Google LLC patent applications on August 29th, 2024
Patent Applications by Google LLC on August 29th, 2024
Google LLC: 42 patent applications
Google LLC has applied for patents in the areas of G10L15/06 (9), G10L15/26 (4), G10L15/22 (4), G06F40/40 (3), G10L15/18 (2) G10L15/063 (4), G06N10/00 (2), A61B5/02416 (1), H01L25/162 (1), G09G3/3258 (1)
With keywords such as: data, device, based, user, network, training, application, input, determining, and video in patent application abstracts.
Patent Applications by Google LLC
20240285183. Cardiovascular Monitoring Using Multiple Sensors_simplified_abstract_(google llc)
Inventor(s): Yojan Patel of London (GB) for google llc, SeongHwan Cho of Mountain View CA (US) for google llc, Justin Phillips of London (GB) for google llc
IPC Code(s): A61B5/024, A61B5/00, A61B5/021, A61B5/0295
CPC Code(s): A61B5/02416
Abstract: a cardiovascular monitoring system includes a first monitoring device configured to couple to a first body part of a subject and a second monitoring device configured to couple to a second body part of the subject. the first monitoring device is configured to measure a first cardiovascular signal and a first motion signal at the first body part, and the second monitoring device is configured to measure a second cardiovascular signal and a second motion signal at the second body part. a controller of the system receives the first and second cardiovascular signals and the first and second motion signals and filters the first and second cardiovascular signals by removing spectral components that correspond to spectral components of the first and second motion signals. based on a correlated spectral component that is present in both the filtered first and second cardiovascular signals, the system determines cardiovascular information of the subject.
20240288122. Hydrogen Fueling and Storage Optimization Model_simplified_abstract_(google llc)
Inventor(s): Dhruv Gupta of San Jose CA (US) for google llc, Hariharan Subramanian of Everett WA (US) for google llc, Priya Chhiba of Atlanta GA (US) for google llc, Varun Sakalkar of Redwood City CA (US) for google llc
IPC Code(s): F17C5/00, F17C13/02, G05B19/4155
CPC Code(s): F17C5/007
Abstract: aspects of the disclosure are directed to an optimization model for storing liquid hydrogen to power fuel cells in data centers. the optimization model can be based on hydrogen fuel consumption rates in the data center, refueling rates from vendors, refueling response time, storage tank area constraints in the data center, and/or logistical refueling constraints. the optimization model can allow for providing sufficient fuel within a constrained space for backup power in the data center, such as when an emergency arises.
20240289027. Automated SSD Recovery_simplified_abstract_(google llc)
Inventor(s): Diwakar Gupta of Seattle WA (US) for google llc, Connor Owen McCoy of Seattle WA (US) for google llc
IPC Code(s): G06F3/06
CPC Code(s): G06F3/0619
Abstract: aspects of the disclosure are directed to providing users more control over ssd storage recovery, such as providing capabilities and configuration options for a cloud platform to manage the ssd recovery. aspects of the disclosure can include providing a restart-in-place maintenance mode, a configurable time-out option for ssd recovery, automatic snapshot triggering, automatic archiving, and/or extending stop/start virtual machine functionality to work with local ssd storage.
Inventor(s): Tomer Amarilio of Palo Alto CA (US) for google llc, Yuzhao Ni of Sunnyvale CA (US) for google llc, Bryan Allen of Emeryville CA (US) for google llc, Norbert Tydingco of Sunnyvale CA (US) for google llc, Will Donnelly of Sunnyvale CA (US) for google llc, Feng Yuan of Mountain View CA (US) for google llc, Nathaniel Nesiba of Palo Alto CA (US) for google llc, Anurag Jain of Palo Alto CA (US) for google llc, Jacky Cheung of San Jose CA (US) for google llc, Ronghui Zhu of San Jose CA (US) for google llc, Chunya Hua of South San Francisco CA (US) for google llc, Gregory Kielian of South San Francisco CA (US) for google llc
IPC Code(s): G06F3/16, G10L15/08, G10L15/22
CPC Code(s): G06F3/167
Abstract: in response to a user interacting with a tangible peripheral assistant control device (e.g., depressing a button of the device), causing an automated assistant to perform one or more actions. the action(s) performed can be based on input previously provided by the user in configuring the peripheral assistant control device. the action(s) performed in response to interaction with the peripheral assistant control device can vary based on one or more conditions, such as which user is currently active, where the peripheral assistant control device is currently located (which can optionally be inferred based on which of multiple assistant computing devices the button is paired with), and/or the current state of one or more smart devices and/or other devices (e.g., as determined based on a device topology). a utility of the peripheral assistant control device can be automatically extended beyond what was specifically requested by a user during configuration.
Inventor(s): Fabrice Aidan of Ramat HaSharon (IL) for google llc, Evgeni Krimer of Haifa (IL) for google llc
IPC Code(s): G06F11/10, H03M13/00, H03M13/15
CPC Code(s): G06F11/1044
Abstract: aspects of the disclosed technology include techniques and mechanisms for an efficient error correction coding scheme that can detect and correct data errors that may occur in a memory. in general, the scheme comprises segmenting the data that would be transferred as part of a data request into different parts and applying error correction codes to the separate parts.
