Patents by Inventor Andreas Simon Thore Jansson

Andreas Simon Thore Jansson 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: 20250087232
    Abstract: A system, method and computer product for training a neural network system. The method comprises applying an audio signal to the neural network system, the audio signal including a vocal component and a non-vocal component. The method also comprises comparing an output of the neural network system to a target signal, and adjusting at least one parameter of the neural network system to reduce a result of the comparing, for training the neural network system to estimate one of the vocal component and the non-vocal component. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate vocal or instrumental components of an audio signal, depending on which type of component the system is trained to estimate.
    Type: Application
    Filed: November 22, 2024
    Publication date: March 13, 2025
    Inventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung
  • Patent number: 12183363
    Abstract: A system, method and computer product for training a neural network system. The method comprises applying an audio signal to the neural network system, the audio signal including a vocal component and a non-vocal component. The method also comprises comparing an output of the neural network system to a target signal, and adjusting at least one parameter of the neural network system to reduce a result of the comparing, for training the neural network system to estimate one of the vocal component and the non-vocal component. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate vocal or instrumental components of an audio signal, depending on which type of component the system is trained to estimate.
    Type: Grant
    Filed: November 20, 2023
    Date of Patent: December 31, 2024
    Assignee: Spotify AB
    Inventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung
  • Patent number: 12175957
    Abstract: A system, method and computer product for training a neural network system. The method comprises inputting an audio signal to the system to generate plural outputs f(X, ?). The audio signal includes one or more of vocal content and/or musical instrument content, and each output f(X, ?) corresponds to a respective one of the different content types. The method also comprises comparing individual outputs f(X, ?) of the neural network system to corresponding target signals. For each compared output f(X, ?), at least one parameter of the system is adjusted to reduce a result of the comparing performed for the output f(X, ?), to train the system to estimate the different content types. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate various different types of vocal and/or instrument components of an audio signal, depending on which type of component(s) the system is trained to estimate.
    Type: Grant
    Filed: December 23, 2022
    Date of Patent: December 24, 2024
    Assignee: Spotify AB
    Inventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung, Rachel M. Bittner
  • Publication number: 20240161770
    Abstract: A system, method and computer product for training a neural network system. The method comprises applying an audio signal to the neural network system, the audio signal including a vocal component and a non-vocal component. The method also comprises comparing an output of the neural network system to a target signal, and adjusting at least one parameter of the neural network system to reduce a result of the comparing, for training the neural network system to estimate one of the vocal component and the non-vocal component. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate vocal or instrumental components of an audio signal, depending on which type of component the system is trained to estimate.
    Type: Application
    Filed: November 20, 2023
    Publication date: May 16, 2024
    Applicant: Spotify AB
    Inventors: Andreas Simon Thore JANSSON, Angus William Sackfield, Ching Chuan Sung
  • Patent number: 11862191
    Abstract: A system, method and computer product for training a neural network system. The method comprises applying an audio signal to the neural network system, the audio signal including a vocal component and a non-vocal component. The method also comprises comparing an output of the neural network system to a target signal, and adjusting at least one parameter of the neural network system to reduce a result of the comparing, for training the neural network system to estimate one of the vocal component and the non-vocal component. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate vocal or instrumental components of an audio signal, depending on which type of component the system is trained to estimate.
    Type: Grant
    Filed: December 28, 2020
    Date of Patent: January 2, 2024
    Assignee: Spotify AB
    Inventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung
  • Publication number: 20230125789
    Abstract: A system, method and computer product for training a neural network system. The method comprises inputting an audio signal to the system to generate plural outputs f(X, ?). The audio signal includes one or more of vocal content and/or musical instrument content, and each output f(X, ?) corresponds to a respective one of the different content types. The method also comprises comparing individual outputs f(X, ?) of the neural network system to corresponding target signals. For each compared output f(X, ?), at least one parameter of the system is adjusted to reduce a result of the comparing performed for the output f(X, ?), to train the system to estimate the different content types. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate various different types of vocal and/or instrument components of an audio signal, depending on which type of component(s) the system is trained to estimate.
