “A” that are the closet match to the phonetic pronunciation used to generate the transcription 116. In one example, the prompt 124 may ask a user to select the contact name that the user 100 intended to call when the user vocalized the voice utterance 110 with an entity name pronounced “Fawr ⋅ chuh ⋅ n” 112. For instance, the list of contact names provided to the user 100 may include, Fuchini, Fucili, and Fuchun, each of which may be associated with an entry in the user's 100 personalized pronunciation dictionary 152 in state “A.” In some implementations, the list of contact names provided may not be phonetically close to the user's unique pronunciation of the entity name. For instance, the list of contact names provided in the prompt may be phonetically unrelated entity names such as, for example, Edwin, Fuchun, and Steve. In response to the prompt 124, the user selects “Fuchun,” as the user 100 knows that the entity name the user 100 vocalized in utterance 110 was “Fuchun.” In response to the user's 100 selection of “Fuchun,” the mobile device 120 may initiate a call to “Fuchun,” and also transmit 164 feedback information 118 to server 130."; Initiating a call to “Fuchun” in response to the user's selection of “Fuchun”, where the user is asked to select the contact name that the user intended to call when the user vocalized a voice utterance with an entity name pronounced “Fawr ⋅ chuh ⋅ n”, where the list of contact names provided to the user includes Fuchini, Fucili, and Fuchun, each of which are associated with an entry in the user's personalized pronunciation dictionary, reads on selecting an alternative text sample corresponding to the audio sample based on an encoding of allowable pronunciations for the alternative text sample, the alternative text sample including the correction text sample, and the correction text sample being based on the alternative text sample, where “Fuchun” reads on the correction text sample and the alternative text sample including the correction text sample.).
Regarding claim 4 Bruguier discloses the method as claimed in claim 1.
Bruguier further discloses:
wherein the updated encoding of allowable pronunciations of the correction text sample is based on an acoustic similarity between an allowable pronunciation and the pronunciation of the predicted text sample (Column 6, lines 43-60, "The server 130 may also transmit 162 additional information to mobile device 120 that may be associated with the transcription 116. For instance, the transcription 116 that may be transmitted 162 to the mobile device 120 may also be associated with an indication that the user's 100 personal pronunciation dictionary 152 in stage “A” did not include any entries that corresponded to the phonetic pronunciation “Fawr ⋅ chuh ⋅ n.” Alternatively, or in addition, the transcription 116 may also be associated with a list one or more contacts in a user's 100 personalized pronunciation dictionary 152, stage “A”, that may be the closest match to the generated phonetic pronunciation that corresponds to the extracted portion of audio signals 114. This additional information may be provided to the mobile device 120 by server 130 in order to prompt the user 100 for feedback information that may be used to help the personalized pronunciation dictionary 150 learn the unique entity pronunciation 112 uttered by user 100."; The transcription being associated with a list one or more contacts in a user's personalized pronunciation dictionary that are the closest match to the generated phonetic pronunciation that corresponds to the extracted portion of audio signals and providing this information to prompt the user for feedback information that may be used to help the personalized pronunciation dictionary learn the unique entity pronunciation uttered by the user reads on the updated encoding of allowable pronunciations of the correction text sample being based on an acoustic similarity between an allowable pronunciation and the pronunciation of the predicted text sample, where the closest phonetic pronunciation match between contacts in a user's personalized pronunciation and the extracted portion of audio signals reads on an acoustic similarity between an allowable pronunciation and the pronunciation of the predicted text sample.).
Regarding claim 6 Bruguier discloses the method as claimed in claim 1.