Inventor(s): Dong Hyuk Woo of San Jose CA (US) for google llc, Ravi Narayanaswami of San Jose CA (US) for google llc
IPC Code(s): G06F13/16, G06F9/38, G06F15/76, G06F17/16, G06N3/045, G06N3/063, G06N3/08, G06N3/10, G06N5/04, G06N20/00, G06N20/10
CPC Code(s): G06F13/1668
Abstract: a computer-implemented method includes receiving, by a computing device, input activations and determining, by a controller of the computing device, whether each of the input activations has either a zero value or a non-zero value. the method further includes storing, in a memory bank of the computing device, at least one of the input activations. storing the at least one input activation includes generating an index comprising one or more memory address locations that have input activation values that are non-zero values. the method still further includes providing, by the controller and from the memory bank, at least one input activation onto a data bus that is accessible by one or more units of a computational array. the activations are provided, at least in part, from a memory address location associated with the index.
20240289329. Technique for Parallel Recovery on Read Replica_simplified_abstract_(google llc)
Inventor(s): Anjan Kumar Amirishetty of Fremont CA (US) for google llc, Simhachala Sasikanth Gottapu of Dublin CA (US) for google llc, Niranjan Nilakantan of Cupertino CA (US) for google llc, Anthony Hsu of Sunnyvale CA (US) for google llc, Junjie Liang of San Francsico CA (US) for google llc
IPC Code(s): G06F16/2453, G06F16/23, G06F16/27
CPC Code(s): G06F16/24532
Abstract: aspects of the disclosure are directed to a parallel recovery mode that applies log records while allowing read queries on read-replica databases. the parallel recovery mode can include applying log records in log sequence number (lsn) order for a block or for multiple blocks, and managing log records affecting multiple blocks. the parallel recovery mode can further manage dependency between different log records and maintain transactional consistency on read queries.
20240289384. Local Node Embeddings for Heterogeneous Graphs_simplified_abstract_(google llc)
Inventor(s): Kimon Fountoulakis of Kitchener (CA) for google llc, Dake He of Toronto (CA) for google llc
IPC Code(s): G06F16/901
CPC Code(s): G06F16/9024
Abstract: provided are computing systems, methods, and platforms that obtain local node embeddings for heterogeneous graphs. a heterogeneous graph comprising a plurality of nodes can be obtained. weight values respectively associated with subgraphs of the heterogeneous graph can be determined. at least one node from among the plurality of nodes can be selected. an embedding for the at least one selected node can be learned using an embedding objective computed based on the weight values. the heterogeneous graph can be processed based on the embedding. submodular hypergraphs can be used to represent heterogeneous graphs and their cuts. the -regularized personalized pagerank can be applied to hypergraphs, where the optimal solution gives the node embedding for the given seed nodes. the resulting -regularized personalized pagerank can be solved in running time without depending on the size of the whole graph.
20240289395. FACTUALITY OF GENERATED RESPONSES_simplified_abstract_(google llc)
Inventor(s): Hao Zhou of Redwood City CA (US) for google llc, Shrestha Basu Mallick of San Francisco CA (US) for google llc, Trevor Strohman of Menlo Park CA (US) for google llc, Patricia Luisa Romero Domingo of Jackson Heights NY (US) for google llc, Amirhossein Kiani of San Francisco CA (US) for google llc, Yu Du of Sunnyvale CA (US) for google llc, Xinying Song of Kirkland WA (US) for google llc, Heng-Tze Cheng of Mountain View CA (US) for google llc, Quoc V. Le of Palo Alto CA (US) for google llc, Ed Huai-Hsin Chi of Palo Alto CA (US) for google llc, Christopher Jamie Maclean Hall of Tempe (AU) for google llc
IPC Code(s): G06F16/9532, G06F16/955, G06F40/40
CPC Code(s): G06F16/9532
Abstract: implementations relate to helping a large language model generate factual responses to prompts that request factual content is disclosed. the large language model may receive a prompt context, a plurality of encoded context passages as input. the large language model is trained to determine whether or not to utilize the encoded context passages in generating the response. implementations also relate to different methods of fine-tuning the responses generated by the large language model through query refinements, response re-writes, and evaluation of factual accuracy.
20240289407. SEARCH WITH STATEFUL CHAT_simplified_abstract_(google llc)
Inventor(s): Mahsan Rofouei of Menlo Park CA (US) for google llc, Anand Shukla of Palo Alto CA (US) for google llc, Qing Wei of Mountain View CA (US) for google llc, Chi Tang of Mountain View CA (US) for google llc, Ryan Brown of San Diego CA (US) for google llc, Enrique Piqueras of San Jose CA (US) for google llc
IPC Code(s): G06F16/957, G06F16/9532, G06F16/9535, G06F40/40
CPC Code(s): G06F16/9577
Abstract: implementations are described herein for augmenting a traditional search session with stateful chat—via what will be referred to as a “generative companion”—to facilitate more interactive searching. in various implementations, a query may be received, e.g., from a client device operated by a user. contextual information associated with the user or the client device may be retrieved. generative model (gm) output may be generated based on processing, using a generative model, data indicative of the query and the contextual information. synthetic queries may be generated using the gm output, and search result documents (srds) may be selected. state data indicative of: the query, contextual information, one or more of the synthetic queries, and the set of search result documents, may be processed to identify a classification of the query. based on the classification downstream gm(s) may be selected and used to generate one or more additional gm outputs.
Inventor(s): Behnoosh Hariri of New York NY (US) for google llc, Konstantin Yakovlev of Zurich (CH) for google llc
IPC Code(s): G06F21/62, G06F8/65
CPC Code(s): G06F21/6209
Abstract: a method is disclosed that includes receiving user input indicating a command to embed a source application data object created in a source application into a host application, in response to the user input, causing the source application data object created in the source application to be embedded in a host application file of the host application, identifying a modification made to the embedded source application data object via a host application user interface of the host application, sending a notification to the source application to update a corresponding source copy of the source application data object in a source application data store based on the modification made to the embedded source application data object, identifying a change made by a user to the source copy of the source application data object via a source application user interface of the source application, determining, based on access permissions associated with the host application file, whether the user is allowed to make changes to the host application file, and if so, causing the host application to update the embedded source application data object in a host application data store based on the change made by the user to the source copy of the source application data object.
