Patents by Inventor Anshuman Tripathi

Anshuman Tripathi 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).

  • Publication number: 20230096805
    Abstract: A method includes receiving a plurality of unlabeled audio samples corresponding to spoken utterances not paired with corresponding transcriptions. At a target branch of a contrastive Siamese network, the method also includes generating a sequence of encoder outputs for the plurality of unlabeled audio samples and modifying time characteristics of the encoder outputs to generate a sequence of target branch outputs. At an augmentation branch of a contrastive Siamese network, the method also includes performing augmentation on the unlabeled audio samples, generating a sequence of augmented encoder outputs for the augmented unlabeled audio samples, and generating predictions of the sequence of target branch outputs generated at the target branch. The method also includes determining an unsupervised loss term based on target branch outputs and predictions of the sequence of target branch outputs. The method also includes updating parameters of the audio encoder based on the unsupervised loss term.
    Type: Application
    Filed: December 14, 2021
    Publication date: March 30, 2023
    Applicant: Google LLC
    Inventors: Jaeyoung Kim, Soheil Khorram, Hasim Sak, Anshuman Tripathi, Han Lu, Qian Zhang
  • Publication number: 20230089308
    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: December 14, 2021
    Publication date: March 23, 2023
    Applicant: Google LLC
    Inventors: Quan Wang, Han Lu, Evan Clark, Ignacio Lopez Moreno, Hasim Sak, Wei Xia, Taral Joglekar, Anshuman Tripathi
  • Publication number: 20230084758
    Abstract: A method for training a speech recognition model with a loss function includes receiving an audio signal including a first segment corresponding to audio spoken by a first speaker, a second segment corresponding to audio spoken by a second speaker, and an overlapping region where the first segment overlaps the second segment. The overlapping region includes a known start time and a known end time. The method also includes generating a respective masked audio embedding for each of the first and second speakers. The method also includes applying a masking loss after the known end time to the respective masked audio embedding for the first speaker when the first speaker was speaking prior to the known start time, or applying the masking loss prior to the known start time when the first speaker was speaking after the known end time.
    Type: Application
    Filed: November 15, 2022
    Publication date: March 16, 2023
    Applicant: Google LLC
    Inventors: Anshuman Tripathi, Han Liu, Hasim Sak
  • Patent number: 11521595
    Abstract: A method for training a speech recognition model with a loss function includes receiving an audio signal including a first segment corresponding to audio spoken by a first speaker, a second segment corresponding to audio spoken by a second speaker, and an overlapping region where the first segment overlaps the second segment. The overlapping region includes a known start time and a known end time. The method also includes generating a respective masked audio embedding for each of the first and second speakers. The method also includes applying a masking loss after the known end time to the respective masked audio embedding for the first speaker when the first speaker was speaking prior to the known start time, or applying the masking loss prior to the known start time when the first speaker was speaking after the known end time.
    Type: Grant
    Filed: May 1, 2020
    Date of Patent: December 6, 2022
    Assignee: Google LLC
    Inventors: Anshuman Tripathi, Han Lu, Hasim Sak
  • Publication number: 20220310097
    Abstract: A streaming speech recognition model includes an audio encoder configured to receive a sequence of acoustic frames and generate a higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The streaming speech recognition model also includes a label encoder configured to receive a sequence of non-blank symbols output by a final softmax layer and generate a dense representation. The streaming speech recognition model also includes a joint network configured to receive the higher order feature representation generated by the audio encoder and the dense representation generated by the label encoder and generate a probability distribution over possible speech recognition hypotheses. Here, the streaming speech recognition model is trained using self-alignment to reduce prediction delay by encouraging an alignment path that is one frame left from a reference forced-alignment frame.
