Patents Assigned to Google LLC
-
Patent number: 12080271Abstract: Computer generated speech can be generated for cross-lingual natural language textual data streams by utilizing a universal phoneme set. In a variety of implementations, the natural language textual data stream includes a primary language portion in a primary language and a secondary language portion that is not in the primary language. Phonemes corresponding to the secondary language portion can be determined from a set of phonemes in a universal data set. These phonemes can be mapped back to a set of phonemes for the primary language. Audio data can be generated for these phonemes to pronounce the secondary language portion of the natural language textual data stream utilizing phonemes associated with the primary language.Type: GrantFiled: August 26, 2022Date of Patent: September 3, 2024Assignee: GOOGLE LLCInventors: Ami Patel, Siamak Tazari
-
Patent number: 12079700Abstract: Techniques of generating input for a kernel-based machine learning system that uses a kernel to perform classification operations on data involve generating unbiased estimators for gaussian kernels according to a new framework called Structured Orthogonal Random Features (SORF). The unbiased estimator KSORF to the kernel involves a linear transformation matrix WSORF computed using products of a set of pairs of matrices, each pair including an orthogonal matrix and respective diagonal matrix whose elements are real numbers following a specified probability distribution. Typically, the orthogonal matrix is a Walsh-Hadamard matrix, the specified probability distribution is a Rademacher distribution, and there are at least two, usually three, pairs of matrices multiplied together to form the linear transformation matrix WSORF.Type: GrantFiled: October 25, 2017Date of Patent: September 3, 2024Assignee: GOOGLE LLCInventors: Daniel Holtmann-Rice, Sanjiv Kumar, Xinnan Yu, Krzysztof Marcin Choromanski, Ananda Theertha Suresh
-
Patent number: 12082097Abstract: This document describes methods and systems for common search space configuration and system information acquisition. As part of the methods and systems, a base station (120) wirelessly communicating with a user equipment (110) that is in an engaged mode determines (402) to configure a common search space through which the user equipment (110) can receive a system information block that is other than a system information block type 1 or a master information block. The base station (120) transmits a first message (404) that includes a set of common search space configuration parameters for the user equipment (110) to receive the other system information block. The base station (120) transmits (406), in accordance with the set of common search space configuration parameters, a second message that includes the other system information block.Type: GrantFiled: September 23, 2019Date of Patent: September 3, 2024Assignee: GOOGLE LLCInventors: Chih-Hsiang Wu, Teming Chen
-
Patent number: 12080311Abstract: Systems and methods of the present disclosure are directed toward digital signal processing using machine-learned differentiable digital signal processors. For example, embodiments of the present disclosure may include differentiable digital signal processors within the training loop of a machine-learned model (e.g., for gradient-based training). Advantageously, systems and methods of the present disclosure provide high quality signal processing using smaller models than prior systems, thereby reducing energy costs (e.g., storage and/or processing costs) associated with performing digital signal processing.Type: GrantFiled: June 29, 2023Date of Patent: September 3, 2024Assignee: GOOGLE LLCInventors: Jesse Engel, Adam Roberts, Chenjie Gu, Lamtharn Hantrakul
-
Patent number: 12079695Abstract: A computer-implemented method of generating scale-permuted models can generate models having improved accuracy and reduced evaluation computational requirements. The method can include defining, by a computing system including one or more computing devices, a search space including a plurality of candidate permutations of a plurality of candidate feature blocks, each of the plurality of candidate feature blocks having a respective scale. The method can include performing, by the computing system, a plurality of search iterations by a search algorithm to select a scale-permuted model from the search space, the scale-permuted model based at least in part on a candidate permutation of the plurality of candidate permutations.Type: GrantFiled: October 1, 2020Date of Patent: September 3, 2024Assignee: GOOGLE LLCInventors: Xianzhi Du, Yin Cui, Tsung-Yi Lin, Quoc V. Le, Pengchong Jin, Mingxing Tan, Golnaz Ghiasi, Xiaodan Song
-
Patent number: 12079703Abstract: Systems and methods can utilize a conformer model to process a data set for various data processing tasks, including, but not limited to, speech recognition, sound separation, protein synthesis determination, video or other image set analysis, and natural language processing. The conformer model can use feed-forward blocks, a self-attention block, and a convolution block to process data to learn global interactions and relative-offset-based local correlations of the input data.Type: GrantFiled: December 31, 2020Date of Patent: September 3, 2024Assignee: GOOGLE LLCInventors: Anmol Gulati, Ruoming Pang, Niki Parmar, Jiahui Yu, Wei Han, Chung-Cheng Chiu, Yu Zhang, Yonghui Wu, Shibo Wang, Weikeng Qin, Zhengdong Zhang
-