    Type: Application
    Filed: December 23, 2022
    Publication date: April 27, 2023
    Applicant: Spotify AB
    Inventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung, Rachel M. Bittner
  • Patent number: 11568256
    Abstract: A system, method and computer product for training a neural network system. The method comprises inputting an audio signal to the system to generate plural outputs f(X, ?). The audio signal includes one or more of vocal content and/or musical instrument content, and each output f(X, ?) corresponds to a respective one of the different content types. The method also comprises comparing individual outputs f(X, ?) of the neural network system to corresponding target signals. For each compared output f(X, ?), at least one parameter of the system is adjusted to reduce a result of the comparing performed for the output f(X, ?), to train the system to estimate the different content types. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate various different types of vocal and/or instrument components of an audio signal, depending on which type of component(s) the system is trained to estimate.
    Type: Grant
    Filed: March 18, 2021
    Date of Patent: January 31, 2023
    Assignee: Spotify AB
    Inventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung, Rachel M. Bittner
  • Publication number: 20210279588
    Abstract: A system, method and computer product for training a neural network system. The method comprises inputting an audio signal to the system to generate plural outputs f(X, ?). The audio signal includes one or more of vocal content and/or musical instrument content, and each output f(X, ?) corresponds to a respective one of the different content types. The method also comprises comparing individual outputs f(X, ?) of the neural network system to corresponding target signals. For each compared output f(X, ?), at least one parameter of the system is adjusted to reduce a result of the comparing performed for the output f(X, ?), to train the system to estimate the different content types. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate various different types of vocal and/or instrument components of an audio signal, depending on which type of component(s) the system is trained to estimate.
    Type: Application
    Filed: March 18, 2021
    Publication date: September 9, 2021
    Applicant: Spotify AB
    Inventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung, Rachel M. Bittner
  • Publication number: 20210256994
    Abstract: A system, method and computer product for training a neural network system. The method comprises applying an audio signal to the neural network system, the audio signal including a vocal component and a non-vocal component. The method also comprises comparing an output of the neural network system to a target signal, and adjusting at least one parameter of the neural network system to reduce a result of the comparing, for training the neural network system to estimate one of the vocal component and the non-vocal component. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate vocal or instrumental components of an audio signal, depending on which type of component the system is trained to estimate.
    Type: Application
    Filed: December 28, 2020
    Publication date: August 19, 2021
    Applicant: Spotify AB
    Inventors: Andreas Simon Thore JANSSON, Angus William Sackfield, Ching Chuan Sung
  • Publication number: 20210256995
    Abstract: A system, method and computer product for training a neural network system. The method comprises applying an audio signal to the neural network system, the audio signal including a vocal component and a non-vocal component. The method also comprises comparing an output of the neural network system to a target signal, and adjusting at least one parameter of the neural network system to reduce a result of the comparing, for training the neural network system to estimate one of the vocal component and the non-vocal component. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate vocal or instrumental components of an audio signal, depending on which type of component the system is trained to estimate.
    Type: Application
    Filed: December 28, 2020
    Publication date: August 19, 2021
    Inventors: Andreas Simon Thore JANSSON, Angus William Sackfield, Ching Chuan Sung
  • Patent number: 10991385
    Abstract: A system, method and computer product for estimating a component of a provided audio signal. The method comprises converting the provided audio signal to an image, processing the image with a neural network trained to estimate one of vocal content and instrumental content, and storing a spectral mask output from the neural network as a result of the image being processed by the neural network. The neural network is a U-Net. The method also comprises providing the spectral mask to a client media playback device, which applies the spectral mask to a spectrogram of the provided audio signal, to provide a masked spectrogram. The media playback device also transforms the masked spectrogram to an audio signal, and plays back that audio signal via an output user interface.
    Type: Grant
    Filed: October 19, 2018
    Date of Patent: April 27, 2021
    Assignee: Spotify AB
    Inventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung, David Rubinstein
  • Patent number: 10977555
    Abstract: A system, method and computer product for training a neural network system. The method comprises inputting an audio signal to the system to generate plural outputs f(X, ?). The audio signal includes one or more of vocal content and/or musical instrument content, and each output f(X, ?) corresponds to a respective one of the different content types. The method also comprises comparing individual outputs f(X, ?) of the neural network system to corresponding target signals. For each compared output f(X, ?), at least one parameter of the system is adjusted to reduce a result of the comparing performed for the output f(X, ?), to train the system to estimate the different content types. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate various different types of vocal and/or instrument components of an audio signal, depending on which type of component(s) the system is trained to estimate.