    Type: Application
    Filed: December 15, 2021
    Publication date: September 29, 2022
    Applicant: Google LLC
    Inventors: Jaeyoung Kim, Han Lu, Anshuman Tripathi, Qian Zhang, Hasim Sak
  • Publication number: 20220108689
    Abstract: A transformer-transducer model for unifying streaming and non-streaming speech recognition includes an audio encoder, a label encoder, and a joint network. The audio encoder receives a sequence of acoustic frames, and generates, at each of a plurality of time steps, a higher order feature representation for a corresponding acoustic frame. The label encoder receives a sequence of non-blank symbols output by a final softmax layer, and generates, at each of the plurality of time steps, a dense representation. The joint network receives the higher order feature representation and the dense representation at each of the plurality of time steps, and generates a probability distribution over possible speech recognition hypothesis. The audio encoder of the model further includes a neural network having an initial stack of transformer layers trained with zero look ahead audio context, and a final stack of transformer layers trained with a variable look ahead audio context.
    Type: Application
    Filed: March 23, 2021
    Publication date: April 7, 2022
    Applicant: Google LLC
    Inventors: Anshuman Tripathi, Hasim Sak, Han Lu, Qian Zhang, Jaeyoung Kim
  • Publication number: 20210343273
    Abstract: A method for training a speech recognition model with a loss function includes receiving an audio signal including a first segment corresponding to audio spoken by a first speaker, a second segment corresponding to audio spoken by a second speaker, and an overlapping region where the first segment overlaps the second segment. The overlapping region includes a known start time and a known end time. The method also includes generating a respective masked audio embedding for each of the first and second speakers. The method also includes applying a masking loss after the known end time to the respective masked audio embedding for the first speaker when the first speaker was speaking prior to the known start time, or applying the masking loss prior to the known start time when the first speaker was speaking after the known end time.
    Type: Application
    Filed: May 1, 2020
    Publication date: November 4, 2021
    Applicant: Google LLC
    Inventors: Anshuman Tripathi, Han Lu, Hasim Sak
  • Patent number: 10554144
    Abstract: This invention relates to a method of controlling a Solid State Transformer (SST).
    Type: Grant
    Filed: April 5, 2019
    Date of Patent: February 4, 2020
    Assignee: Nanyang Technological University
    Inventors: Shuyu Cao, Brihadeeswara Sriram Vaisambhayana, Anshuman Tripathi, Fengjiao Cui, Abishek Sethupandi, Hossein Dehghani Tafti
  • Publication number: 20190312521
    Abstract: This invention relates to a method of controlling a Solid State Transformer (SST).
    Type: Application
    Filed: April 5, 2019
    Publication date: October 10, 2019
    Inventors: Shuyu Cao, Brihadeeswara Sriram Vaisambhayana, Anshuman Tripathi, Fengjiao Cui, Abishek Sethupandi, Hossein Dehghani Tafti
  • Patent number: 10245959
    Abstract: There is provided a power converter system including a power bus, a plurality of power converter modules connected to the power bus in parallel, a plurality of energy storage modules, each energy storage module coupled to the power bus via a corresponding one of the plurality of power converter modules, and a controller module configured to control at least one of the power converter modules to operate in one of a plurality of operating modes. In particular, the plurality of operating modes of the power converter module includes a plurality of charging power conversion modes for connecting an input power source to the corresponding energy storage module for charging power to the corresponding energy storage module. There is also provided a corresponding method of manufacturing the power converter system.
    Type: Grant
    Filed: October 7, 2015
    Date of Patent: April 2, 2019
    Assignee: Nanyang Technological University
    Inventors: Anshuman Tripathi, Satyajit Athlekar, Nishanthi Duraisamy
  • Patent number: 10088838
    Abstract: A method for diagnostic monitoring of a wind turbine generator system, said wind turbine generator system comprising a generator, a drive train, and a number of sensors for providing signals and a control system. The method comprising the selection of three sets of signals from said sensors. From the three sets of signals three conditioned sets of signals are obtained by high pass filtering said first set of signals, low pass filtering the second set of signals, and forming a moving average value on the third set of signals. Based on each of said first, second and third set of conditioned signals an evaluation is performed in order to determine a fault, where said evaluation comprises comparing the first, second and third set of conditioned signals with reference values. If said comparison indicates a fault an alarm is set.
