Patents by Inventor Quan Wang

Quan Wang has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 12776323
    Abstract: Techniques disclosed herein are directed towards streaming keyphrase detection which can be customized to detect one or more particular keyphrases, without requiring retraining of any model(s) for those particular keyphrase(s). Many implementations include processing audio data using a speaker separation model to generate separated audio data which isolates an utterance spoken by a human speaker from one or more additional sounds not spoken by the human speaker, and processing the separated audio data using a text independent speaker identification model to determine whether a verified and/or registered user spoke a spoken utterance captured in the audio data. Various implementations include processing the audio data and/or the separated audio data using an automatic speech recognition model to generate a text representation of the utterance.
    Type: Grant
    Filed: July 5, 2024
    Date of Patent: October 27, 2026
    Assignee: GOOGLE LLC
    Inventors: Rajeev Rikhye, Quan Wang, Yanzhang He, Qiao Liang, Ian C. McGraw
  • Publication number: 20260320312
    Abstract: A method (500) includes, for each training sample (410) of a plurality of training samples: processing, using a sequence transduction model (200), corresponding training input features (415) to obtain one or more output token sequence hypotheses (432) each including one or more predicted common tokens (204); and determining a token-level loss (462) based on, for each hypothesis: a number of special token insertions each associated with a corresponding predicted special token that appears in the hypothesis but does not appear in a corresponding sequence of ground-truth output tokens; and a number of special token deletions each associated with a corresponding ground-truth special token in the set of ground-truth special tokens that does not appear in hypothesis. The method also includes training the sequence transduction model to minimize additive error rate based on the token-level losses determined for the plurality of training samples.
    Type: Application
    Filed: November 11, 2022
    Publication date: October 15, 2026
    Applicant: Google LLC
    Inventors: Guanlong Zhao, Quan Wang, Beltrán Labrador Serrano, Han Lu, Ignacio Lopez Moreno, Yiling Huang
  • Publication number: 20260321666
    Abstract: A current collector, an electrode sheet and a battery. The current collector comprises: n non-conductive layers and n+1 conductive layers, wherein the n non-conductive layers and the n+1 conductive layers are alternately stacked, and the outermost layer is the conductive layer, n being an integer greater than 1; and each non-conductive layer comprises one non-conductive metal layer or a plurality of stacked non-conductive metal layers, and each conductive layer comprises at least one metal conductive layer. The current collector has high safety, low processing difficulty, low cost and a high yield.
    Type: Application
    Filed: February 18, 2024
    Publication date: October 15, 2026
    Inventors: Siwei WEI, Zhiyi JIANG, Hongming WANG, Quan WANG, Haicheng WAN, Taotao HUO
  • Publication number: 20260311688
    Abstract: A method includes obtaining a training dataset including a plurality of training utterances each paired with a corresponding transcription. For each respective training utterance the operations include generating, using a large language model (LLM), a corresponding speech recognition result of the respective training utterance; determining a corresponding ground-truth histogram based on the corresponding transcription, determining a corresponding prediction histogram based on the corresponding speech recognition result; and determining a corresponding word-level hallucination loss based on the corresponding ground-truth histogram and the corresponding prediction histogram. The corresponding ground-truth histogram represents a number of occurrences of each token in the corresponding transcription, while the corresponding prediction histogram represents a number of occurrences of each token in the corresponding speech recognition result.
    Type: Application
    Filed: February 27, 2026
    Publication date: October 8, 2026
    Applicant: GDM Holding LLC
    Inventors: Quan Wang, Qingyun Dou, Yonghui Xiao, Fadi Biadsy, Parisa Haghani, Neeraj Gaur, Sean Csukas, Peng Chen, Jia Guo, Kartik Audhkhasi, Virat Vishnu Shejwalkar, Arun Narayanan, Youzheng Chen, Bhuvana Ramabhadran
  • Publication number: 20260300624
    Abstract: A method includes obtaining a plurality of audio data segments characterizing a conversation between two or more speakers. For each respective audio data segment, the method includes generating a corresponding short-form diarized transcript of a respective portion of the conversation. The corresponding short-form diarized transcript includes a respective sequence of terms and a respective one or more speaker tokens attributing each of the sequence terms to a corresponding speaker identity. The method includes generating a reconciled long-form diarized transcript based on the corresponding short-form diarized transcript generated for each respective audio data segment. A sequence processing neural network generates the reconciled diarized transcript by, for one of the corresponding short-form diarized transcripts, permuting a first speaker token and a second speaker token of the at least one of the corresponding short-form diarized transcripts.
