Patents Examined by Yogeshkumar Patel
  • Patent number: 12784767
    Abstract: Systems and methods for identifying audio events in one or more audio streams include the use of a cascade audio spotting system (such as a cascade keyword spotting system (KWS)) to reduce power consumption while maintaining a desired performance. An example cascade audio spotting system may include a first module and a high-power subsystem. The first module is to receive an audio stream from one or more audio streams, process the audio stream to detect a first target sound activity in the audio stream, and provide a first signal in response to detecting the first target sound activity in the audio stream. The high-power subsystem is to (in response to the first signal being provided by the first module) receive the one or more audio streams and process the one or more audio streams to detect a second target sound activity in the one or more audio streams.
    Type: Grant
    Filed: June 20, 2024
    Date of Patent: November 3, 2026
    Assignee: Synaptics Incorporated
    Inventors: Saeed Mosayyebpour Kaskari, Hong Qiu, Atabak Pouya
  • Patent number: 12784739
    Abstract: A method for training an audio encoder includes receiving first training data comprising first audio data, performing a first training task on an audio encoder using the first training data, receiving second training data comprising first image data and second audio data, and performing a second training task on the audio encoder using the second training data. The method also includes receiving third training data comprising first text data and third audio data, performing a third training task on the audio encoder using the third training data, and performing at least one downstream task using the audio encoder.
    Type: Grant
    Filed: April 12, 2024
    Date of Patent: November 3, 2026
    Assignee: Robert Bosch GmbH
    Inventors: Ho-Hsiang Wu, Gyuhak Kim, Luca Bondi, Samarjit Das
  • Patent number: 12775896
    Abstract: A system and method for document summarization generates summarized articles and risk factor categorizations for display at a graphical user interface (GUI) dashboard. A transaction monitoring system includes an adverse media dashboard pipeline for processing risk factor alerts and generating document summarizations for display at a user device. Document summarization extracts several sentences from a source text and stacks the sentences to create a summary. The method creates a vector representation of each sentence using a machine learning word embedding model and generates a sentence similarity matrix by computing cosine similarity values. A sentence graph creation algorithm creates a graph corresponding to the sentence similarity matrix and calculates importance scores used in selecting sentences for the document summary.
    Type: Grant
    Filed: August 19, 2024
    Date of Patent: October 27, 2026
    Assignee: BANK OF MONTREAL
    Inventors: Drew R. Galow, Meera Das
  • Patent number: 12776324
    Abstract: An apparatus comprising means for: obtaining a bitstream comprising encoded spatial metadata and encoded transport audio signals; decoding transport audio signals from the bitstream encoded transport audio signals; decoding spatial metadata from the bitstream encoded spatial metadata; generating an encoding metric; and generating spatial audio signals from the transport audio signals based on the encoding metric and the spatial metadata.
    Type: Grant
    Filed: January 30, 2023
    Date of Patent: October 27, 2026
    Assignee: NOKIA TECHNOLOGIES OY
    Inventors: Mikko-Ville Laitinen, Tapani Pihlajakuja, Juha Tapio Vilkamo, Adriana Vasilache, Lasse Juhani Laaksonen
  • Patent number: 12771566
    Abstract: This application discloses a conference creation method, a conference control method, and an electronic device. In the method, in response to receiving an operation performed by a user in a first interface, a first electronic device enters a second interface. The second interface includes an input box for inputting information and a first control for creating a conference. The user inputs conference information in the input box of the second interface. A third interface is displayed in response to receiving an operation performed by the user on the first control in the second interface. The third interface includes an agenda arrangement list, the agenda arrangement list is generated based on time of the conference and a preset agenda template, and the agenda arrangement list of the conference includes at least one topic. The user may edit an agenda in the agenda arrangement list, for example, uploading a conference material.
