Patents Examined by Fariba Sirjani
  • Patent number: 10665243
    Abstract: A system for subvocalized speech recognition includes a plurality of sensors, a controller and a processor. The sensors are coupled to a near-eye display (NED) and configured to capture non-audible and subvocalized commands provided by a user wearing the NED. The controller interfaced with the plurality of sensors is configured to combine data acquired by each of the plurality of sensors. The processor coupled to the controller is configured to extract one or more features from the combined data, compare the one or more extracted features with a pre-determined set of commands, and determine a command of the user based on the comparison.
    Type: Grant
    Filed: October 23, 2017
    Date of Patent: May 26, 2020
    Assignee: Facebook Technologies, LLC
    Inventors: Eric Michael Whitmire, Laura Cristina Trutoiu
  • Patent number: 10665229
    Abstract: There is provided an information processing device that appropriately presents a topic in consideration of a behavior of a user presenting the topic. The information processing device includes: a topic generation unit configured to generate topics with a conversation partner on the basis of a comparison result between a certain behavior of a user and comparison information regarding the behavior; and a topic suggestion unit configured to decide a topic candidate to be suggested to the user from the generated topics.
    Type: Grant
    Filed: March 2, 2016
    Date of Patent: May 26, 2020
    Assignee: SONY CORPORATION
    Inventors: Takashi Ogata, Masanori Katsu
  • Patent number: 10657967
    Abstract: An apparatus and method for executing a voice command in an electronic device. In an exemplary embodiment, a voice signal is detected and speech thereof is recognized. When the recognized speech contains a wakeup command, a voice command mode is activated, and a signal containing at least a portion of the detected voice signal is transmitted to a server. The server generates a control signal or a result signal corresponding to the voice command, and transmits the same to the electronic device. The device receives and processes the control or result signal, and awakens. Thereby, voice commands are executed without the need for the user to physically touch the electronic device.
    Type: Grant
    Filed: October 2, 2018
    Date of Patent: May 19, 2020
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Subhojit Chakladar, Sang-Hoon Lee, Hee-Woon Kim
  • Patent number: 10657202
    Abstract: A method, computer program product, and computing system for receiving a presentation file including one or more audio portions and one or more textual portions. An audio transcript of the one or more audio portions of the presentation file may be generated. A textual transcript of the one or more textual portions of the presentation file may be generated. One or more rich portions of the presentation file may be determined based upon, at least in part, a comparison of the audio transcript and the textual transcript. At least the one or more rich portions of the presentation file may be presented.
    Type: Grant
    Filed: December 11, 2017
    Date of Patent: May 19, 2020
    Assignee: International Business Machines Corporation
    Inventors: Nan Chen, June-Ray Lin, Ju Ling Liu, Jin Zhang, Li Bo Zhang
  • Patent number: 10643624
    Abstract: An apparatus for reconstructing a frame including a speech signal as a reconstructed frame is provided, the apparatus including a determination unit and a frame reconstructor being configured to reconstruct the reconstructed frame, such that the reconstructed frame completely or partially includes the first reconstructed pitch cycle, such that the reconstructed frame completely or partially includes a second reconstructed pitch cycle, and such that the number of samples of the first reconstructed pitch cycle differs from a number of samples of the second reconstructed pitch cycle.
    Type: Grant
    Filed: June 14, 2018
    Date of Patent: May 5, 2020
    Assignee: Fraunhofer-Gesellschaft zur Föerderung der angewandten Forschung e.V.
    Inventors: Jérémie Lecomte, Michael Schnabel, Goran Markovic, Martin Dietz, Bernhard Neugebauer
  • Patent number: 10621975
    Abstract: Training a machine by a machine learning technique for recognizing speech utterance to determine language fluency level of a user. Native speaker recorded data and language specific dictionary of heteronyms may be retrieved. The native speaker recorded data may be parsed and the heteronyms from the native speaker recorded data may be isolated. Linguistic features from the native speaker recorded data including at least linguistic features associated with the heteronyms may be extracted, and a language dependent machine learning model is generated based on the linguistic features.
    Type: Grant
    Filed: November 20, 2017
    Date of Patent: April 14, 2020
    Assignee: International Business Machines Corporation
    Inventors: David Millen, Livy Maria Real Coelho
  • Patent number: 10614172
    Abstract: An apparatus configured to provide translated content to a receiver includes a storage configured to store address book information including identification information identifying a user of the receiver; a user inputter configured to receive input including the identification information and content to be transmitted to the receiver; a controller configured to determine a language corresponding to the user of the receiver identified by the receiver identification information based on the address book information and the identification information; and a communicator configured to transmit a request to translate the content into the determined language.
