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 .
Claims 1-21 are pending.
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.
Claim(s) 1-21 is/are rejected under 35 U.S.C. 102 (a) (1) as being anticipated by Lee et al. (hereinafter Lee) (US 20200118544 A1).
As to claim 1, Lee teaches an integrated circuit for generating wake signals, comprising:
a host processor configured to receive a signal stream [0034: “the processor may :transmit the voice data…” i.e., a sequential start language uttered sequentially with a utterance language from the voice.] [FIG. 16];
a co-processor [AI processor] including an artificial neural network [FIG. 5] [0148: “The AI processor 21 may learn a neural network using a program stored in the memory 25] [0149] that is configured to:
identify one or more target signals among one or more signals received from the host processor [0034: “the AI processed information may be information that has determined whether the sequential start language recognized from the voice data is recognized as start language of the voice recognizing apparatus.”]; and
verify the source of the identified target signal [abstract: “…thereby being able to authenticate a user and recognize a voice even through a seamless scheme voice that is uttered in an actual situation.”] [0255 The speaker identification may mean specifying a person who utters in a dialogue group enrolled by voices. The speaker identification may include a process of identifying a pre-enrolled speaker …”];
a communications interface between the host processor and the co-processor configured to transmit information therebetween [0034: “The processor may: transmit the voice data to an AI processor included in the network through the communication unit; and receive AI-processed information from the AI processor,”].
As to claim 2, Lee teaches wherein the target signal includes at least one wake keyword [FIG. 16: Hi LG].
As to claim 3, Lee teaches wherein verification of the source includes identifying the speaker of the at least one wake keyword [0255: “The speaker identification may mean specifying a person who utters in a dialogue group enrolled by voices. The speaker identification may include a process of identifying a pre-enrolled speaker …”].
As to claim 4, Lee teaches wherein verification further includes determining if the identified speaker is on a list of pre-authorized users [0255: “The speaker identification may mean specifying a person who utters in a dialogue group enrolled by voices. The speaker identification may include a process of identifying a pre-enrolled speaker …”].
As to claim 5, Lee teaches wherein verification further includes generating verification data in response to verification of the identified speaker on the list of pre-authorized users [0255: “The speaker identification may mean specifying a person who utters in a dialogue group enrolled by voices. The speaker identification may include a process of identifying a pre-enrolled speaker …”].
As to claim 6, Lee teaches wherein the co-processor is further configured to transmit verification data to the host processor via the communications interface [0034: “The processor may: transmit the voice data to an AI processor included in the network through the communication unit; and receive AI-processed information from the AI processor,”].
As to claim 7, Lee teaches wherein the host processor, in response to receiving verification data, generates a wake signal [0023: “a processor that starts the voice recognizing apparatus when a basic start language pre-set as a start language of the voice recognizing apparatus is recognized from the voice…”].
As to claim 8, Lee teaches wherein the wake signal is configured to change a computing device from a first power consumption mode into a second, higher power consumption mode [0023: “a processor that starts the voice recognizing apparatus when a basic start language pre-set as a start language of the voice recognizing apparatus is recognized from the voice…”] [Apparently, power consumption is higher after it is started.”].
As to claim 9, Lee teaches wherein the wake signal is configured to establish a connection between a communication agent and a computing device [0020-0021].
As to claim 10, Lee teaches wherein the signal stream is comprised of signals received via at least one microphone [0180: “the input unit 120 may include a microphone”].
