Patents by Inventor Yonghui Wu

Yonghui Wu 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: 11223349
    Abstract: A joint control method with variable ZVS angles for dynamic efficiency optimization in a WPC system for EVs under ZVS conditions, including: adjusting a phase-shift duty cycle of a secondary active rectifier to control a charging voltage and a charging current of EV's batteries through a charging voltage closed loop and a charging current closed loop, respectively; adjusting a power angle of the secondary active rectifier to control a ZVS angle of the secondary active rectifier through a secondary ZVS angle closed loop; adjusting a phase-shift duty cycle of a primary inverter to control a ZVS angle of the primary inverter through the primary ZVS angle closed loop; determining the current operating case of the WPC system and adjusting the ZVS angles of the primary inverter and the secondary active rectifier to automatically identify an optimal operating point with a maximum charging efficiency through the P&O method.
    Type: Grant
    Filed: December 28, 2019
    Date of Patent: January 11, 2022
    Assignee: Xi'an Jiaotong University
    Inventors: Yue Wang, Yongbin Jiang, Chenxu Zhao, Ruibang Li, Yonghui Liu, Min Wu, Laili Wang, Xu Yang
  • Publication number: 20220005465
    Abstract: A method for performing speech recognition using sequence-to-sequence models includes receiving audio data for an utterance and providing features indicative of acoustic characteristics of the utterance as input to an encoder. The method also includes processing an output of the encoder using an attender to generate a context vector, generating speech recognition scores using the context vector and a decoder trained using a training process, and generating a transcription for the utterance using word elements selected based on the speech recognition scores. The transcription is provided as an output of the ASR system.
    Type: Application
    Filed: September 20, 2021
    Publication date: January 6, 2022
    Applicant: Google LLC
    Inventors: Rohit Prakash Prabhavalkar, Zhifeng Chen, Bo Li, Chung-cheng Chiu, Kanury Kanishka Rao, Yonghui Wu, Ron J. Weiss, Navdeep Jaitly, Michiel A.u. Bacchiani, Tara N. Sainath, Jan Kazimierz Chorowski, Anjuli Patricia Kannan, Ekaterina Gonina, Patrick An Phu Nguyen
  • Publication number: 20210390271
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural machine translation. The method comprises obtaining a first sequence of words in a source language, generating a modified sequence of words in the source language by inserting a word boundary symbol only at the beginning of each word in the first sequence of words and not at the end of each word, dividing the modified sequence of words into wordpieces using a wordpiece model, generating, from the wordpieces, an input sequence of input tokens for a neural machine translation system; and generating an output sequence of words using the neural machine translation system based on the input sequence of input tokens.
    Type: Application
    Filed: August 27, 2021
    Publication date: December 16, 2021
    Inventors: Mohammad Norouzi, Zhifeng Chen, Yonghui Wu, Michael Schuster, Quoc V. Le
  • Publication number: 20210366463
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language.
    Type: Application
    Filed: August 2, 2021
    Publication date: November 25, 2021
    Inventors: Samuel Bengio, Yuxuan Wang, Zongheng Yang, Zhifeng Chen, Yonghui Wu, Ioannis Agiomyrgiannakis, Ron J. Weiss, Navdeep Jaitly, Ryan M. Rifkin, Robert Andrew James Clark, Quoc V. Le, Russell J. Ryan, Ying Xiao
  • Publication number: 20210358491
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for speech recognition using attention-based sequence-to-sequence models. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A sequence of feature vectors indicative of the acoustic characteristics of the utterance is generated. The sequence of feature vectors is processed using a speech recognition model that has been trained using a loss function that uses N-best lists of decoded hypotheses, the speech recognition model including an encoder, an attention module, and a decoder. The encoder and decoder each include one or more recurrent neural network layers. A sequence of output vectors representing distributions over a predetermined set of linguistic units is obtained. A transcription for the utterance is obtained based on the sequence of output vectors. Data indicating the transcription of the utterance is provided.