    Type: Grant
    Filed: May 3, 2018
    Date of Patent: April 7, 2020
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Hyun-jae Shin, Hak-jung Kim
  • Patent number: 10599771
    Abstract: Negation scope analysis for negation detection is provided. In various embodiments, a phrase is read from a report collection. The phrase is searched for at least one of a predetermined set of negation keywords. A dependency parse tree is generated of the phrase. The dependency parse tree is traversed starting with the at least one of the predetermined set of negation keywords. Based on the traversal, a plurality of words of the phrase are determined that are spanned by the at least one of the predetermined set of negation keywords.
    Type: Grant
    Filed: April 10, 2017
    Date of Patent: March 24, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventor: Yufan Guo
  • Patent number: 10599769
    Abstract: A method performed by a device may include identifying a plurality of samples of textual content; performing tokenization of the plurality of samples to generate a respective plurality of tokenized samples; performing embedding of the plurality of tokenized samples to generate a sample matrix; determining groupings of attributes of the sample matrix using a convolutional neural network; determining context relationships between the groupings of attributes using a bidirectional long short term memory (LSTM) technique; selecting predicted labels for the plurality of samples using a model, wherein the model selects, for a particular sample of the plurality of samples, a predicted label of the predicted labels from a plurality of labels based on respective scores of the particular sample with regard to the plurality of labels and based on a nonparametric paired comparison of the respective scores; and providing information identifying the predicted labels.
    Type: Grant
    Filed: June 26, 2018
    Date of Patent: March 24, 2020
    Assignee: Capital One Services, LLC
    Inventors: Jon Austin Osbourne, Aaron Raymer, Megan Yetman, Venkat Yashwanth Gunapati
  • Patent number: 10580435
    Abstract: Monitoring and analysis of a user's speech to detect symptoms of a mental health disorder by continuously monitoring a user's speech in real-time to generate audio data based, transcribing the audio data to text and analyzing the text of the audio data to determine a sentiment of the audio data is disclosed. A trained machine learning model may be applied to correlate the text and the determined sentiment to clinical information associated with symptoms of a mental health disorder to determine whether the symptoms are a symptom event. The initial determination may be transmitted to a second device to determine (and/or verify) whether or not the symptom event was falsely recognized. The trained machine learning model may be updated based on a response from the second device.
    Type: Grant
    Filed: November 27, 2017
    Date of Patent: March 3, 2020
    Assignee: International Business Machines Corporation
    Inventors: Maryam Ashoori, Benjamin D. Briggs, Lawrence A. Clevenger, Leigh Anne H. Clevenger
  • Patent number: 10573314
    Abstract: Systems and methods are disclosed. A digitized human vocal expression of a user and digital images are received over a network from a remote device. The digitized human vocal expression is processed to determine characteristics of the human vocal expression, including: pitch, volume, rapidity, a magnitude spectrum identify, and/or pauses in speech. Digital images are received and processed to detect characteristics of the user face, including detecting if one or more of the following is present: a sagging lip, a crooked smile, uneven eyebrows, and/or facial droop. Based at least on part on the human vocal expression characteristics and face characteristics, a determination is made as to what action is to be taken. A cepstrum pitch may be determined using an inverse Fourier transform of a logarithm of a spectrum of a human vocal expression signal. The volume may be determined using peak heights in a power spectrum of the human vocal expression.
    Type: Grant
    Filed: February 27, 2019
    Date of Patent: February 25, 2020
    Inventor: Karen Elaine Khaleghi
  • Patent number: 10510351
    Abstract: A method of encoding samples in a digital signal is provided that includes receiving a frame of N samples of the digital signal, determining L possible distinct data values in the N samples, determining a reference data value in the L possible distinct data values and a coding order of L?1 remaining possible distinct data values, wherein each of the L?1 remaining possible distinct data values is mapped to a position in the coding order, decomposing the N samples into L?1 coding vectors based on the coding order, wherein each coding vector identifies the locations of one of the L?1 remaining possible distinct data values in the N samples, and encoding the L?1 coding vectors.
    Type: Grant
    Filed: February 8, 2016
    Date of Patent: December 17, 2019
    Assignee: TEXAS INSTRUMENTS INCORPORATED
    Inventors: Lorin Paul Netsch, Jacek Piotr Stachurski
  • Patent number: 10475455
    Abstract: An approach is described that obtains spectrum coefficients for a replacement frame of an audio signal. A tonal component of a spectrum of an audio signal is detected based on a peak that exists in the spectra of frames preceding a replacement frame. For the tonal component of the spectrum a spectrum coefficients for the peak and its surrounding in the spectrum of the replacement frame is predicted, and for the non-tonal component of the spectrum a non-predicted spectrum coefficient for the replacement frame or a corresponding spectrum coefficient of a frame preceding the replacement frame is used.
    Type: Grant
    Filed: December 15, 2017
    Date of Patent: November 12, 2019
    Assignee: Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.