As to claim 11, Lee teaches a method for generating a weight file that causes an integrated circuit to generate wake signals by detecting desired user-specified signals and speakers, comprising:
listing desired target signals and known users that may be detected by a signal detector [0255: “The speaker identification may mean specifying a person who utters in a dialogue group enrolled by voices. The speaker identification may include a process of identifying a pre-enrolled speaker …”] [user and corresponding user’s voice are enrolled];
retrieving one or more signal databases that are comprised of standard target signals that may be detected by the signal detector [0156: “ The learning data acquisition unit 23 can acquire learning data required for a neural network model for classifying and recognizing data. For example, the learning data acquisition unit 23 can acquire, as learning data, voice data and/or basic start language data to be input to a neural network model.”];
combining the desired target signals and the one or more signal databases to build a modified database [0157: “The learning data acquisition unit 23 may obtain training data for a neural network model for classifying and recognizing data. For example, the learning data acquisition unit 23 may obtain microphone detection signal to be input to the neural network model and/or a feature value, extracted from the message, as the training data.”] [0011: “A method in which a voice recognizing apparatus according to an embodiment of the present disclosure intelligently recognizes a voice, includes: receiving a voice; and starting the voice recognizing apparatus when a basic start language pre-set as a start language of the voice recognizing apparatus is recognized from the voice, in which the starting includes: acquiring a sequential start language sequentially uttered with an utterance language from the voice; and setting the sequential start language as an additional start language that can start the voice recognizing apparatus other than the basic start language when the sequential start language is recognized as a start language of the voice recognizing apparatus.”];
using the modified database to train a neural network implementation to recognize the target signals and the standard signals [0158-0159] ;
producing a set of weights by way of training the neural network implementation [0198: “The acoustic model may include rules that can be used by a parameter synthesis engine to assign specific audio waveform parameters to input phonetic units and/or prosodic annotations. The rules can be used to calculate a score that shows possibility that specific audio output parameters (a frequency, a volume, etc.) correspond to the part of input symbolic linguistic representation from the front-end.”]; and
translating the set of weights into the weight file suitable for being stored in a memory storage that is accessible to the integrated circuit [0293: “ the voice recognizing apparatus 10 can acquire a recognition score of a sequential start language by inputting the sequential start language into a voice recognition model (S1200). “].
As to claim 12, Lee teaches wherein the target signal includes at least one wake keyword [FIG. 16: Hi LG].
As to claim 13, Lee teaches wherein listing comprises entering the target signals into a computing device that is configured to generate the weight file [0149: “In particular, the AI processor can learn a neural network for recognizing a recognition score for a sequential start language in a voice by analyzing voice data. Further, the AI processor 21 can learn a neural network for recognizing a basic start language set in advance in a voice by analyzing voice data. Here, the neural network for recognizing a basic start language set in advance may be designed to simulate the brain structure of human on a computer and may include a plurality of network nodes having weights and simulating the neurons of human neural network.”].
As to claim 14, Lee teaches wherein listing comprises entering the target signals into a cloud-based application that is configured to generate the weight file [0213: “a voice process that is performed in a device environment and/or a cloud environment…”].
As to claim 15, Lee teaches wherein listing comprises entering the target signals into a stand-alone software that is configured to generate the weight file [0148-0149: “[0148] The AI processor 21 may learn a neural network using a program stored in the memory 25. In particular, the AI processor can learn a neural network for recognizing a recognition score for a sequential start language in a voice by analyzing voice data.”]
As to claim 16, Lee teaches wherein the target signals are comprised of signal patterns within input signals received via at least one microphone [0180: “the input unit 120 may include a microphone”].
As to claim 17, Lee teaches wherein the target signals may be spoken keywords, or non-verbal acoustic signals such as specific sounds [0222].
As to claim 18, Lee teaches wherein the neural network implementation is a software model of a neural network that is implemented in the integrated circuit comprising the signal detector [0148-150] [0180: “the input unit 120 may include a microphone”].
As to claim 19, Lee teaches wherein the weight file may be provided to an end-user upon purchasing a mobile device [0273: “In this case, the start language recognition model may be learned in advance using a pre-set basic start language before the voice is received in step S1010. In detail, the start language recognition model may be learned in advance to be able to output a recognition score showing the degree of similarity of the received voice and the basic start language in a probability value type. That is, the start language recognition model can have the received voices as an input value and can output the degree of similarity of the received voice and the basic start language in a probability value type. “].
As to claim 20, Lee teaches wherein upon an end-user installing the weight file the mobile device, the signal detector may detect the target signals by way of the set of weights [0147] [0159] [0170].
As to claim 21, Lee teaches wherein the signal detector continues detecting the target signals in an offline state comprised of an absence of connectivity between the signal detector and an external communications network, such as the Internet, the cloud, and the like [0214: “On the contrary, FIG. 8 shows an example of on-device processing in which the entire operation of voice processing that processes input voice and synthesizes voices, as described above, is performed in a device 70.”].
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to XUXING CHEN whose telephone number is (571)270-3486. The examiner can normally be reached M-F 9-5:30PM.
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, Jaweed Abbaszadeh can be reached at 571-270-1640. 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.
/XUXING CHEN/Primary Examiner, Art Unit 2176
Prosecution Insights