    Type: Grant
    Filed: November 17, 2023
    Date of Patent: October 20, 2026
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Yiting Zhao, Ning Zhuang, Yuanyuan Xiao
  • Patent number: 12769789
    Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to improve media identification. An example apparatus includes a hash handler to generate a first set of reference matches by performing hash functions on a subset of media data associated with media to generate hashed media data based on a first bucket size, a candidate determiner to identify a second set of reference matches that include ones of the first set, the second set including ones having first quantities of hits that did not satisfy a threshold, determine second quantities of hits for ones of the second set by matching ones to the hash tables based on a second bucket size, and identify one or more candidate matches based on at least one of (1) ones of the first set or (2) ones of the second set, and a report generator to generate a report including a media identification.
    Type: Grant
    Filed: May 29, 2024
    Date of Patent: October 20, 2026
    Assignee: Gracenote, Inc.
    Inventors: Jeffrey Scott, Matthew James Wilkinson, Robert Coover, Shashank Merchant
  • Patent number: 12763088
    Abstract: A method for enhancing audio signals is provided. In some implementations, the method involves (a) obtaining a training set comprising a plurality of training samples, each training sample comprising a distorted audio signal and a clean audio signal. In some implementations, the method involves (b), for a training sample of the plurality of training samples: obtaining a frequency-domain representation of the distorted audio signal; providing the frequency-domain representation to a convolutional neural network (CNN) comprising a plurality of convolutional layers and to a recurrent element, wherein an output of the recurrent element is provided to a subset of the plurality of convolutional layers; generating a predicted enhancement mask, wherein the CNN generates the predicted enhancement mask; generating a predicted enhanced audio signal based on the predicted enhancement mask; and updating weights associated with the CNN and the recurrent element based on the predicted enhanced audio signal.
    Type: Grant
    Filed: July 12, 2022
    Date of Patent: October 13, 2026
    Assignee: Dolby Laboratories Licensing Corporation
    Inventors: Jia Dai, Kai Li, Xiaoyu Liu, Richard J. Cartwright
  • Patent number: 12763093
    Abstract: A distributed voice controlled system has a primary assistant and at least one secondary assistant. The primary assistant has a housing to hold one or more microphones, one or more speakers, and various computing components. The secondary assistant is similar in structure, but is void of speakers. The voice controlled assistants perform transactions and other functions primarily based on verbal interactions with a user. The assistants within the system are coordinated and synchronized to perform acoustic echo cancellation, selection of a best audio input from among the assistants, and distributed processing.
    Type: Grant
    Filed: August 7, 2024
    Date of Patent: October 13, 2026
    Assignee: Amazon Technologies, Inc.
    Inventors: Michael Alan Pogue, Kavitha Velusamy, Preethi Parasseri Narayanan, Tony David, Philip Ryan Hilmes
  • Patent number: 12743247
    Abstract: An acoustic device configured to mix a first music piece and a second music piece includes: a reservation unit configured to set a playback start point of the second music piece; and a display controller configured to display a first screen on a display device, where, on the first screen, a first image indicating a playback status of the second music piece and time information of the playback start point is moved based on a second image indicating a current playback point when a reservation set by the reservation unit is executed.
    Type: Grant
    Filed: November 22, 2021
    Date of Patent: September 22, 2026
    Assignee: AlphaTheta Corporation
    Inventors: Toshiki Nakai, Nao Takagi, Shintaro Kido
  • Patent number: 12741594
    Abstract: A vehicle body panel is provided defining an internal cavity that is acoustically sealed at least partially along a perimeter with an opening in the vehicle body panel for access to the internal cavity and sized to receive a speaker in the opening. A speaker assembly is provided with the speaker is installed in the opening. A speaker assembly is provided with a first vehicle body panel with an opening. A speaker is installed in the opening. A second vehicle body panel is attached to the first vehicle body panel and sealed along a connection with the first vehicle body panel to collectively provide an internal cavity accessible at the opening, to provide a resonation chamber for the speaker. A method is provided by sealing a plurality of vehicle body panels. A speaker is installed in an opening in the plurality of sealed vehicle body panels.