Bruguier further discloses:
wherein the predicted pronunciation of the correction text sample is predicted based on the pronunciation of the predicted text sample (Column 7, line 64 - Column 8, line 27, "The automated speech recognizer 140 may use the extracted portion of audio signals 114 and the feedback information 118 to teach the personalized pronunciation dictionary 150 the user's 100 unique pronunciation 112 of an entity name 110b. For instance, the automated speech recognizer 140 may generate a phonetic pronunciation for the extracted portion of the audio signals 114, as described above. Alternatively, the automated speech recognizer 140 may retrieve a previously generated phonetic pronunciation that corresponds to the extracted portion of the audio signals 114 that may have been generated, and stored, in response to the original receipt of audio signals 114. In this instance, the generated phonetic pronunciation of the extracted portion of the audio signal 114 that corresponds to the user's 100 unique pronunciation 112 of the entity name 110b in the vocalized utterance 110 may be “Fawr ⋅ chuh ⋅ n”. Automated speech recognizer 140 may then identify the entry from personalized pronunciation dictionary 152 that corresponds to the entity name 152 “Fuchun”. Next, automated speech recognizer 140 may update the personalized pronunciation dictionary entry associated with the entity “Fuchun” such that the entry's initial pronunciation of “Fyoo ⋅ chuh ⋅ n” is replaced by the user's 100 unique pronunciation “Fawr ⋅ chuh ⋅ n”. Replacing the initial pronunciation that corresponds to the entry that is associated with the entity name “Fuchun” with the user's 100 unique pronunciation “Fawr ⋅ chuh ⋅ n” transitions the user's personalized pronunciation dictionary 150 into stage “B”. In stage “B”, the user's 100 personalized pronunciation dictionary 154 includes an entry that associates the entity name 154a “Fuchun” with the user's 100 unique pronunciation “Fawr ⋅ chuh ⋅ n”."; An automated speech recognizer generating a phonetic pronunciation for the extracted portion of the audio reads on the pronunciation of the predicted text sample, and updating the personalized pronunciation dictionary entry associated with the entity “Fuchun” such that the entry's initial pronunciation of “Fyoo ⋅ chuh ⋅ n” is replaced by the user's unique pronunciation “Fawr ⋅ chuh ⋅ n” reads on predicting the pronunciation of the correction text sample.).
Regarding claim 7, Bruguier discloses a device comprising: processing circuitry (Column 3, lines 55-57, "The server 130 may be made up of one or more computing devices that each include a processor 132 and a memory 134.") configured to:
select a predicted text sample corresponding to an audio sample (Column 11, lines 6-18, "The process 200 may begin with a server 230 receiving 202 an utterance from a user 100 that includes a command and an entity. The utterance may be in the form of a set of audio signals. The server 230 may forward the received utterance to an automated speech recognizer that extracts 204 a portion of the utterance that is associated with the entity name. The extracted portion of the utterance corresponding to the entity name may then be associated with a timestamp, and stored in the memory associated with the server 230. The automated speech recognizer may generate 206 an initial transcription of the extracted portion of the audio signals."; Generating an initial transcription of an extracted portion of an audio signal reads on selecting a predicted text sample corresponding to an audio sample.);
receive a correction text sample corresponding to the audio sample and based on the predicted text sample (Column 11, lines 43-46, "In some implementations, the server may obtain a correct transcription for the extracted portion of the audio signal at 208. The correct transcription may be based on, for example, feedback received from the user 100."; Obtaining a correct transcription for the extracted portion of the audio signal reads on receiving a correction text sample corresponding to the audio sample and based on the predicted text sample.);
update an encoding of allowable pronunciations of the correction text sample based on the predicted text sample and the audio sample, the updated encoding of allowable pronunciations of the correction text sample including a pronunciation of the predicted text sample (Column 12, lines 8-22, "The server 230 may receive the correct transcription, and forward the correct transcription to the automated speech recognizer. The automated speech recognizer may obtain the extraction portion of the user's 100 audio signals that were previously stored based on timestamp. For instance, the automated speech recognizer may retrieve the extracted portion of the user's 100 audio signals that were associated with the most recent time stamp. The automated speech recognizer may then generate a phonetic pronunciation that corresponds to the extracted portion of the user's audio signals, as described above. Then, the automated speech recognizer may associate 210 the generated phonetic pronunciation with the received correct transcription. The generated phonetic pronunciation may correspond to the user's 100 unique pronunciation of an entity name."; Generating a phonetic pronunciation that corresponds to an extracted portion of a user's audio signals and associating the generated phonetic pronunciation with a received correct transcription reads on updating an encoding of allowable pronunciations of the correction text sample based on the predicted text sample and the audio sample, where the updated encoding of allowable pronunciations of the correction text sample including a pronunciation of the predicted text sample.);
and predict a pronunciation of the correction text sample based on the updated encoding of allowable pronunciations of the correction text sample (Column 12, lines 23-35, "The automated speech recognizer may then update 212 an entry in the personalized pronunciation dictionary that includes an entity name that corresponds to the correct transcription based on the generated phonetic pronunciation. In some implementations, updating an entry in the personalized pronunciation dictionary may include replacing an initial pronunciation of an entity name with a user's unique pronunciation of the entity name by storing the generated phonetic pronunciation in the personalized pronunciation dictionary in place of the initial pronunciation of the entity name. This may include, for example, deleting the initial pronunciation of the entity name from the personalized pronunciation dictionary."; Updating an entry in a personalized pronunciation dictionary that includes an entity name that corresponds to a correct transcription based on a generated phonetic pronunciation reads on predicting a pronunciation of the correction text sample based on the updated encoding of allowable pronunciations of the correction text sample.).