20240289552. CHARACTER-LEVEL ATTENTION NEURAL NETWORKS_simplified_abstract_(google llc)
Inventor(s): Yi Tay of Singapore (SG) for google llc, Dara Bahri of Lafayette CA (US) for google llc, Donald Arthur Metzler, Jr. of Marina del Rey CA (US) for google llc, Hyung Won Chung of New York NY (US) for google llc, Jai Prakash Gupta of Fremont CA (US) for google llc, Sebastian Nikolas Ruder of London (GB) for google llc, Simon Baumgartner of Brooklyn NY (US) for google llc, Vinh Quoc Tran of New York NY (US) for google llc, Zhen Qin of Mountain View CA (US) for google llc
IPC Code(s): G06F40/284
CPC Code(s): G06F40/284
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing a machine learning task on an input sequence of characters that has a respective character at each of a plurality of character positions to generate a network output. one of the systems includes a neural network configured to perform the machine learning task, the neural network comprising a gradient-based sub-word tokenizer and an output neural network. the gradient-based sub-word tokenizer is configured to apply a learned, i.e., flexible, sub-word tokenization strategy to the input sequence of characters to generate a sequence of latent sub-word representations. the output neural network is configured to process the latent sub-word representation to generate the network output for the task.
20240289563. SPEECH-TO-SPEECH TRANSLATION WITH MONOLINGUAL DATA_simplified_abstract_(google llc)
Inventor(s): Michelle Tadmor Ramanovich of Tel-Aviv (IL) for google llc, Eliya Nachmani of Tel-Aviv (IL) for google llc, Alon Levkovitch of Tel-Aviv (IL) for google llc, Byungha Chun of Tokyo (JP) for google llc, Yifan Ding of Tokyo (JP) for google llc, Nadav Bar of Raanana (IL) for google llc, Chulayuth Asawaroengchai of Zurich (CH) for google llc
IPC Code(s): G06F40/58, G10L15/00, G10L15/06, G10L25/18
CPC Code(s): G06F40/58
Abstract: training and/or utilizing a speech-to-speech translation (s2st) system that can be used to generate, based on processing source audio data that captures a spoken utterance in a source language, target audio data that includes a synthetic spoken utterance that is spoken in a target language and that corresponds, both linguistically and para-linguistically, to the spoken utterance in the source language. implementations that are directed to training the s2st system utilize an unsupervised approach, with monolingual speech data, in training the s2st system.
20240289605. Proxy Task Design Tools for Neural Architecture Search_simplified_abstract_(google llc)
Inventor(s): Lav Rai of Sammamish WA (US) for google llc, Xiang Xu of Mountain View CA (US) for google llc, Yen-Min Hsu of Mountain View CA (US) for google llc, Bo Wu of Mountain View CA (US) for google llc, Daiyi Peng of Mountain View CA (US) for google llc
IPC Code(s): G06N3/08
CPC Code(s): G06N3/08
Abstract: aspects of the disclosure are directed to proxy task design tools that automatically find proxy tasks, such as optimal proxy tasks, for neural architecture searches. the proxy task design tools can include one or more tools to search for an optimal proxy task having the lowest neural architecture search cost while meeting a minimum correlation requirement threshold after being provided with a proxy task search space definition. the proxy task design tools can further include one or more tools to select candidate models for computing correlation scores of proxy tasks as well as one or more tools to measure variance of a model. the proxy task design tools can minimize time and effort involved in designing the proxy task.
20240289619. GRADIENT-FREE STRUCTURED PRUNING OF NEURAL NETWORKS_simplified_abstract_(google llc)
Inventor(s): Azade Nova of San Jose CA (US) for google llc, Hanjun Dai of Atlanta GA (US) for google llc, Dale Eric Schuurmans of Edmonton (CA) for google llc
IPC Code(s): G06N3/082, G06N3/048
CPC Code(s): G06N3/082
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing a machine learning task on a network input to generate a network output. one of the methods includes: obtaining data specifying an initial neural network configured to perform a machine learning task; a representativeness measure for each of a plurality of filters; determining a central tendency measure for the plurality of filters based on processing a batch of network inputs using the initial neural network; determining a cumulative importance score for each of the plurality of filters; selecting a proper subset of the plurality of filters; and generating a pruned neural network configured to perform the machine learning task.
20240289658. Enhancing Simulated Annealing with Quantum Annealing_simplified_abstract_(google llc)
Inventor(s): Hartmut NEVEN of Malibu CA (US) for google llc
IPC Code(s): G06N10/00, G06F15/163, G06N7/01
CPC Code(s): G06N10/00
Abstract: methods and apparatus for enhancing simulated annealing with quantum fluctuations. in one aspect, a method includes obtaining an input state; performing simulated annealing on the input state with a temperature reduction schedule until a decrease in energy is below a first minimum value; terminating the simulated annealing in response to determining that the decrease in energy is below the first minimum level; outputting a first evolved state and first temperature value; reducing the temperature to a minimum temperature value; performing quantum annealing on the first evolved state with a transversal field increase schedule until a completion of a second event occurs; terminating the quantum annealing in response to determining that a completion of the second event has occurred; outputting a second evolved state as a subsequent input state for the simulated annealing, and determining that the completion of the first event has occurred.