Patent number: 12080272Abstract: A method (400) for representing an intended prosody in synthesized speech includes receiving a text utterance (310) having at least one word (240), and selecting an utterance embedding (204) for the text utterance. Each word in the text utterance has at least one syllable (230) and each syllable has at least one phoneme (220). The utterance embedding represents an intended prosody. For each syllable, using the selected utterance embedding, the method also includes: predicting a duration (238) of the syllable by decoding a prosodic syllable embedding (232, 234) for the syllable based on attention by an attention mechanism (340) to linguistic features (222) of each phoneme of the syllable and generating a plurality of fixed-length predicted frames (260) based on the predicted duration for the syllable.Type: GrantFiled: December 10, 2019Date of Patent: September 3, 2024Assignee: Google LLCInventors: Robert Clark, Chun-an Chan, Vincent Wan
-
Patent number: 12080055Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an image representation neural network.Type: GrantFiled: March 17, 2022Date of Patent: September 3, 2024Assignee: Google LLCInventors: Tsung-Yi Lin, Barret Zoph, Ekin Dogus Cubuk, Golnaz Ghiasi, Quoc V. Le
-
Patent number: 12079845Abstract: A method of presenting information to a party through a messaging application is described. Responsive to receipt of a communication from a party (e.g., the first user), a reply is sent. The communication and the reply is presented in an interface to the sender. The messaging system determines matching content that is relevant to one or both of the communication and the reply and determines a quality of the match. Determining the quality of the match may include determining a score for an advertisement based on the advertisement's responsiveness to content identified in the reply message that was sent. Based on a determination that the quality is above a threshold, the matching content is presented along with the communication and the reply.Type: GrantFiled: May 9, 2023Date of Patent: September 3, 2024Assignee: Google LLCInventors: Alan B. Sheinberg, Stanley Chen
-
Patent number: 12080276Abstract: A method for optimizing speech recognition includes receiving a first acoustic segment characterizing a hotword detected by a hotword detector in streaming audio captured by a user device, extracting one or more hotword attributes from the first acoustic segment, and adjusting, based on the one or more hotword attributes extracted from the first acoustic segment, one or more speech recognition parameters of an automated speech recognition (ASR) model. After adjusting the speech recognition parameters of the ASR model, the method also includes processing, using the ASR model, a second acoustic segment to generate a speech recognition result. The second acoustic segment characterizes a spoken query/command that follows the first acoustic segment in the streaming audio captured by the user device.Type: GrantFiled: March 22, 2023Date of Patent: September 3, 2024Assignee: Google LLCInventors: Matthew Sharifi, Aleksandar Kracun
-
Patent number: 12079644Abstract: Methods, systems, and media for generating modified user engagement signals based on obstructed layers in a user interface are provided.Type: GrantFiled: October 28, 2022Date of Patent: September 3, 2024Assignee: Google LLCInventor: Sylvia N'guessan
-
Patent number: 12080204Abstract: A display system varies a size of a field of view area of a display for augmented reality (AR) applications based on at least one of ambient light in the environment and content displayed at the display and varying a brightness level of the field of view area such that the brightness level within the field of view area is inversely proportional to the field of view area. Based on an amount of ambient light detected in the environment of the display system, the display system adjusts the size of the area of the field of view of the display in inverse proportion to the amount of detected ambient light. As the size of the field of view area decreases, the display system increases the brightness level of the display within the field of view such that the brightness level is approximately inversely proportional to the field of view area.Type: GrantFiled: December 14, 2020Date of Patent: September 3, 2024Assignee: GOOGLE LLCInventors: Stuart James Myron Nicholson, Timothy Paul Bodiya, Daniel Adema, Shreyas Potnis
-
Patent number: 12080285Abstract: Implementations are directed to using an automated assistant to initiate an assisted call on behalf of a given user. The assistant can, during the assisted call, receiving a request, from an additional user on the assisted call, for information that is not known to the assistant. In response, the assistant can render a prompt for the information and, while awaiting responsive input from the given user, continue the assisted call using already resolved value(s) for the assisted call. If responsive input is received within a threshold duration of time, synthesized speech, corresponding to the responsive input, is rendered as part of the assisted call. Implementations are additionally or alternatively directed to using the automated assistant to provide, during an ongoing call between a given user and an additional user, output that is based on a value requested by the additional user during the ongoing call.Type: GrantFiled: April 22, 2020Date of Patent: September 3, 2024Assignee: GOOGLE LLCInventors: Yuval Baror, Yaniv Leviathan
-