    Type: Application
    Filed: July 27, 2021
    Publication date: November 18, 2021
    Applicant: Google LLC
    Inventors: Rohit Prakash Prabhavalkar, Tara N. Sainath, Yonghui Wu, Patrick An Phu Nguyen, Zhifeng Chen, Chung-Cheng Chiu, Anjuli Patricia Kannan
  • Publication number: 20210326573
    Abstract: Provided are a fingerprint identification device, a fingerprint identification method and an electronic device, which could improve security of fingerprint identification. The fingerprint identification device includes an optical fingerprint sensor including a plurality of pixel units; at least two filter units disposed above at least two of the plurality of pixel units, where each filter unit corresponds to one pixel unit, and the at least two filter units comprise filter units in at least two colors.
    Type: Application
    Filed: May 21, 2021
    Publication date: October 21, 2021
    Applicant: SHENZHEN GOODIX TECHNOLOGY CO., LTD.
    Inventors: Shunzhan LI, Xiang CHENG, Qin GU, Yonghui WU
  • Patent number: 11145293
    Abstract: Methods, systems, and apparatus, including computer-readable media, for performing speech recognition using sequence-to-sequence models. An automated speech recognition (ASR) system receives audio data for an utterance and provides features indicative of acoustic characteristics of the utterance as input to an encoder. The system processes an output of the encoder using an attender to generate a context vector and generates speech recognition scores using the context vector and a decoder trained using a training process that selects at least one input to the decoder with a predetermined probability. An input to the decoder during training is selected between input data based on a known value for an element in a training example, and input data based on an output of the decoder for the element in the training example. A transcription is generated for the utterance using word elements selected based on the speech recognition scores. The transcription is provided as an output of the ASR system.
    Type: Grant
    Filed: July 19, 2019
    Date of Patent: October 12, 2021
    Assignee: Google LLC
    Inventors: Rohit Prakash Prabhavalkar, Zhifeng Chen, Bo Li, Chung-Cheng Chiu, Kanury Kanishka Rao, Yonghui Wu, Ron J. Weiss, Navdeep Jaitly, Michiel A. U. Bacchiani, Tara N. Sainath, Jan Kazimierz Chorowski, Anjuli Patricia Kannan, Ekaterina Gonina, Patrick An Phu Nguyen
  • Patent number: 11138392
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for machine translation using neural networks. In some implementations, a text in one language is translated into a second language using a neural network model. The model can include an encoder neural network comprising a plurality of bidirectional recurrent neural network layers. The encoding vectors are processed using a multi-headed attention module configured to generate multiple attention context vectors for each encoding vector. A decoder neural network generates a sequence of decoder output vectors using the attention context vectors. The decoder output vectors can represent distributions over various language elements of the second language, allowing a translation of the text into the second language to be determined based on the sequence of decoder output vectors.
    Type: Grant
    Filed: July 25, 2019
    Date of Patent: October 5, 2021
    Assignee: Google LLC
    Inventors: Zhifeng Chen, Macduff Richard Hughes, Yonghui Wu, Michael Schuster, Xu Chen, Llion Owen Jones, Niki J. Parmar, George Foster, Orhan Firat, Ankur Bapna, Wolfgang Macherey, Melvin Jose Johnson Premkumar
  • Publication number: 20210295858
    Abstract: Methods, systems, and computer program products for generating, from an input character sequence, an output sequence of audio data representing the input character sequence. The output sequence of audio data includes a respective audio output sample for each of a number of time steps. One example method includes, for each of the time steps: generating a mel-frequency spectrogram for the time step by processing a representation of a respective portion of the input character sequence using a decoder neural network; generating a probability distribution over a plurality of possible audio output samples for the time step by processing the mel-frequency spectrogram for the time step using a vocoder neural network; and selecting the audio output sample for the time step from the possible audio output samples in accordance with the probability distribution.
    Type: Application
    Filed: April 5, 2021
    Publication date: September 23, 2021
    Inventors: Yonghui Wu, Jonathan Shen, Ruoming Pang, Ron J. Weiss, Michael Schuster, Navdeep Jaitly, Zongheng Yang, Zhifeng Chen, Yu Zhang, Yuxuan Wang, Russell John Wyatt Skerry-Ryan, Ryan M. Rifkin, Ioannis Agiomyrgiannakis
  • Patent number: 11113480
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural machine translation. One of the systems includes an encoder neural network comprising: an input forward long short-term memory (LSTM) layer configured to process each input token in the input sequence in a forward order to generate a respective forward representation of each input token, an input backward LSTM layer configured to process each input token in a backward order to generate a respective backward representation of each input token and a plurality of hidden LSTM layers configured to process a respective combined representation of each of the input tokens in the forward order to generate a respective encoded representation of each of the input tokens; and a decoder subsystem configured to receive the respective encoded representations and to process the encoded representations to generate an output sequence.