20240289659. VARIATIONAL QUANTUM STATE PREPARATION_simplified_abstract_(google llc)
Inventor(s): Ryan Babbush of Venice CA (US) for google llc, Ian David Kivlichan of Cambridge MA (US) for google llc
IPC Code(s): G06N10/00, G06F15/16
CPC Code(s): G06N10/00
Abstract: methods, systems and apparatus for performing quantum state preparation. in one aspect, a method includes the actions of defining a target quantum state of a quantum system, wherein time evolution of the quantum system is governed by a target hamiltonian, and defining a total hamiltonian that interpolates between an initial hamiltonian and the target hamiltonian, wherein the total hamiltonian is equal to the initial hamiltonian at an initial time and is equal to the target hamiltonian at a final time; approximating the time evolution of the total hamiltonian using a truncated linear combination of unitary simulations to generate a truncated time evolution operator; evolving a ground state of the initial hamiltonian according to the truncated time evolution operator for a truncated number of time steps to generate an intermediate state; and variationally adjusting the intermediate state to determine a wavefunction that approximates the target quantum state of the quantum system.
Inventor(s): Ofer Naaman of Santa Barbara CA (US) for google llc
IPC Code(s): G06N10/40, H03F7/00
CPC Code(s): G06N10/40
Abstract: the disclosure is towards parametric amplifiers with inductive input coupling for quantum computing systems. one example aspect of the present disclosure is directed to a quantum computing system comprising a first qubit, a first measurement device, and a first amplifier. the first measurement device is configured to generate a first qubit signal corresponding to a first quantum state of the first qubit. the first amplifier is configured to amplify the first qubit signal. the first amplifier comprises a first transmission-line resonator. the first transmission-line resonator provides an inductive reactance for an electrical coupling between the first measurement device and the first amplifier. the inductive reactance for the electrical coupling enables a transmission of the first qubit signal.
Inventor(s): Rolando D. Somma of Santa Fe NM (US) for google llc
IPC Code(s): G06N10/80, G06N10/20, G06N10/40, G06N10/60
CPC Code(s): G06N10/80
Abstract: systems and methods for simulating classical physical systems are provided. in one example, a method may include initializing one or more qubits with an initial quantum state encoding one or more physical properties of a classical physical system comprising an oscillator network. an example method may include simulating, by one or more quantum computing devices using the one or more qubits, the classical physical system.
Inventor(s): Yushi Jing of Mountain View CA (US) for google llc, Shumeet Baluja of Leesburg VA (US) for google llc
IPC Code(s): G06Q30/0251, G06Q30/02, G06Q30/0201, G06Q30/0241, G06Q30/0273, G06Q30/08
CPC Code(s): G06Q30/0257
Abstract: techniques for identifying groups of local features in an image and presenting advertisement information associated with stored images that match one or more features within the group of local features are described. the techniques include providing an image, identifying a region of interest in the image, providing a user-selectable link associated with the region of interest in the image, receiving a request for the region of interest in the image via the user-selectable link, and presenting advertisement information associated with a stored image that matches one or more features within the requested region of interest.
20240289926. PROCESSING IMAGES USING MIXTURE OF EXPERTS_simplified_abstract_(google llc)
Inventor(s): Carlos Riquelme Ruiz of Zurich (CH) for google llc, André Susano Pinto of Zurich (CH) for google llc, Basil Mustafa of Zurich (CH) for google llc, Daniel M. Keysers of Stallikon (CH) for google llc, Joan Puigcerver i Perez of Zurich (CH) for google llc, Maxim Neumann of Zurich (CH) for google llc, Neil Matthew Tinmouth Houlsby of Zurich (CH) for google llc, Rodolphe Jenatton of Berlin (DE) for google llc
IPC Code(s): G06T5/60
CPC Code(s): G06T5/60
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating predictions about images. one of the systems includes a neural network comprising a sequence of one or more network blocks that are each configured to perform operations comprising: obtaining a block input that represents an intermediate representation of an input image; determining a plurality of patches of the block input or of an updated representation of the block input, wherein each patch comprises a different subset of elements of the block input or of the updated representation of the block input; assigning each patch to one or more respective expert modules of a plurality of expert modules of the network block; for each patch of the plurality of patches, processing the patch using the corresponding expert modules to generate respective module outputs; and generating a block output by combining the module outputs.
Inventor(s): Wei-Cheng Kuo of Santa Clara CA (US) for google llc, Fred Bertsch of Belmont CA (US) for google llc, Wei Li of Fremont CA (US) for google llc, Anthony J. Piergiovanni of Denver CO (US) for google llc, Mohammad Taghi Saffar of Santa Clara CA (US) for google llc, Anelia Angelova of Palo Alto CA (US) for google llc
IPC Code(s): G06T7/73, G06F40/126, G06F40/40, G06V10/77, G06V10/80
CPC Code(s): G06T7/73
Abstract: generally, the disclosure is directed to generalized objected location, where the located object is in accordance to a natural language (nl) query. more specifically, the embodiments include a unified generalized visual localization architecture. the architecture achieves enhanced performance on the following three tasks: referring expression comprehension, object localization, and object detection. the embodiments employ machine-learned nl models and/or image models. the architecture is enabled to understand and answer natural localization questions towards an image, to output multiple boxes, provide no output if the object is not present (e.g., a null result), as well as, solve general detection tasks.