    Type: Grant
    Filed: February 29, 2024
    Date of Patent: September 22, 2026
    Assignee: Harman Becker Automotive Systems GmbH
    Inventor: Jian Wang
  • Patent number: 12737542
    Abstract: According to an embodiment, a computer-implemented method for obtaining at least one number based on a word buffer comprises: obtaining a word buffer; filling a number word buffer based on the word buffer by repeatedly obtaining a word from the word buffer, checking whether the word is a number word, and, in response to the word being a number word, adding the word to the number word buffer; in response to at least one preconfigured condition being met, converting the number word buffer into at least one number; and adding the at least one number to a result buffer.
    Type: Grant
    Filed: April 11, 2023
    Date of Patent: September 15, 2026
    Assignee: ELISA OYJ
    Inventors: Ville Ruutu, Jussi Ruutu
  • Patent number: 12737354
    Abstract: Various embodiments described herein provide for systems, methods, devices, instructions, and like for generating communication content using one or more large language models (LLMs). In particular, some embodiments provide a communication content generation system that generates content for a communication to a target organization using one or more LLMs and information regarding the target organization provided by an organization database, which can comprise curated organization-intelligence data.
    Type: Grant
    Filed: March 19, 2024
    Date of Patent: September 15, 2026
    Assignee: Snowflake Inc.
    Inventors: David Gojo, Orestis Kostakis
  • Patent number: 12739592
    Abstract: Disclosed are systems, methods, and other implementations, including a method for controlling a configurable audio processor, coupled via a plurality of transducers (such as the microphones 220A-C and/or the loudspeakers 224A-B of FIG. 2) to an acoustic environment, that includes determining a three-dimensional spatial variation in the acoustic environment of a processing characteristic of the audio processor based on configuration values for the audio processor, forming a three-dimensional image of the three-dimensional spatial variation of the processing characteristic, and providing the three-dimensional image for presentation to a user for controlling the configuration values.
    Type: Grant
    Filed: December 20, 2023
    Date of Patent: September 15, 2026
    Assignee: Cerence Operating Company
    Inventors: Gabriel Haas, Markus Funk, Simon Graf, Tobias Wolff
  • Patent number: 12726716
    Abstract: An image sensor device has a first number of first pixels disposed in a substrate and a second number of second pixels disposed in the substrate. The first number is substantially equal to the second number. A light-blocking structure disposed over the first pixels and the second pixels. The light-blocking structure defines a plurality of first openings and second openings through which light can pass. The first openings are disposed over the first pixels. The second openings are disposed over the second pixels. The second openings are smaller than the first openings. A microcontroller is configured to turn on different ones of the second pixels at different points in time.
    Type: Grant
    Filed: August 3, 2023
    Date of Patent: September 1, 2026
    Assignee: TAIWAN SEMICONDUCTOR MANUFACTURING CO., LTD.
    Inventors: Yun-Wei Cheng, Chun-Hao Chou, Kuo-Cheng Lee, Hsin-Chi Chen
  • Patent number: 12724977
    Abstract: A system and method of compressing cognitive data, such as command trajectories, operator interaction histories, and geometric structures, while preserving the spatial and semantic relationships required for reasoning and decision-making. The system allows trajectory calculations, geodesic measurements, and other cognitive operations to be performed directly on the compressed data without decompression. Compressed cognitive states are shared across multiple processing nodes using synchronization protocols that preserve the structure of the underlying manifold. Correlation networks are used to restore relationships that may be partially lost during compression. The system learns how to optimize compression strategies based on performance requirements and adapts over time. It also monitors the accuracy of cognitive operations and adjusts fidelity levels to maintain reliable output. This approach enables efficient, distributed cognitive computing where compressed data can still support advanced reasoning tasks.
    Type: Grant
    Filed: December 18, 2025
    Date of Patent: September 1, 2026
    Assignee: ATOM BEAM TECHNOLOGIES INC.