    Type: Grant
    Filed: September 25, 2017
    Date of Patent: September 7, 2021
    Assignee: Google LLC
    Inventors: Mohammad Norouzi, Zhifeng Chen, Yonghui Wu, Michael Schuster, Quoc V. Le
  • Patent number: 11107463
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for speech recognition using attention-based sequence-to-sequence models. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A sequence of feature vectors indicative of the acoustic characteristics of the utterance is generated. The sequence of feature vectors is processed using a speech recognition model that has been trained using a loss function that uses N-best lists of decoded hypotheses, the speech recognition model including an encoder, an attention module, and a decoder. The encoder and decoder each include one or more recurrent neural network layers. A sequence of output vectors representing distributions over a predetermined set of linguistic units is obtained. A transcription for the utterance is obtained based on the sequence of output vectors. Data indicating the transcription of the utterance is provided.
    Type: Grant
    Filed: August 1, 2019
    Date of Patent: August 31, 2021
    Assignee: Google LLC
    Inventors: Rohit Prakash Prabhavalkar, Tara N. Sainath, Yonghui Wu, Patrick An Phu Nguyen, Zhifeng Chen, Chung-Cheng Chiu, Anjuli Patricia Kannan
  • Patent number: 11107457
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language.
    Type: Grant
    Filed: November 26, 2019
    Date of Patent: August 31, 2021
    Assignee: Google LLC
    Inventors: Samuel Bengio, Yuxuan Wang, Zongheng Yang, Zhifeng Chen, Yonghui Wu, Ioannis Agiomyrgiannakis, Ron J. Weiss, Navdeep Jaitly, Ryan M. Rifkin, Robert Andrew James Clark, Quoc V. Le, Russell J. Ryan, Ying Xiao
  • Publication number: 20210217404
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech synthesis. The methods, systems, and apparatus include actions of obtaining an audio representation of speech of a target speaker, obtaining input text for which speech is to be synthesized in a voice of the target speaker, generating a speaker vector by providing the audio representation to a speaker encoder engine that is trained to distinguish speakers from one another, generating an audio representation of the input text spoken in the voice of the target speaker by providing the input text and the speaker vector to a spectrogram generation engine that is trained using voices of reference speakers to generate audio representations, and providing the audio representation of the input text spoken in the voice of the target speaker for output.
    Type: Application
    Filed: May 17, 2019
    Publication date: July 15, 2021
    Applicant: Google LLC
    Inventors: Ye Jia, Zhifeng Chen, Yonghui Wu, Jonathan Shen, Ruoming Pang, Ron J. Weiss, Ignacio Lopez Moreno, Fei Ren, Yu Zhang, Quan Wang, Patrick Nguyen
  • Publication number: 20210209315
    Abstract: The present disclosure provides systems and methods that train and use machine-learned models such as, for example, sequence-to-sequence models, to perform direct and text-free speech-to-speech translation. In particular, aspects of the present disclosure provide an attention-based sequence-to-sequence neural network which can directly translate speech from one language into speech in another language, without relying on an intermediate text representation.
    Type: Application
    Filed: March 7, 2020
    Publication date: July 8, 2021
    Inventors: Ye Jia, Zhifeng Chen, Yonghui Wu, Melvin Johnson, Fadi Biadsy, Ron Weiss, Wolfgang Macherey
  • Patent number: 11048910
    Abstract: Provided are a fingerprint identification device, a fingerprint identification method and an electronic device, which could improve security of fingerprint identification. The fingerprint identification device includes an optical fingerprint sensor including a plurality of pixel units; at least two filter units disposed above at least two pixel units of the plurality of pixel units, where each filter unit corresponds to one pixel unit, and the at least two filter units comprise filter units in at least two colors.