    Type: Grant
    Filed: January 17, 2012
    Date of Patent: October 2, 2018
    Assignee: VESTAS WIND SYSTEMS A/S
    Inventors: Shu Yu Cao, Bing Li, Anshuman Tripathi, Hock Heng Thia, Rasool Beevi D-O Mohamed Arif, Kheng Hong Ang
  • Patent number: 9722520
    Abstract: A method for controlling a variable speed wind turbine generator is disclosed. The generator is connected to a power converter comprising switches. The generator comprises a stator and a set of terminals connected to the stator and to the switches of the power converter. The method comprises: determining a stator flux reference value corresponding to a generator power of a desired magnitude, determining an estimated stator flux value corresponding to an actual generator power, determining a difference between the determined stator flux reference value and the estimated stator flux value, and operating said switches in correspondence to the determined stator flux reference value and the estimated stator flux value to adapt at least one stator electrical quantity to obtain said desired generator power magnitude.
    Type: Grant
    Filed: August 28, 2009
    Date of Patent: August 1, 2017
    Assignee: VESTAS WIND SYSTEMS A/S
    Inventors: Anshuman Tripathi, Cao Shu Yu, Allan Holm J├Ârgensen, Lars Helle
  • Patent number: 9590546
    Abstract: A power dissipating arrangement for dissipating power from a generator in a wind turbine is provided. The generator comprises a plurality of output terminals corresponding to a multi-phase output. The power dissipating arrangement comprises a plurality of dissipating units, a plurality of semiconductor switches, a trigger circuit for switching the semiconductor switches and a control unit for controlling the operation of the trigger circuit, thereby controlling the switching of the semiconductor switches.
    Type: Grant
    Filed: November 6, 2015
    Date of Patent: March 7, 2017
    Assignee: VESTAS WIND SYSTEMS A/S
    Inventors: Ove Styhm, Anshuman Tripathi, Amit Kumar Gupta
  • Patent number: 9494138
    Abstract: A variable speed wind turbine is provided. The wind turbine comprises a generator, a power converter for converting at least a portion of electrical power generated by the generator, an energy management arrangement coupled to the power converter, the energy management arrangement comprises an energy storage unit, and a controller. The controller is adapted to detect a power imbalance event and to transfer at least a portion of excess electrical energy generated by the generator to the energy storage unit to be stored therein when the power imbalance event is detected.
    Type: Grant
    Filed: August 10, 2010
    Date of Patent: November 15, 2016
    Assignee: VESTAS WIND SYSTEMS A/S
    Inventors: Amit Kumar Gupta, Gil Lampong Opina, Jr., Anshuman Tripathi, Yugarajan Karuppanan, Michael Casem Tumabcao
  • Patent number: 9476408
    Abstract: A method of controlling a wind turbine generator is provided, the wind turbine generator converting mechanical energy to electrical. The method comprises: determining an electromagnetic power reference representing the electromagnetic power generated by the wind turbine generator, wherein the electromagnetic power reference is determined based on a desired output of the wind turbine generator; controlling the electrical power generated by the wind turbine generator using a control signal, wherein the control signal is derived from the electromagnetic power reference and is modified in dependence on an inverse power function of the wind turbine generator by incorporating minimal copper loss constraint and stator voltage limiting constraint such that non-linearity of the wind turbine generator is compensated in the control loop and it operates at its maximum efficiency. One effect of the method is that classical linear control loop design can be employed in spite of the plant being a non-linear identity.