Regarding claim 8 Bruguier discloses the device as claimed in claim 7.
Bruguier further discloses:
wherein the processing circuitry is further configured to receive the audio sample from a second device (Column 5, lines 21-24, "Once the microphone has been activated, the user 100 may vocalize an utterance 110 that may be detected by the microphone 125 associated with user's mobile device 120."; Column 5, line 65 - Column 6, line 3, "Server 130 may receive the audio signals 114 that correspond to the utterance 110, and forward the received audio signals 114 to the automated speech recognizer 140. The automated speech recognizer 140 may then extract the portion of the audio signals 114 that corresponds to the entity name 110b."; A user's mobile device reads on a second device.).
Regarding claim 9, arguments analogous to claim 2 are applicable.
Regarding claim 10, arguments analogous to claim 3 are applicable.
Regarding claim 11, arguments analogous to claim 4 are applicable.
Regarding claim 13, arguments analogous to claim 6 are applicable.
Regarding claim 14, Bruguier discloses a non-transitory computer-readable storage medium for storing computer-readable instructions that, when executed by a computer, cause the computer to perform a method (Column 3, lines 55-59, "The server 130 may be made up of one or more computing devices that each include a processor 132 and a memory 134. The processor 132 may be made up of one or more processors configured to execute instructions associated with applications stored in memory 134."), the method comprising:
selecting a predicted text sample corresponding to an audio sample (Column 11, lines 6-18, "The process 200 may begin with a server 230 receiving 202 an utterance from a user 100 that includes a command and an entity. The utterance may be in the form of a set of audio signals. The server 230 may forward the received utterance to an automated speech recognizer that extracts 204 a portion of the utterance that is associated with the entity name. The extracted portion of the utterance corresponding to the entity name may then be associated with a timestamp, and stored in the memory associated with the server 230. The automated speech recognizer may generate 206 an initial transcription of the extracted portion of the audio signals."; Generating an initial transcription of an extracted portion of an audio signal reads on selecting a predicted text sample corresponding to an audio sample.);
receiving a correction text sample corresponding to the audio sample and based on the predicted text sample (Column 11, lines 43-46, "In some implementations, the server may obtain a correct transcription for the extracted portion of the audio signal at 208. The correct transcription may be based on, for example, feedback received from the user 100."; Obtaining a correct transcription for the extracted portion of the audio signal reads on receiving a correction text sample corresponding to the audio sample and based on the predicted text sample.);
updating an encoding of allowable pronunciations of the correction text sample based on the predicted text sample and the audio sample, the updated encoding of allowable pronunciations of the correction text sample including a pronunciation of the predicted text sample (Column 12, lines 8-22, "The server 230 may receive the correct transcription, and forward the correct transcription to the automated speech recognizer. The automated speech recognizer may obtain the extraction portion of the user's 100 audio signals that were previously stored based on timestamp. For instance, the automated speech recognizer may retrieve the extracted portion of the user's 100 audio signals that were associated with the most recent time stamp. The automated speech recognizer may then generate a phonetic pronunciation that corresponds to the extracted portion of the user's audio signals, as described above. Then, the automated speech recognizer may associate 210 the generated phonetic pronunciation with the received correct transcription. The generated phonetic pronunciation may correspond to the user's 100 unique pronunciation of an entity name."; Generating a phonetic pronunciation that corresponds to an extracted portion of a user's audio signals and associating the generated phonetic pronunciation with a received correct transcription reads on updating an encoding of allowable pronunciations of the correction text sample based on the predicted text sample and the audio sample, where the updated encoding of allowable pronunciations of the correction text sample including a pronunciation of the predicted text sample.);
and predicting a pronunciation of the correction text sample based on the updated encoding of allowable pronunciations of the correction text sample (Column 12, lines 23-35, "The automated speech recognizer may then update 212 an entry in the personalized pronunciation dictionary that includes an entity name that corresponds to the correct transcription based on the generated phonetic pronunciation. In some implementations, updating an entry in the personalized pronunciation dictionary may include replacing an initial pronunciation of an entity name with a user's unique pronunciation of the entity name by storing the generated phonetic pronunciation in the personalized pronunciation dictionary in place of the initial pronunciation of the entity name. This may include, for example, deleting the initial pronunciation of the entity name from the personalized pronunciation dictionary."; Updating an entry in a personalized pronunciation dictionary that includes an entity name that corresponds to a correct transcription based on a generated phonetic pronunciation reads on predicting a pronunciation of the correction text sample based on the updated encoding of allowable pronunciations of the correction text sample.).