Patent number: 12079447Abstract: A method is implemented in a computing device having an operating system configured to capture screenshot images in response to entries of a pre-defined user input. In the method, an application executes in a current state or mode in which an application screen is shown on the display device, detects an entry of the pre-defined user input by a user, and identifies one or more features that (i) are supported by the application, (ii) are at least partially determined by the current state or mode, and (iii) can use at least one type of information displayed by the application screen to perform respective function(s). The application generates a selectable link for each identified feature, and presents, on the display device, the generated selectable link(s), such that a selection by the user of any one of the generated selectable link(s) causes the application to perform the respective set of functions.Type: GrantFiled: December 10, 2021Date of Patent: September 3, 2024Assignee: GOOGLE LLCInventors: Haroon Baig, Holger-Frederik Flier
-
Patent number: 12081442Abstract: A distributed sender driven Admission Control System (ACS) is described herein, leveraging Weighted-Fair Quality of Service (QoS) queues, found in standard NICs and switches, to guarantee RPC level latency service level objectives (SLOs) by a judicious selection of QoS weights and traffic-mix across QoS queues. ACS installs cluster-wide RPC latency SLOs by mapping LS RPCs to higher weight QoS queues, and coping with overloads by adaptively apportioning LS RPCs amongst QoS queues based on measured completion times for each queue. When the network demand spikes unexpectedly to predetermined threshold percentage of provisioned capacity, ACS achieves a latency SLO that is significantly lower than the state-of-art congestion control at the 99.9th-p and admits significantly more RPCs meeting SLO target when RPC sizes are not aligned with priorities.Type: GrantFiled: January 20, 2022Date of Patent: September 3, 2024Assignee: Google LLCInventors: Gautam Kumar, Yiwen Zhang, Nandita Dukkipati, Xian Wu, Amin Vahdat
-
Patent number: 12079191Abstract: Systems and methods are disclosed herein for modifying suggestion metadata in an electronic document. A copy request is received to copy a portion of the electronic document. The portion of the electronic document includes a suggestion having metadata that indicates the suggestion was made by a first user. The copy request is received from a second user. A paste request to paste the copied portion is received from the second user. Responsive to determining to modify the metadata of the suggestion, the indication that the first suggestion was made by the first user is replaced with an indication that the first suggestion was made by the second user.Type: GrantFiled: February 7, 2022Date of Patent: September 3, 2024Assignee: Google LLCInventors: Jacob Robert Voytko, Luiz Do Amaral De Franca Pereira Filho, Fil Zembowicz
-
Patent number: 12079711Abstract: Apparatus and methods for processing neural network models are provided. The apparatus can comprise a plurality of identical artificial intelligence processing dies. Each artificial intelligence processing die among the plurality of identical artificial intelligence processing dies can include at least one inter-die input block and at least one inter-die output block. Each artificial intelligence processing die among the plurality of identical artificial intelligence processing dies is communicatively coupled to another artificial intelligence processing die among the plurality of identical artificial intelligence processing dies by way of one or more communication paths from the at least one inter-die output block of the artificial intelligence processing die to the at least one inter-die input block of the artificial intelligence processing die.Type: GrantFiled: February 26, 2021Date of Patent: September 3, 2024Assignee: Google LLCInventors: Uday Kumar Dasari, Olivier Temam, Ravi Narayanaswami, Dong Hyuk Woo
-
Patent number: 12080283Abstract: A method includes receiving a sequence of acoustic frames extracted from audio data corresponding to an utterance. During a first pass, the method includes processing the sequence of acoustic frames to generate N candidate hypotheses for the utterance. During a second pass, and for each candidate hypothesis, the method includes: generating a respective un-normalized likelihood score; generating a respective external language model score; generating a standalone score that models prior statistics of the corresponding candidate hypothesis; and generating a respective overall score for the candidate hypothesis based on the un-normalized likelihood score, the external language model score, and the standalone score. The method also includes selecting the candidate hypothesis having the highest respective overall score from among the N candidate hypotheses as a final transcription of the utterance.Type: GrantFiled: March 22, 2022Date of Patent: September 3, 2024Assignee: Google LLCInventors: Neeraj Gaur, Tongzhou Chen, Ehsan Variani, Bhuvana Ramabhadran, Parisa Haghani, Pedro J. Moreno Mengibar
-
Patent number: 12081404Abstract: A method for arbitrarily grouping computer system resources includes receiving a resource policy to be applied to a group of resources associated with a user. The resource policy includes a unique user-defined label assigned to each resource of the group of resources. The method also includes identifying the group of resources among a plurality of resources using the user-defined label. Here, the plurality of resources is associated with the user and distributed across a plurality of different computing environments. For each identified resource of the group of resources, the method also includes applying the resource policy to a corresponding identified resource by accessing the respective computing environment where the corresponding identified resource resides.Type: GrantFiled: July 17, 2023Date of Patent: September 3, 2024Assignee: Google LLCInventors: Cyrus Harvesf, Marco Cavalli
-
Patent number: D1040845Type: GrantFiled: November 5, 2021Date of Patent: September 3, 2024Assignee: GOOGLE LLCInventors: Jonathan Gaiser, Felix David Mejia Abreu, Andrew Schoneweis, Julian Le, In-Hee Bae
