Patents by Inventor Niranjan Subrahmanya

Niranjan Subrahmanya 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: 20240355324
    Abstract: Techniques are described herein for improving performance of machine learning model(s) and thresholds utilized in determining whether automated assistant function(s) are to be initiated. A method includes: receiving, via one or more microphones of a client device, audio data that captures a spoken utterance of a user; processing the audio data using a machine learning model to generate a predicted output that indicates a probability of one or more hotwords being present in the audio data; determining that the predicted output satisfies a secondary threshold that is less indicative of the one or more hotwords being present in the audio data than is a primary threshold; in response to determining that the predicted output satisfies the secondary threshold, prompting the user to indicate whether or not the spoken utterance includes a hotword; receiving, from the user, a response to the prompting; and adjusting the primary threshold based on the response.
    Type: Application
    Filed: July 1, 2024
    Publication date: October 24, 2024
    Inventors: Aleks Kracun, Niranjan Subrahmanya, Aishanee Shah
  • Patent number: 12027160
    Abstract: Techniques are described herein for improving performance of machine learning model(s) and thresholds utilized in determining whether automated assistant function(s) are to be initiated. A method includes: receiving, via one or more microphones of a client device, audio data that captures a spoken utterance of a user; processing the audio data using a machine learning model to generate a predicted output that indicates a probability of one or more hotwords being present in the audio data; determining that the predicted output satisfies a secondary threshold that is less indicative of the one or more hotwords being present in the audio data than is a primary threshold; in response to determining that the predicted output satisfies the secondary threshold, prompting the user to indicate whether or not the spoken utterance includes a hotword; receiving, from the user, a response to the prompting; and adjusting the primary threshold based on the response.
    Type: Grant
    Filed: December 5, 2022
    Date of Patent: July 2, 2024
    Assignee: GOOGLE LLC
    Inventors: Aleks Kracun, Niranjan Subrahmanya, Aishanee Shah
  • Patent number: 12027162
    Abstract: Teacher-student learning can be used to train a keyword spotting (KWS) model using augmented training instance(s). Various implementations include aggressively augmenting (e.g., using spectral augmentation) base audio data to generate augmented audio data, where one or more portions of the base instance of audio data can be masked in the augmented instance of audio data (e.g., one or more time frames can be masked, one or more frequencies can be masked, etc.). Many implementations include processing augmented audio data using a KWS teacher model to generate a soft label, and processing the augmented audio data using a KWS student model to generate predicted output. One or more portions of the KWS student model can be updated based on a comparison of the soft label and the generated predicted output.
    Type: Grant
    Filed: March 3, 2021
    Date of Patent: July 2, 2024
    Assignee: GOOGLE LLC
    Inventors: Hyun Jin Park, Pai Zhu, Ignacio Lopez Moreno, Niranjan Subrahmanya
  • Publication number: 20230101572
    Abstract: Techniques are described herein for improving performance of machine learning model(s) and thresholds utilized in determining whether automated assistant function(s) are to be initiated. A method includes: receiving, via one or more microphones of a client device, audio data that captures a spoken utterance of a user; processing the audio data using a machine learning model to generate a predicted output that indicates a probability of one or more hotwords being present in the audio data; determining that the predicted output satisfies a secondary threshold that is less indicative of the one or more hotwords being present in the audio data than is a primary threshold; in response to determining that the predicted output satisfies the secondary threshold, prompting the user to indicate whether or not the spoken utterance includes a hotword; receiving, from the user, a response to the prompting; and adjusting the primary threshold based on the response.
    Type: Application
    Filed: December 5, 2022
    Publication date: March 30, 2023
    Inventors: Aleks Kracun, Niranjan Subrahmanya, Aishanee Shah
  • Patent number: 11521604
    Abstract: Techniques are described herein for improving performance of machine learning model(s) and thresholds utilized in determining whether automated assistant function(s) are to be initiated. A method includes: receiving, via one or more microphones of a client device, audio data that captures a spoken utterance of a user; processing the audio data using a machine learning model to generate a predicted output that indicates a probability of one or more hotwords being present in the audio data; determining that the predicted output satisfies a secondary threshold that is less indicative of the one or more hotwords being present in the audio data than is a primary threshold; in response to determining that the predicted output satisfies the secondary threshold, prompting the user to indicate whether or not the spoken utterance includes a hotword; receiving, from the user, a response to the prompting; and adjusting the primary threshold based on the response.
    Type: Grant
    Filed: September 3, 2020
    Date of Patent: December 6, 2022
    Assignee: GOOGLE LLC
    Inventors: Aleks Kracun, Niranjan Subrahmanya, Aishanee Shah
  • Publication number: 20220284891
    Abstract: Teacher-student learning can be used to train a keyword spotting (KWS) model using augmented training instance(s). Various implementations include aggressively augmenting (e.g., using spectral augmentation) base audio data to generate augmented audio data, where one or more portions of the base instance of audio data can be masked in the augmented instance of audio data (e.g., one or more time frames can be masked, one or more frequencies can be masked, etc.). Many implementations include processing augmented audio data using a KWS teacher model to generate a soft label, and processing the augmented audio data using a KWS student model to generate predicted output. One or more portions of the KWS student model can be updated based on a comparison of the soft label and the generated predicted output.
    Type: Application
    Filed: March 3, 2021
    Publication date: September 8, 2022
    Inventors: Hyun Jin Park, Pai Zhu, Ignacio Lopez Moreno, Niranjan Subrahmanya
  • Publication number: 20220068268
    Abstract: Techniques are described herein for improving performance of machine learning model(s) and thresholds utilized in determining whether automated assistant function(s) are to be initiated. A method includes: receiving, via one or more microphones of a client device, audio data that captures a spoken utterance of a user; processing the audio data using a machine learning model to generate a predicted output that indicates a probability of one or more hotwords being present in the audio data; determining that the predicted output satisfies a secondary threshold that is less indicative of the one or more hotwords being present in the audio data than is a primary threshold; in response to determining that the predicted output satisfies the secondary threshold, prompting the user to indicate whether or not the spoken utterance includes a hotword; receiving, from the user, a response to the prompting; and adjusting the primary threshold based on the response.
    Type: Application
    Filed: September 3, 2020
    Publication date: March 3, 2022
    Inventors: Aleks Kracun, Niranjan Subrahmanya, Aishanee Shah