    Type: Grant
    Filed: July 25, 2019
    Date of Patent: April 13, 2021
    Assignee: Spotify AB
    Inventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung, Rachel M. Bittner
  • Patent number: 10923142
    Abstract: A system, method and computer product for training a neural network system. The method comprises applying an audio signal to the neural network system, the audio signal including a vocal component and a non-vocal component. The method also comprises comparing an output of the neural network system to a target signal, and adjusting at least one parameter of the neural network system to reduce a result of the comparing, for training the neural network system to estimate one of the vocal component and the non-vocal component. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate vocal or instrumental components of an audio signal, depending on which type of component the system is trained to estimate.
    Type: Grant
    Filed: January 8, 2019
    Date of Patent: February 16, 2021
    Assignee: Spotify AB
    Inventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung
  • Patent number: 10923141
    Abstract: A system, method and computer product for training a neural network system. The method comprises applying an audio signal to the neural network system, the audio signal including a vocal component and a non-vocal component. The method also comprises comparing an output of the neural network system to a target signal, and adjusting at least one parameter of the neural network system to reduce a result of the comparing, for training the neural network system to estimate one of the vocal component and the non-vocal component. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate vocal or instrumental components of an audio signal, depending on which type of component the system is trained to estimate.
    Type: Grant
    Filed: August 6, 2018
    Date of Patent: February 16, 2021
    Assignee: Spotify AB
    Inventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung
  • Publication number: 20200043517
    Abstract: A system, method and computer product for estimating a component of a provided audio signal. The method comprises converting the provided audio signal to an image, processing the image with a neural network trained to estimate one of vocal content and instrumental content, and storing a spectral mask output from the neural network as a result of the image being processed by the neural network. The neural network is a U-Net. The method also comprises providing the spectral mask to a client media playback device, which applies the spectral mask to a spectrogram of the provided audio signal, to provide a masked spectrogram. The media playback device also transforms the masked spectrogram to an audio signal, and plays back that audio signal via an output user interface.
    Type: Application
    Filed: October 19, 2018
    Publication date: February 6, 2020
    Applicant: Spotify AB
    Inventor: Andreas Simon Thore JANSSON
  • Publication number: 20200043518
    Abstract: A system, method and computer product for training a neural network system. The method comprises applying an audio signal to the neural network system, the audio signal including a vocal component and a non-vocal component. The method also comprises comparing an output of the neural network system to a target signal, and adjusting at least one parameter of the neural network system to reduce a result of the comparing, for training the neural network system to estimate one of the vocal component and the non-vocal component. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate vocal or instrumental components of an audio signal, depending on which type of component the system is trained to estimate.
    Type: Application
    Filed: January 8, 2019
    Publication date: February 6, 2020
    Applicant: Spotify AB
    Inventors: Andreas Simon Thore JANSSON, Angus William Sackfield, Ching Chuan Sung
  • Publication number: 20200043516
    Abstract: A system, method and computer product for training a neural network system. The method comprises applying an audio signal to the neural network system, the audio signal including a vocal component and a non-vocal component. The method also comprises comparing an output of the neural network system to a target signal, and adjusting at least one parameter of the neural network system to reduce a result of the comparing, for training the neural network system to estimate one of the vocal component and the non-vocal component. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate vocal or instrumental components of an audio signal, depending on which type of component the system is trained to estimate.
    Type: Application
    Filed: August 6, 2018
    Publication date: February 6, 2020
    Applicant: Spotify AB
    Inventors: Andreas Simon Thore JANSSON, Angus William Sackfield, Ching Chuan Sung
  • Publication number: 20200042879
    Abstract: A system, method and computer product for training a neural network system. The method comprises inputting an audio signal to the system to generate plural outputs f(X, ?). The audio signal includes one or more of vocal content and/or musical instrument content, and each output f(X, ?) corresponds to a respective one of the different content types. The method also comprises comparing individual outputs f(X, ?) of the neural network system to corresponding target signals. For each compared output f(X, ?), at least one parameter of the system is adjusted to reduce a result of the comparing performed for the output f(X, ?), to train the system to estimate the different content types. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate various different types of vocal and/or instrument components of an audio signal, depending on which type of component(s) the system is trained to estimate.
    Type: Application
    Filed: July 25, 2019
    Publication date: February 6, 2020
    Inventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung, Rachel M. Bittner