20240290025. AVATAR BASED ON MONOCULAR IMAGES_simplified_abstract_(google llc)
Inventor(s): Yinda Zhang of Palo Alto CA (US) for google llc, Sean Ryan Francesco Fanello of San Francisco CA (US) for google llc, Ziqian Bai of Burnaby (CA) for google llc, Feitong Tan of Mountain View CA (US) for google llc, Zeng Huang of Los Angeles CA (US) for google llc, Kripasindhu Sarkar of Zurich (CH) for google llc, Danhang Tang of West Hollywood CA (US) for google llc, Di Qiu of Kitchener (CA) for google llc, Abhimitra Meka of San Francisco CA (US) for google llc, Ruofei Du of San Francisco CA (US) for google llc, Mingsong Dou of Cupertino CA (US) for google llc, Sergio Orts Escolano of Zurich (CH) for google llc, Rohit Kumar Pandey of Sunnyvale CA (US) for google llc, Thabo Beeler of Egg (CH) for google llc
IPC Code(s): G06T13/40, G06T7/90, G06T17/20, G06V10/44
CPC Code(s): G06T13/40
Abstract: a method comprises receiving a first sequence of images of a portion of a user, the first sequence of images being monocular images; generating an avatar based on the first sequence of images, the avatar being based on a model including a feature vector associated with a vertex; receiving a second sequence of images of the portion of the user; and based on the second sequence of images, modifying the avatar with a displacement of the vertex to represent a gesture of the avatar.
Inventor(s): Chun-Yen Liu of Zhubei (TW) for google llc, Chiaching Chu of New Taipei City (TW) for google llc, Ion Bita of Los Altos CA (US) for google llc
IPC Code(s): G09G3/3258
CPC Code(s): G09G3/3258
Abstract: this document describes systems and techniques directed at enlarging active areas of displays in electronic devices. in aspects, a display includes a grid of transistors positioned within a display panel module to control an illumination of one or more electroluminescent layers. routing lines extend from one or more transistors of the grid of transistors to at least one electroluminescent layer. in this way, the at least one electroluminescent layer can be positioned away from the grid of transistors and disposed above portions of display panel module driving circuitry. as a result, active areas of displays can be enlarged and information content can be maximized without a panel border area allotted to the display panel module driving circuitry surrounding transistors having to be reduced.
Inventor(s): Françoise Beaufays of Mountain View CA (US) for google llc, Johan Schalkwyk of Scarsdale NY (US) for google llc, Khe Chai Sim of Dublin CA (US) for google llc
IPC Code(s): G10L13/047, G10L15/06
CPC Code(s): G10L13/047
Abstract: processor(s) of a client device can: identify a textual segment stored locally at the client device; process the textual segment, using a speech synthesis model stored locally at the client device, to generate synthesized speech audio data that includes synthesized speech of the identified textual segment; process the synthesized speech, using an on-device speech recognition model that is stored locally at the client device, to generate predicted output; and generate a gradient based on comparing the predicted output to ground truth output that corresponds to the textual segment. in some implementations, the generated gradient is used, by processor(s) of the client device, to update weights of the on-device speech recognition model. in some implementations, the generated gradient is additionally or alternatively transmitted to a remote system for use in remote updating of global weights of a global speech recognition model.
Inventor(s): Wenqian Huang of Mountain View CA (US) for google llc, Hao Zhang of Jericho NY (US) for google llc, Shankar Kumar of New York NY (US) for google llc, Shuo-yiin Chang of Sunnyvale CA (US) for google llc, Tara N. Sainath of Jersey City NJ (US) for google llc
IPC Code(s): G10L15/06, G06F40/30, G10L15/26
CPC Code(s): G10L15/063
Abstract: a joint segmenting and asr model includes an encoder to receive a sequence of acoustic frames and generate, at each of a plurality of output steps, a higher order feature representation for a corresponding acoustic frame. the model also includes a decoder to generate based on the higher order feature representation at each of the plurality of output steps a probability distribution over possible speech recognition hypotheses, and an indication of whether the corresponding output step corresponds to an end of segment (eos). the model is trained on a set of training samples, each training sample including audio data characterizing multiple segments of long-form speech; and a corresponding transcription of the long-form speech, the corresponding transcription annotated with ground-truth eos labels obtained via distillation from a language model teacher that receives the corresponding transcription as input and injects the ground-truth eos labels into the corresponding transcription between semantically complete segments.
20240290321. CHUNK-WISE ATTENTION FOR LONGFORM ASR_simplified_abstract_(google llc)
Inventor(s): Yongqiang Wang of Kirkland WA (US) for google llc, Yu Zhang of Mountain View CA (US) for google llc, Wei Han of Mountain View CA (US) for google llc, Parisa Haghani of Mountain View CA (US) for google llc, Pedro J. Moreno Mengibar of Jersey City NJ (US) for google llc
IPC Code(s): G10L15/06, G10L15/26
CPC Code(s): G10L15/063
Abstract: a method includes receiving training data including a corpus of multilingual unspoken textual utterances, a corpus of multilingual un-transcribed non-synthetic speech utterances, and a corpus of multilingual transcribed non-synthetic speech utterances. for each un-transcribed non-synthetic speech utterance, the method includes generating a target quantized vector token and a target token index, generating contrastive context vectors from corresponding masked audio features, and deriving a contrastive loss term. the method also includes generating an alignment output, generating a first probability distribution over possible speech recognition hypotheses for the alignment output, and determining an alignment output loss term. the method also includes generating a second probability distribution over possible speech recognition hypotheses and determining a non-synthetic speech loss term. the method also includes pre-training an audio encoder based on the contrastive loss term, the alignment output loss term, and the non-synthetic speech loss term.