    Type: Grant
    Filed: March 12, 2014
    Date of Patent: October 25, 2016
    Assignee: VESTAS WIND SYSTEMS A/S
    Inventors: Shu Yu Cao, Anshuman Tripathi, Kim B. Larsen, Gert Karmisholt Andersen, Lars Helle
  • Patent number: 9438155
    Abstract: Parameters of PM machines, especially for IPM machine, are known to vary by significant amounts. This affects the controllability of such machines, which may lead to reduced power loading capability and increased losses. The present invention relates to a method for PM machine inductance profile identification based on voltage mode stator flux observation which could be easily integrated to the generator start-up process in wind turbine application for both stator flux vector feedback control system and current vector feedback control system.
    Type: Grant
    Filed: December 28, 2012
    Date of Patent: September 6, 2016
    Assignee: Vestas Wind Systems A/S
    Inventors: Shu Yu Cao, Anshuman Tripathi, Swee Yee Fonn, Ramasamy Anbarasu, Amit Kumar Gupta
  • Patent number: 9429142
    Abstract: The present invention relates to a method for charging a DC link of a power converter included in a wind turbine generator, the wind turbine generator comprising a generator side converter connected to an electrical generator and a grid side converter connectable, or connected, to an electrical grid through a grid circuit breaker, and a converter controller arranged to control at least the DC link, the DC link having a DC voltage level, the wind turbine generator comprising a wind turbine rotor arranged to rotate the electrical generator, wherein the method comprises rotating the wind turbine rotor whereby the electrical generator generates electrical power, rectifying the electrical power through at least one diode of the generator side converter in order to pre-charge the DC link to a DC voltage level, closing the grid circuit breaker when the DC voltage level is greater than a threshold level.
    Type: Grant
    Filed: October 28, 2014
    Date of Patent: August 30, 2016
    Assignee: Vestas Wind Systems AS
    Inventors: Weifu Yu, Anshuman Tripathi, Ravi Kandasamy
  • Patent number: 9353732
    Abstract: According to a method of the present invention, a method of operating a wind turbine comprising a power generator, a generator side converter connected to the power generator, a line side converter connected to a power grid through power components, and a DC-link connected between the generator side converter and the line side converter is provided, the method comprising: monitoring the grid voltages on the power grid for overvoltage events; if an overvoltage event is detected, operating the line side converter in an overmodulation range for at least a part of the duration of the overvoltage event.
    Type: Grant
    Filed: December 20, 2011
    Date of Patent: May 31, 2016
    Assignee: Vestas Wind Systems A/S
    Inventors: Amit Kumar Gupta, Anshuman Tripathi
  • Publication number: 20160114692
    Abstract: According to various embodiments, a battery charging device may be provided. The battery charging device may include: a first determination circuit configured to determine a state of a first battery of an electric vehicle; a second determination circuit configured to determine a state of a second battery of the electric vehicle; a first charging circuit configured to charge the first battery based on the determined condition of the first battery; and a second charging circuit configured to charge the second battery based on the determined condition of the second battery.
    Type: Application
    Filed: June 6, 2014
    Publication date: April 28, 2016
    Inventors: Anshuman Tripathi, Jyothi Nirupam
  • Patent number: 9325268
    Abstract: A power dissipating arrangement for dissipating power from a generator in a wind turbine is provided. The generator comprises a plurality of output terminals corresponding to a multi-phase output. The power dissipating arrangement comprises a plurality of dissipating units, a plurality of semiconductor switches, a trigger circuit for switching the semiconductor switches and a control unit for controlling the operation of the trigger circuit, thereby controlling the switching of the semiconductor switches. Each dissipating unit includes a first terminal and a second terminal. The first terminal of each dissipating unit is coupled to each output terminal of the generator. Each semiconductor switch includes a first terminal anode, a second terminal and a gate terminal.
    Type: Grant
    Filed: July 24, 2012
    Date of Patent: April 26, 2016
    Assignee: Vestas Wind Systems A/S
    Inventors: Ove Styhm, Anshuman Tripathi, Amit Kumar Gupta