    Type: Application
    Filed: March 31, 2025
    Publication date: October 1, 2026
    Applicant: Google LLC
    Inventors: Quan Wang, Neeraj Gaur, Guanlong Zhao, Parisa Haghani
  • Patent number: 12743583
    Abstract: A method includes receiving a prompt including a textual diarization request and corresponding audio data characterizing a conversation between multiple speakers. The method also includes generating a sequence of audio encoding chunks based on the corresponding data. For each respective audio encoding chunk, the method includes using a trained large language model (LLM) generating corresponding diarization results based on the respective audio encoding chunk and the textual diarization request and generating a new audio cohort for the respective audio encoding chunk based on the corresponding diarization results. The corresponding diarization results include a speech recognition result that has one or more predicted terms. Each respective predicted term is associated with a corresponding speaker token representing a predicted identity of a respective speaker that spoke the respective predicted term.
    Type: Grant
    Filed: April 25, 2024
    Date of Patent: September 22, 2026
    Assignee: Google LLC
    Inventors: Quan Wang, Yiling Huang, Guanlong Zhao
  • Patent number: 12731043
    Abstract: A method for training a multivariate relationship generation model, an electronic device and a medium are provided. The technical solution includes: obtaining a plurality of knowledge text entries; performing semantic parsing on each knowledge text entry to obtain a plurality of entities and semantic information of each knowledge text entry; constructing a heterogeneous graph based on the plurality of entities and the semantic information; and training an initial artificial intelligence (AI) network model based on the heterogeneous graph to obtain a multivariate relationship generation model.
    Type: Grant
    Filed: September 21, 2021
    Date of Patent: September 8, 2026
    Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.
    Inventors: Quan Wang, Haifeng Wang, Yajuan Lyu, Yong Zhu
  • Publication number: 20260256011
    Abstract: A chip stacked structure, a package structure, and an electronic device are provided. In a first direction, a second chip located on an even-numbered layer is offset from a first chip located on an odd-numbered layer to expose multiple first signal pads on the first chip on the odd-numbered layer, and the multiple first signal pads are arranged in a second direction; in the second direction, the second chip located on the even-numbered layer is offset from the first chip located on the odd-numbered layer to expose multiple first common pads on the first chip on the odd-numbered layer, the multiple first signal pads are arranged in the first direction; and the first direction is perpendicular to the second direction; and multiple second common pads on the second chip are arranged in the first direction, and a lead between one of the first common pads and one of the second common pads is perpendicular to the first direction.
    Type: Application
    Filed: December 19, 2025
    Publication date: August 27, 2026
    Inventors: Quan WANG, Hengrong SHI
  • Patent number: 12701304
    Abstract: Provided in the present disclosure are a video generation method and apparatus, and a device and a storage medium. The method includes: firstly, when an application request for a target effect object has been received, acquiring location information of the current user; then, on the basis of the location information of the current user, determining a target place of interest (POI) corresponding to the current user; acquiring an effect resource of the target POI, and on the basis of the location information of the current user and location information of the target POI, determining a direction relationship between the current user and the target POI; on the basis of the direction relationship, displaying, on a photographic page, a photographic effect corresponding to the effect resource; and then on the basis of the photographic effect corresponding to the effect resource, generating a result video corresponding to the target effect object.
    Type: Grant
    Filed: January 3, 2023
    Date of Patent: August 4, 2026
    Assignee: Lemon Inc.
    Inventors: Jingjie Chen, Tianyang Xu, Siyao Yang, Weikai Li, Zihao Chen, Changhao Ou, Yixin Zhao, Yiling Chen, Sang Hyup Lee, Yi Yue, Jie Liao, Shengchuan Shi, Zixiong Zhang, Quan Wang, Jian Sun, Aoyu Wang
  • Patent number: 12694625
    Abstract: Embodiments of the present disclosure provide an image processing method and apparatus, an electronic device, and a program product. The method includes: obtaining a live-action shooting image; determining a target object image in the live-action shooting image, where the target object image is an image containing a target object; acquiring a displaying object associated with the target object; determining, according to the target object image, a target displaying position of the displaying object in the live-action shooting image; and displaying the displaying object at the target displaying position in the live-action shooting image.