    Inventors: Janine Sukowski, Ralph Sperschneider, Goran Markovic, Wolfgang Jaegers, Christian Helmrich, Bernd Edler, Ralf Geiger
  • Patent number: 10467616
    Abstract: There is provided systems and method for a voice data processor for distinguishing multiple voice inputs. One or more merchant devices may include or be linked to a voice input and output component, where the component may be used to receive voice input and distinguish between multiple voice inputs. The component may activate in a first direction associated with the merchant to detect merchant voice input that establishes a transaction with a user at the merchant's location. The component may activate a merchant device to establish the transaction based on detecting the merchant voice input and/or through voice recognition of the merchant. Once the transaction is established, the component may then activate in a direction of the user, and may request that the user provide voice input to confirm the transaction and engage in transaction processing. The voice input may also confirm and complete a payment to the merchant.
    Type: Grant
    Filed: April 3, 2018
    Date of Patent: November 5, 2019
    Assignee: PAYPAL, INC.
    Inventors: Ryan Christopher May, Josh Beyers, Vidit Maniyar
  • Patent number: 10460728
    Abstract: Methods, systems, and computer-readable media for exporting dialog-driven applications to digital communication platforms are disclosed. A launch condition is received from a user. The launch condition is caused to be registered with one or more digital communication platforms. Detection of the launch condition is to cause a natural language input to be routed from at least one of the digital communication platforms to an application management service.
    Type: Grant
    Filed: June 16, 2017
    Date of Patent: October 29, 2019
    Assignee: Amazon Technologies, Inc.
    Inventors: Vikram Sathyanarayana Anbazhagan, Swaminathan Sivasubramanian, Stefano Stefani, Vladimir Zhukov
  • Patent number: 10431203
    Abstract: Training a machine by a machine learning technique for recognizing speech utterance to determine language fluency level of a user. Native speaker recorded data and language specific dictionary of heteronyms may be retrieved. The native speaker recorded data may be parsed and the heteronyms from the native speaker recorded data may be isolated. Linguistic features from the native speaker recorded data including at least linguistic features associated with the heteronyms may be extracted, and a language dependent machine learning model is generated based on the linguistic features.
    Type: Grant
    Filed: September 5, 2017
    Date of Patent: October 1, 2019
    Assignee: International Business Machines Corporation
    Inventors: David Millen, Livy Maria Real Coelho
  • Patent number: 10394961
    Abstract: According to one embodiment, an input unit accepts input of an input sentence that is a second sentence of the native language corresponding to a first sentence. A language analysis execution unit executes language analysis for the input sentence. A grammatical feature extraction unit extracts a grammatical feature of the input sentence based on a result of the executed language analysis. A search query generation unit generates a search query based on the extracted grammatical feature. An output unit searches for an index based on the generated search query and outputs an exemplary sentence set including an exemplary sentence of the native language corresponding to an index that matches the search query and an exemplary sentence of the foreign language corresponding to the exemplary sentence of the native language.
    Type: Grant
    Filed: October 30, 2015
    Date of Patent: August 27, 2019
    Assignees: KABUSHIKI KAISHA TOSHIBA, TOSHIBA SOLUTIONS CORPORATION
    Inventors: Guowei Zu, Toshiyuki Kano
  • Patent number: 10387564
    Abstract: Methods and arrangements for document quality assessment. Documents are accepted and a quality specification containing predetermined quality criteria is assimilated. Each document is assessed based on the predetermined quality criteria, and a quality score is assigned to each document, the quality score being a function of positive and negative attributes assessed for each document.
    Type: Grant
    Filed: November 12, 2010
    Date of Patent: August 20, 2019
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Rema Ananthanarayanan, Biplav Srivastava
  • Patent number: 10381011
    Abstract: An apparatus for determining an estimated pitch lag is provided. The apparatus includes an input interface for receiving a plurality of original pitch lag values, and a pitch lag estimator for estimating the estimated pitch lag. The pitch lag estimator is configured to estimate the estimated pitch lag depending on a plurality of original pitch lag values and depending on a plurality of information values, wherein for each original pitch lag value of the plurality of original pitch lag values, an information value of the plurality of information values is assigned to the original pitch lag value.
    Type: Grant
    Filed: December 21, 2015
    Date of Patent: August 13, 2019
    Assignee: Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.
    Inventors: Jeremie Lecomte, Michael Schnabel, Goran Markovic, Martin Dietz, Bernhard Neugebauer
  • Patent number: 10381020
    Abstract: Several embodiments of a digital speech signal enhancer are described that use an artificial neural network that produces clean speech coding parameters based on noisy speech coding parameters as its input features. A vocoder parameter generator produces the noisy speech coding parameters from a noisy speech signal. A vocoder model generator processes the clean speech coding parameters into estimated clean speech spectral magnitudes. In one embodiment, a magnitude modifier modifies an original frequency spectrum of the noisy speech signal using the estimated clean speech spectral magnitudes, to produce an enhanced frequency spectrum, and a synthesis block converts the enhanced frequency spectrum into time domain, as an output speech sequence. Other embodiments are also described.
    Type: Grant
    Filed: June 16, 2017
    Date of Patent: August 13, 2019
    Assignee: Apple Inc.
    Inventor: Sean A. Ramprashad