Inventor(s): JAEYOUNG Kim of Cupertino CA (US) for google llc, Han Lu of Redmond WA (US) for google llc, Soheil Khorram of Redwood City CA (US) for google llc, Anshuman Tripathi of Mountain View CA (US) for google llc, Qian Zhang of Mountain View CA (US) for google llc, Hasim Sak of Santa Clara CA (US) for google llc
IPC Code(s): G10L15/06
CPC Code(s): G10L15/063
Abstract: a method of training an accent recognition model includes receiving a corpus of training utterances spoken across various accents, each training utterance in the corpus including training audio features characterizing the training utterance, and executing a training process to train the accent recognition model on the corpus of training utterances to teach the accent recognition model to learn how to predict accent representations from the training audio features. the accent recognition model includes one or more strided convolution layers, a stack of multi-headed attention layers, and a pooling layer configured to generate a corresponding accent representation.
Inventor(s): Wenqian Ronny Huang of Mountain View CA (US) for google llc, Tara N. Sainath of Jersey City NJ (US) for google llc
IPC Code(s): G10L15/06, G06N3/02, G10L15/16, G10L15/197, G10L15/22
CPC Code(s): G10L15/063
Abstract: a method of training a language model for rare-word speech recognition includes obtaining a set of training text samples, and obtaining a set of training utterances used for training a speech recognition model. each training utterance in the plurality of training utterances includes audio data corresponding to an utterance and a corresponding transcription of the utterance. the method also includes applying rare word filtering on the set of training text samples to identify a subset of rare-word training text samples that include words that do not appear in the transcriptions from the set of training utterances or appear in the transcriptions from the set of training utterances less than a threshold number of times. the method further includes training the external language model on the transcriptions from the set of training utterances and the identified subset of rare-word training text samples.
Inventor(s): Matthew Sharifi of Kilchberg (CH) for google llc, Victor Carbune of Zürich (CH) for google llc
IPC Code(s): G10L15/065, G10L15/01, G10L15/06, G10L15/18, G10L15/26, G10L15/30
CPC Code(s): G10L15/065
Abstract: a method includes receiving user queries directed toward a cloud-based assistant service. for each received user query directed toward the cloud-based assistant service, the method also includes extracting one or more attributes from the user query and logging the user query into one or more of a plurality of category buckets based on the one or more attributes extracted from the user query. the method also includes determining when at least one of the plurality of category buckets includes a threshold number of the user queries logged into the at least one category bucket, and when the at least one of the plurality of category buckets includes the threshold number of the user queries, generating a distilled model of the cloud-based assistant service. the distilled model of the cloud-based assistant service is configured to execute on one or more target client devices.
Inventor(s): William J. Byrne of Davis CA (US) for google llc, Karthik Krishnamoorthi of San Jose CA (US) for google llc, Saravanan Ganesh of Sunnyvale CA (US) for google llc
IPC Code(s): G10L15/197, G10L13/02, G10L15/06, G10L15/22
CPC Code(s): G10L15/197
Abstract: a method includes obtaining an utterance from a user including a user query directed toward a digital assistant. the method includes generating, using a language model, a first prediction string based on the utterance and determining whether the first prediction string includes an application programming interface (api) call to invoke a program via an api. when the first prediction string includes the api call to invoke the program, the method includes calling, using the api call, the program via the api to retrieve a program result; receiving, via the api, the program result; updating a conversational context with the program result that includes the utterance; and generating, using the language model, a second prediction string based on the updated conversational context. when the first prediction string does not include the api call, the method includes providing an utterance response to the utterance based on the first prediction string.
20240290333. PROVIDING PRE-COMPUTED HOTWORD MODELS_simplified_abstract_(google llc)
Inventor(s): Matthew Sharifi of Kilchberg (CH) for google llc
IPC Code(s): G10L15/22, G06F3/04842, G06F3/16, G10L15/06, G10L15/08, G10L15/18, G10L15/26, G10L15/30
CPC Code(s): G10L15/22
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, for each of multiple words or sub-words, audio data corresponding to multiple users speaking the word or sub-word; training, for each of the multiple words or sub-words, a pre-computed hotword model for the word or sub-word based on the audio data for the word or sub-word; receiving a candidate hotword from a computing device; identifying one or more pre-computed hotword models that correspond to the candidate hotword; and providing the identified, pre-computed hotword models to the computing device.
20240290763. Pluggable CPU Modules with Vertical Power_simplified_abstract_(google llc)
Inventor(s): Houle Gan of Santa Clara CA (US) for google llc, Richard Stuart Roy of Mountain View CA (US) for google llc, Yujeong Shim of Cupertino CA (US) for google llc, William F. Edwards, JR. of Livermore CA (US) for google llc, Chenhao Nan of Santa Clara CA (US) for google llc
IPC Code(s): H01L25/16, H01L23/00, H05K1/11, H05K1/18
CPC Code(s): H01L25/162
Abstract: a pluggable processor module includes a microprocessor package, a voltage regulator including a capacitor board, and contact pads that each include a first side in contact with the microprocessor package and a second side in contact with the capacitor board.
Inventor(s): Bonan Liu of New York NY (US) for google llc, Ramesh Rathan Dharan of New York NY (US) for google llc, Michelle Morgan Socher of New York NY (US) for google llc, Shuen Wen Si of Mountain View CA (US) for google llc, Anwesha Das of New York NY (US) for google llc
IPC Code(s): H04L9/08, H04L9/14, H04L67/1095, H04L67/561
CPC Code(s): H04L9/0825
Abstract: a method includes obtaining a key status for a first cryptographic key. the first cryptographic key is used to encrypt replicated data of a first replication instance. the method also includes determining, based on the key status, that the first cryptographic key is inaccessible which causes the first replication instance to be unavailable. in response to determining that the first cryptographic key is inaccessible, the method includes scheduling a second replication instance to be unavailable after a threshold amount of time has passed. the second replication instance includes replicated data encrypted by a second cryptographic key that is accessible. after the threshold amount of time has passed and when the first cryptographic key is still inaccessible, the method includes setting the second replication instance as unavailable.