    Type: Grant
    Filed: January 25, 2022
    Date of Patent: July 28, 2026
    Inventor: Quan Wang
  • Patent number: 12682906
    Abstract: A method of generating an accurate speaker representation for an audio sample includes receiving a first audio sample from a first speaker and a second audio sample from a second speaker. The method includes dividing a respective audio sample into a plurality of audio slices. The method also includes, based on the plurality of slices, generating a set of candidate acoustic embeddings where each candidate acoustic embedding includes a vector representation of acoustic features. The method further includes removing a subset of the candidate acoustic embeddings from the set of candidate acoustic embeddings. The method additionally includes generating an aggregate acoustic embedding from the remaining candidate acoustic embeddings in the set of candidate acoustic embeddings after removing the subset of the candidate acoustic embeddings.
    Type: Grant
    Filed: September 19, 2022
    Date of Patent: July 14, 2026
    Assignee: Google LLC
    Inventors: Yeming Fang, Quan Wang, Pedro Jose Moreno Mengibar, Ignacio Lopez Moreno, Gang Feng, Fang Chu, Jin Shi, Jason William Pelecanos
  • Patent number: 12670912
    Abstract: A speaker verification method includes receiving audio data corresponding to an utterance, processing the audio data to generate a reference attentive d-vector representing voice characteristics of the utterance, the evaluation ad-vector includes ne style classes each including a respective value vector concatenated with a corresponding routing vector. The method also includes generating using a self-attention mechanism, at least one multi-condition attention score that indicates a likelihood that the evaluation ad-vector matches a respective reference ad-vector associated with a respective user. The method also includes identifying the speaker of the utterance as the respective user associated with the respective reference ad-vector based on the multi-condition attention score.
    Type: Grant
    Filed: October 2, 2023
    Date of Patent: June 30, 2026
    Assignee: Google LLC
    Inventors: Ignacio Lopez Moreno, Quan Wang, Jason Pelecanos, Yiling Huang, Mert Saglam
  • Patent number: 12639464
    Abstract: Provided are a file leak detection method. The method includes: acquiring a file operation event on a terminal device, wherein the file operation event is an event in which a specified operation is executed on a target file; extracting, from the file operation event, a file path of the target file involved in the file operation event; searching for file content of the target file according to the file path, and performing mapping processing on the file content of the target file, so as to obtain a file fingerprint of the target file; determining, according to the file path and the file fingerprint, whether the target file belongs to a specified file library which is used for dynamically maintaining a service file that needs to be protected; and if the target file belongs to the specified file library, determining that a file in the specified file library is leaking.
    Type: Grant
    Filed: October 27, 2022
    Date of Patent: May 26, 2026
    Assignee: Beijing Bytedance Network Technology Co., Ltd.
    Inventors: Quan Wang, Xinci Liu, Jian Yang, Xianglong Ma
  • Publication number: 20260134193
    Abstract: A method includes receiving audio data characterizing an utterance spoken by a user. The method also includes processing the audio data to generate a transcription of the utterance using a multimodal large language model (LLM). The transcription includes a sequence of terms. The method also includes processing, using the multimodal LLM, the audio data and the transcription in parallel to identify one or more revision terms in the sequence of terms. The one or more revision terms specify a revision action to perform on at least on other term in the sequence of terms. The method also includes modifying the transcription based on the one or more revision terms.
    Type: Application
    Filed: November 11, 2024
    Publication date: May 14, 2026
    Applicant: Google LLC
    Inventors: Quan Wang, Francoise Beaufays, Bhuvana Ramabhadran, Zhong Meng, Neng Chen, Antoine Bruguier, Yanzhang He, Golan Pundak, Guanlong Zhao
  • Publication number: 20260105919
    Abstract: A method (500) includes receiving an input audio signal (122) that corresponds to utterances (120) spoken by multiple speakers. The method also includes processing the input audio to generate a transcription (200) of the utterances and a sequence of speaker turn tokens (224) each indicating a location of a respective speaker turn. The method also includes segmenting the input audio signal into a plurality of speaker segments (225) based on the sequence of speaker tokens. The method also includes extracting a speaker-discriminative embedding from each speaker segment and performing spectral clustering on the speaker-discriminative embeddings to cluster the plurality of speaker segments into k classes. The method also includes assigning a respective speaker label (250) to each speaker segment clustered into the respective class that is different than the respective speaker label assigned to the speaker segments clustered into each other class of the k classes.