Regarding claim 15 Bruguier discloses the non-transitory computer-readable storage medium as claimed in claim 14.
Bruguier further discloses:
wherein the method further includes receiving the audio sample from a device (Column 5, lines 21-24, "Once the microphone has been activated, the user 100 may vocalize an utterance 110 that may be detected by the microphone 125 associated with user's mobile device 120."; Column 5, line 65 - Column 6, line 3, "Server 130 may receive the audio signals 114 that correspond to the utterance 110, and forward the received audio signals 114 to the automated speech recognizer 140. The automated speech recognizer 140 may then extract the portion of the audio signals 114 that corresponds to the entity name 110b."; A user's mobile device reads on a device.).
Regarding claim 16, arguments analogous to claim 2 are applicable.
Regarding claim 17, arguments analogous to claim 3 are applicable.
Regarding claim 18, arguments analogous to claim 4 are applicable.
Regarding claim 20, arguments analogous to claim 6 are applicable.
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 5, 12 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Bruguier in view of Adams et al. (US Patent No. 10,339,920), hereinafter Adams.
Regarding claim 5, Bruguier discloses the method as claimed in claim 1, but does not specifically disclose: wherein the predicted pronunciation of the correction text sample is predicted by a grapheme to phoneme model.
Adams teaches:
wherein the predicted pronunciation of the correction text sample is predicted by a grapheme to phoneme model (Column 11, lines 29-39, "As noted, the lexicon also may include one or more expected pronunciations of each textual identifier, which allows the user to access associate content items through a speech command. For example, the user may attempt to play a song stored in the music catalog by saying the name of the artist, album or song title. The expected pronunciation may be determined based on a spelling of the word. The process of determining the expected pronunciation of the word based on the spelling is defined as grapheme to phoneme (G2P) conversion or pronunciation guessing (commonly referred to as pronguessing)."; Column 13, lines 10-14, "In some aspects of the disclosure, a conversion model, such as grapheme to phoneme (G2P) conversion or pronguessing model may be developed for each potential language of origin. The conversion model derives a pronunciation of a foreign text from a spelling of the foreign text."; Determining the expected pronunciation of a word using grapheme to phoneme conversion reads on the pronunciation of a text sample being predicted by a grapheme to phoneme model.).
Adams is considered to be analogous to the claimed invention because it is in the same field of automatic speech recognition. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Bruguier to incorporate the teachings of Adams to determining the expected pronunciation of a word using grapheme to phoneme conversion. Doing so would allow for determining an expected pronunciation of a textual identifier based on predicting a language of origin of the textual identifier (Adams; Column 2, lines 27-45).
Regarding claim 12, arguments analogous to claim 5 are applicable.
Regarding claim 19, arguments analogous to claim 5 are applicable.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Reinspach et al. (US Patent No. 11,823,659) teaches a method for collecting feedback to train models to better understand utterances and translate diverse user pronunciations into the intended words.
Hsu et al. (US Patent No. 10,885,918) teaches a method for generating customized text representations of audio commands.
Peng et al. (US Patent No. 9,741,339) teaches a method for determining pronunciations for particular terms.
Ge et al. (US Patent No. 9,489,943) teaches a method for learning alternate pronunciations for speech recognition.
Roth et al. (US Patent No. 8,577,681) teaches a method for generating an alternative pronunciation for a word or phrase given an initial pronunciation and a spoken example of the word or phrase.
Weisz et al. (US Patent Application Publication No. 2023/0186898) teaches a method for receiving audio data corresponding to a query spoken and processing the audio data to generate multiple candidate hypotheses each represented by a respective sequence of hypothesized terms.
Lawson et al. (US Patent Application Publication No. 2019/0035385) teaches a method for a visual display of a user interface for a voice-based virtual assistant system, where after displaying a transcription of user speech and performing requested actions, the system allows the user to provide an indication of satisfaction or dissatisfaction, and the user is presented an opportunity to correct the transcription text.
Reddy et al. ("Learning from Mistakes: Expanding Pronunciation Lexicons Using Word Recognition Errors") teaches a method for finding the pronunciation of an out-of-vocabulary word from a set of automatic speech recognition mistakes of one or more speech samples containing the word.
Badr et al. ("Learning New Word Pronunciations from Spoken Examples") teaches a method for using spoken examples of new words to improve the pronunciation generated by an initial letter-to-sound model.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to James Boggs whose telephone number is (571)272-2968. The examiner can normally be reached M-F 8:00 AM - 5:00 PM.
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 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.
/JAMES BOGGS/Examiner, Art Unit 2657
Prosecution Insights