20240291650. SECURE ENVIRONMENT FOR OPERATIONS ON PRIVATE DATA_simplified_abstract_(google llc)
Inventor(s): Carlos Cela of Mountain View CA (US) for google llc, John Tobler of Mountain View CA (US) for google llc, Brian Burdick of Mountain View CA (US) for google llc, Branton Horsley of Mountain View CA (US) for google llc, Mayank Patel of Mountain View CA (US) for google llc, Chanda Patel of Mountain View CA (US) for google llc, Asela Gunawardana of Mountain View CA (US) for google llc
IPC Code(s): H04L9/08, G06F21/53, H04L9/30, H04L9/32
CPC Code(s): H04L9/088
Abstract: the techniques disclosed herein provide a secure control plane (scp), which in turn provides an isolated secure execution environment for a data plane (dp). any arbitrary business logic can execute within the dp, and all sensitive data traversing the scp and entering the dp is encrypted. split keys generated outside the dp are assembled within, and only within, the dp, where they are used to decrypt sensitive data, enabling the business logic to perform computations using the sensitive data within the secure execution environment. the dp also provides attestation for the business logic executing within the dp, enabling outside parties to verify that the deployed business logic matches published logic. in the event of proprietary logic that is not published, techniques are also disclosed herein that enable verification that proprietary business logic deployed on the dp adheres to security policies.
20240291720. Network Reachability Impact Analysis_simplified_abstract_(google llc)
Inventor(s): Hongkun Yang of San Jose CA (US) for google llc, Hui Liu of San Ramon CA (US) for google llc, Gargi Adhav of San Jose CA (US) for google llc, Alan Tang of Los Angeles CA (US) for google llc
IPC Code(s): H04L41/12, H04L41/082, H04L41/084, H04L41/085, H04L43/045
CPC Code(s): H04L41/12
Abstract: a method includes obtaining a stream of consecutive network configuration snapshots each including network configuration information. the method also includes determining that first network configuration information of a first network configuration snapshot of the network from the stream of consecutive network configuration snapshots for the network is not the same as second network configuration information of a second network configuration snapshot of the network from the stream of consecutive network configuration snapshots for the network. the method also includes generating a reachability differentiation graph that identifies a net change to reachability from the first network configuration information and the second network configuration information based on determining that the first network configuration information is not the same as the second network configuration information.
Inventor(s): Justin Lewis of Marina Del Rey CA (US) for google llc, Ruxandra Georgiana Davies of Santa Monica CA (US) for google llc
IPC Code(s): H04L51/10, G06F16/48, G06F16/735, G06F16/9535, H04L51/52
CPC Code(s): H04L51/10
Abstract: methods, systems, and media for identifying video objects linked to a source video are provided. in some embodiments, the method comprises: identifying demographic attributes corresponding to a first user participating in an online conversation; determining at least one keyword associated with the online conversation, wherein the keyword indicates a topic of the online conversation; identifying a video object based at least on the demographic attributes and the at least one keyword, wherein the video object comprises a portion of a video; causing the identified video object to be presented in a group of video objects on a first user device associated with the first user; receiving an indication that the identified video object has been selected on the first user device for inclusion in a message in the online conversation; and causing the identified video object to be presented on a second user device associated with the second user.
Inventor(s): Jue Wang of San Jose CA (US) for google llc, James S. Wong of Sunnyvale CA (US) for google llc
IPC Code(s): H04N21/234, H04N21/235
CPC Code(s): H04N21/23418
Abstract: methods, systems, and media for synchronizing video streams are provided. in some embodiments, the method comprises: identifying a target video stream and a reference video stream, wherein the target video stream and the reference video stream are two different broadcasts of a program; generating, for the target video stream, a sequence of fingerprints; determining a time shift at which the sequence of fingerprints appears within the reference video stream; determining whether the target video stream is synchronized with the reference video stream by determining whether the time shift exceeds a predetermined threshold; and, in response to determining that the target video stream is not synchronized with the reference video stream, causing an electronic programming guide that includes an indication of the target video stream to be modified based on the time shift.
20240292115. Automatic White-Balance (AWB) for a Camera System_simplified_abstract_(google llc)
Inventor(s): Liang Liang of San Diego CA (US) for google llc, Anirban Chatterjee of Santa Clara CA (US) for google llc, Nisha Masharani of San Francisco CA (US) for google llc, Eric Scott Penner of Redmond WA (US) for google llc, Isaac William Reynolds of Longmont UT (US) for google llc
IPC Code(s): H04N23/88, H04N23/12, H04N23/57, H04N23/611, H04N23/63
CPC Code(s): H04N23/88
Abstract: this document describes techniques and apparatuses for automatic white-balance for a camera system. the techniques and apparatuses utilize a precursor image to detect one or more detected faces and determine a tone. the camera system retrieves tonal data based on a group of images determined to contain a same face as the detected face. based on this tonal data, a difference in white balance is determined based on the difference in tone of the detected face within the precursor image and the associated tonal data. camera settings are adjusted based on the difference in white balance to enable capture of an image having an improved tone.
Inventor(s): Dongeek Shin of Santa Clara CA (US) for google llc, Anupam Pathak of San Carlos CA (US) for google llc
IPC Code(s): H04W12/06, H04W12/61, H04W12/63
CPC Code(s): H04W12/06
Abstract: a computer-implemented authentication method comprises broadcasting, by a first device, an ultrawideband (uwb) message. the first device receives one or more uwb responses to the uwb message from one or more uwb equipped devices and determines respective distances to the one or more uwb equipped devices based on timing information associated with the uwb message and the one or more uwb responses. the method further comprises determining one or more of the uwb equipped devices having a respective distance to the first device that is within a threshold radius of the first device to be authenticatable devices, and communicating, by the first device, authentication information to one or more of the authenticatable devices to authenticate a user of the first device on the one or more authenticatable devices.