    Type: Application
    Filed: October 5, 2022
    Publication date: April 16, 2026
    Applicant: Google LLC
    Inventors: Quan Wang, Yiling Huang, Han Lu, Guanlong Zhao
  • Patent number: 12603938
    Abstract: Disclosed is a method for controlling data transmission for smart gas, comprising: obtaining gas data of a gas user, and storing the gas data into a storage unit; predicting a probability of full storage of the storage unit within a preset future time period based on a historical data increment of the storage unit; in response to the probability of full storage meeting a preset probability condition: obtaining the gas data of the gas user within the preset time period; determining the upload demand degree based on the gas data; and in response to the upload demand degree meeting a preset condition, transmitting the gas data within the preset time period to the smart gas management platform based on the smart gas object platform at a target upload time point of at least one smart gas meter of the gas user.
    Type: Grant
    Filed: August 27, 2024
    Date of Patent: April 14, 2026
    Assignee: CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD.
    Inventors: Zehua Shao, Junyan Zhou, Xiaojun Wei, Lei He, Quan Wang
  • Publication number: 20260094600
    Abstract: A method includes receiving a prompt directed towards an assistant large language model (LLM) and generating, using the assistant LLM, a sequence of output tokens based on the prompt. The sequence of output tokens includes a sequence of textual tokens including one or more correct textual tokens and one or more incorrect textual tokens, and one or more revision tokens each indicating a corresponding N number of incorrect textual tokens generated prior to the respective revision token and corresponding replacement textual tokens generated after the respective revision token for replacement of the corresponding N number of incorrect textual tokens. The method also includes generating a revised sequence of output tokens for the prompt based on the sequence of output tokens.
    Type: Application
    Filed: September 22, 2025
    Publication date: April 2, 2026
    Applicant: Google LLC
    Inventors: Quan Wang, Fadi Biadsy, Yonghui Xiao, Youzheng Chen
  • Publication number: 20260085619
    Abstract: A variable geometry turbine device includes: a turbine casing provided with an inlet duct, and defining an exhaust port and a bypass chamber therein; a gear rotating sleeve disposed inside the bypass chamber; a rack actuator; combined nozzle guide vanes including: a fixed nozzle and an elastic nozzle mechanism; and a turbine. A first annular chamber and a second annular chamber are defined between the exhaust port and the bypass chamber. A first radial channel and a second radial channel are defined under the bypass chamber, and are connected to the first annular chamber and the second annular chamber respectively. A side of the gear rotating sleeve defines a first notch and a second notch configured to be selectively connected to the first radial channel and the second radial channel respectively; and opening and closing of the first radial channel and the second radial channel have a time difference.
    Type: Application
    Filed: May 24, 2025
    Publication date: March 26, 2026
    Inventors: Quan LIU, Chao MA, Jianjun HUANG, Xinyuan XIONG, Zhanhao CHEN, Quan WANG, Yangli SUN
  • Publication number: 20260073923
    Abstract: A method includes receiving an input audio signal that corresponds to utterances spoken by multiple speakers. The method also includes processing the input audio to generate a transcription of the utterances and a sequence of speaker turn tokens each indicating a location of a respective speaker turn. The method also includes segmenting the input audio signal into a plurality of speaker segments based on the sequence of speaker tokens. The method also includes extracting a speaker-discriminative embedding from each speaker segment and performing spectral clustering on the speaker-discriminative embeddings to cluster the plurality of speaker segments into k classes. The method also includes assigning a respective speaker label to each speaker segment clustered into the respective class that is different than the respective speaker label assigned to the speaker segments clustered into each other class of the k classes.
    Type: Application
    Filed: November 13, 2025
    Publication date: March 12, 2026
    Applicant: Google LLC
    Inventors: Quan Wang, Han Lu, Evan Clark, Ignacio Lopez Moreno, Hasim Sak, Wei Xia, Taral Joglekar, Anshuman Tripathi
  • Publication number: 20260051318
    Abstract: A method includes receiving training utterances that include non-synthetic speech training utterances and synthetic speech utterances. For each training utterance, the method includes processing, using a memorized neural network, a corresponding sequence of input audio frames to generate a hotword detection output indicating a likelihood the training utterance includes a hotword, determining a first loss based on the hotword detection output, obtaining a hidden layer feature vector for each corresponding input audio frame; processing, using a speech classification model, the hidden layer feature vectors to predict a classification output for the training utterance; and determining an adversarial loss based on the classification output predicted for the training utterance.
    Type: Application
    Filed: August 7, 2025
    Publication date: February 19, 2026
    Applicant: GDM Holding LLC
    Inventors: Hyun Jin Park, Kurt Edward Partridge, Quan Wang