    Inventor: Brian Galvin
  • Patent number: 12706578
    Abstract: Example techniques involve controlling playback volumes. An example implementation includes displaying a group volume control of a synchrony group, the group volume control comprising a group volume indicator on a group volume slider and receiving, via the displayed group volume control, input data representing a selection of the group volume control. The implementation also includes displaying, concurrently with the group volume control, a first volume control comprising a first volume indicator on a first volume slider and a second volume control comprising a second volume indicator on a second volume slider. The implementation also includes receiving, via the displayed group volume control, input data representing an input to modify a first volume setting of the synchrony group to a second volume setting and transmitting instructions to cause the synchrony group to modify volume settings according to the second volume setting of the synchrony group.
    Type: Grant
    Filed: February 18, 2024
    Date of Patent: August 11, 2026
    Assignee: Sonos, Inc.
    Inventor: Eduardo Ahumada Apodaca
  • Patent number: 12701355
    Abstract: An apparatus for estimating sub-band-specific direction information for two or more sub-bands of a plurality of sub-bands according to an embodiment is provided. The apparatus has a feature extractor for obtaining a plurality of feature samples for a plurality of frequency bands of two or more audio signals. Moreover, the apparatus has a direction estimator being configured to receive the plurality of feature samples as input values and being configured to output a plurality of output samples wherein the output samples indicate, for each sub-band of the two or more sub-bands, the sub-band-specific direction information for said sub-band. Each of the plurality of sub-bands is equal to one of the plurality of frequency bands or has at least one frequency band or a portion of a frequency band of the plurality of frequency bands.
    Type: Grant
    Filed: March 11, 2024
    Date of Patent: August 4, 2026
    Assignee: FRAUNHOFER-GESELLSCHAFT ZUR FÖRDERUNG DER ANGEWANDTEN FORSCHUNG E.V.
    Inventors: Soumitro Chakrabarty, Shashi Kumar Kempapura Srinivasa, Fabian Küch, Christian Kroos, Oliver Thiergart
  • Patent number: 12701356
    Abstract: An electronic device is provided.
    Type: Grant
    Filed: April 5, 2024
    Date of Patent: August 4, 2026
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Juyeon Jin, Gupil Cheong, Sanghyeok Kim, Doosuk Kang
  • Patent number: 12694225
    Abstract: A system and method for implementing a Persistent Cognitive Machine (PCMs) that extends beyond the traditional prompt-response paradigm of artificial intelligence are disclosed. A PCM maintains persistent cognitive processes regardless of external interaction, stores and organizes thoughts in a thought cache, retrieves relevant thoughts based on current stimuli, generates new thoughts through reasoning processes, and curates stored thoughts during periods of reduced external interaction. The PCM includes language and reasoning model components, a thought cache, an executive component, and an embedding system. The PCM remains continuously active, remembers previous experiences, learns from these experiences, creates new thought experiences independently, and initiates interactions without waiting for external prompts. The PCM enters sleep-like states during which it curates its thought cache, generalizes experiences, and performs other memory management functions.
    Type: Grant
    Filed: January 13, 2026
    Date of Patent: July 28, 2026
    Assignee: AUTOBEAM TECHNOLOGIES INC.
    Inventor: Brian Galvin
  • Patent number: 12682910
    Abstract: Partially adaptive audio beamforming systems and methods are provided that enable improved acoustic echo cancellation of sound played on a loudspeaker that is in close proximity to a microphone array in an audio device. A stored beamformer parameter, such as an inverse covariance matrix, can be utilized by a frequency domain beamformer to generate a beamformed signal. The overall performance and resource usage by the audio device can be optimized.
    Type: Grant
    Filed: January 24, 2024
    Date of Patent: July 14, 2026
    Assignee: Shure Acquisition Holdings, Inc.
    Inventors: Israel Cohen, Baruch Berdugo