20240292405. Intra-User Equipment-Coordination Set Communication_simplified_abstract_(google llc)
Inventor(s): Jibing Wang of San Jose CA (US) for google llc, Erik Richard Stauffer of Sunnyvale CA (US) for google llc
IPC Code(s): H04W72/121, H04W76/10, H04W76/20, H04W92/10
CPC Code(s): H04W72/121
Abstract: methods, devices, systems, and means for intra-uecs communication by a coordinating user equipment, ue, in a user equipment-coordination set, uecs, are described herein. the coordinating ue allocates first air interface resources to a second ue and second air interface resources to a third ue for intra-uecs communication. the coordinating ue receives, using the allocated first air interface resources, an internet protocol, ip, data packet from the second ue in the uecs. the coordinating ue determines that a destination address included in the ip data packet is an address of the third ue and transmits, using the allocated second air interface resources, the ip data packet to the third ue.
Inventor(s): Chun-Yen Liu of Zhubei (TW) for google llc, Chiaching Chu of New Taipei City (TW) for google llc, Ion Bita of Los Altos CA (US) for google llc
IPC Code(s): H10K59/121, H10K59/131, H10K59/35
CPC Code(s): H10K59/1213
Abstract: this document describes systems and techniques directed at enlarging active areas of displays using variable pixel and/or transistor densities. in aspects, a display includes a cover layer positioned as a topmost layer and an array of pixels positioned thereunder. a plurality of transistors, positioned under the array of pixels, may control an electrical activation of one or more pixels within the array of pixels. in implementations, the plurality of transistors define a smaller area than the array of pixels such that at least one pixel of the array of pixels extends beyond the area defined by the plurality of transistors and above driving circuitry. variable pixel and/or transistor densities can support the enlarged active area of displays and improve user experience.
- Google LLC
- A61B5/024
- A61B5/00
- A61B5/021
- A61B5/0295
- CPC A61B5/02416
- Google llc
- F17C5/00
- F17C13/02
- G05B19/4155
- CPC F17C5/007
- G06F3/06
- CPC G06F3/0619
- G06F3/16
- G10L15/08
- G10L15/22
- CPC G06F3/167
- G06F11/10
- H03M13/00
- H03M13/15
- CPC G06F11/1044
- G06F13/16
- G06F9/38
- G06F15/76
- G06F17/16
- G06N3/045
- G06N3/063
- G06N3/08
- G06N3/10
- G06N5/04
- G06N20/00
- G06N20/10
- CPC G06F13/1668
- G06F16/2453
- G06F16/23
- G06F16/27
- CPC G06F16/24532
- G06F16/901
- CPC G06F16/9024
- G06F16/9532
- G06F16/955
- G06F40/40
- CPC G06F16/9532
- G06F16/957
- G06F16/9535
- CPC G06F16/9577
- G06F21/62
- G06F8/65
- CPC G06F21/6209
- G06F40/284
- CPC G06F40/284
- G06F40/58
- G10L15/00
- G10L15/06
- G10L25/18
- CPC G06F40/58
- CPC G06N3/08
- G06N3/082
- G06N3/048
- CPC G06N3/082
- G06N10/00
- G06F15/163
- G06N7/01
- CPC G06N10/00
- G06F15/16
- G06N10/40
- H03F7/00
- CPC G06N10/40
- G06N10/80
- G06N10/20
- G06N10/60
- CPC G06N10/80
- G06Q30/0251
- G06Q30/02
- G06Q30/0201
- G06Q30/0241
- G06Q30/0273
- G06Q30/08
- CPC G06Q30/0257
- G06T5/60
- CPC G06T5/60
- G06T7/73
- G06F40/126
- G06V10/77
- G06V10/80
- CPC G06T7/73
- G06T13/40
- G06T7/90
- G06T17/20
- G06V10/44
- CPC G06T13/40
- G09G3/3258
- CPC G09G3/3258
- G10L13/047
- CPC G10L13/047
- G06F40/30
- G10L15/26
- CPC G10L15/063
- G06N3/02
- G10L15/16
- G10L15/197
- G10L15/065
- G10L15/01
- G10L15/18
- G10L15/30
- CPC G10L15/065
- G10L13/02
- CPC G10L15/197
- G06F3/04842
- CPC G10L15/22
- H01L25/16
- H01L23/00
- H05K1/11
- H05K1/18
- CPC H01L25/162
- H04L9/08
- H04L9/14
- H04L67/1095
- H04L67/561
- CPC H04L9/0825
- G06F21/53
- H04L9/30
- H04L9/32
- CPC H04L9/088
- H04L41/12
- H04L41/082
- H04L41/084
- H04L41/085
- H04L43/045
- CPC H04L41/12
- H04L51/10
- G06F16/48
- G06F16/735
- H04L51/52
- CPC H04L51/10
- H04N21/234
- H04N21/235
- CPC H04N21/23418
- H04N23/88
- H04N23/12
- H04N23/57
- H04N23/611
- H04N23/63
- CPC H04N23/88
- H04W12/06
- H04W12/61
- H04W12/63
- CPC H04W12/06
- H04W72/121
- H04W76/10
- H04W76/20
- H04W92/10
- CPC H04W72/121
- H10K59/121
- H10K59/131
- H10K59/35
- CPC H10K59/1213