    Type: Grant
    Filed: May 18, 2019
    Date of Patent: June 29, 2021
    Assignee: SHENZHEN GOODIX TECHNOLOGY CO., LTD.
    Inventors: Shunzhan Li, Xiang Cheng, Qin Gu, Yonghui Wu
  • Patent number: 10971170
    Abstract: Methods, systems, and computer program products for generating, from an input character sequence, an output sequence of audio data representing the input character sequence. The output sequence of audio data includes a respective audio output sample for each of a number of time steps. One example method includes, for each of the time steps: generating a mel-frequency spectrogram for the time step by processing a representation of a respective portion of the input character sequence using a decoder neural network; generating a probability distribution over a plurality of possible audio output samples for the time step by processing the mel-frequency spectrogram for the time step using a vocoder neural network; and selecting the audio output sample for the time step from the possible audio output samples in accordance with the probability distribution.
    Type: Grant
    Filed: August 8, 2018
    Date of Patent: April 6, 2021
    Assignee: Google LLC
    Inventors: Yonghui Wu, Jonathan Shen, Ruoming Pang, Ron J. Weiss, Michael Schuster, Navdeep Jaitly, Zongheng Yang, Zhifeng Chen, Yu Zhang, Yuxuan Wang, Russell John Wyatt Skerry-Ryan, Ryan M. Rifkin, Ioannis Agiomyrgiannakis
  • Publication number: 20200410396
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model, wherein the machine learning model has been trained on training data to perform a plurality of machine learning tasks including the first machine learning task, and wherein the machine learning model has been configured through training to process the augmented model input to generate a machine learning model output of the first type for the model input.
    Type: Application
    Filed: July 13, 2020
    Publication date: December 31, 2020
    Inventors: Zhifeng Chen, Michael Schuster, Melvin Jose Johnson Premkumar, Yonghui Wu, Quoc V. Le, Maxim Krikun, Thorsten Brants
  • Publication number: 20200380215
    Abstract: A method of transcribing speech using a multilingual end-to-end (E2E) speech recognition model includes receiving audio data for an utterance spoken in a particular native language, obtaining a language vector identifying the particular language, and processing, using the multilingual E2E speech recognition model, the language vector and acoustic features derived from the audio data to generate a transcription for the utterance. The multilingual E2E speech recognition model includes a plurality of language-specific adaptor modules that include one or more adaptor modules specific to the particular native language and one or more other adaptor modules specific to at least one other native language different than the particular native language. The method also includes providing the transcription for output.
    Type: Application
    Filed: March 30, 2020
    Publication date: December 3, 2020
    Applicant: Google LLC
    Inventors: Anjuli Patricia Kannan, Tara N. Sainath, Yonghui Wu, Ankur Bapna, Arindrima Datta
  • Publication number: 20200380952
    Abstract: A method includes receiving an input text sequence to be synthesized into speech in a first language and obtaining a speaker embedding, the speaker embedding specifying specific voice characteristics of a target speaker for synthesizing the input text sequence into speech that clones a voice of the target speaker. The target speaker includes a native speaker of a second language different than the first language. The method also includes generating, using a text-to-speech (TTS) model, an output audio feature representation of the input text by processing the input text sequence and the speaker embedding. The output audio feature representation includes the voice characteristics of the target speaker specified by the speaker embedding.
    Type: Application
    Filed: April 22, 2020
    Publication date: December 3, 2020
    Applicant: Google LLC
    Inventors: Yu Zhang, Ron J. Weiss, Byungha Chun, Yonghui Wu, Zhifeng Chen, Russell John Wyatt Skerry-Ryan, Ye Jia, Andrew M. Rosenberg, Bhuvana Ramabhadran
  • Patent number: 10713593
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model, wherein the machine learning model has been trained on training data to perform a plurality of machine learning tasks including the first machine learning task, and wherein the machine learning model has been configured through training to process the augmented model input to generate a machine learning model output of the first type for the model input.
    Type: Grant
    Filed: December 29, 2016
    Date of Patent: July 14, 2020
    Assignee: Google LLC
    Inventors: Zhifeng Chen, Michael Schuster, Melvin Jose Johnson Premkumar, Yonghui Wu, Quoc V. Le, Maxim Krikun, Thorsten Brants