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: 20250087232Abstract: 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: ApplicationFiled: November 22, 2024Publication date: March 13, 2025Inventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung
-
Patent number: 12183363Abstract: 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: GrantFiled: November 20, 2023Date of Patent: December 31, 2024Assignee: Spotify ABInventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung
-
Patent number: 12175957Abstract: 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: GrantFiled: December 23, 2022Date of Patent: December 24, 2024Assignee: Spotify ABInventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung, Rachel M. Bittner
-
Publication number: 20240161770Abstract: 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: ApplicationFiled: November 20, 2023Publication date: May 16, 2024Applicant: Spotify ABInventors: Andreas Simon Thore JANSSON, Angus William Sackfield, Ching Chuan Sung
-
Patent number: 11862191Abstract: 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: GrantFiled: December 28, 2020Date of Patent: January 2, 2024Assignee: Spotify ABInventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung
-
Publication number: 20230125789Abstract: 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: ApplicationFiled: December 23, 2022Publication date: April 27, 2023Applicant: Spotify ABInventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung, Rachel M. Bittner
-
Patent number: 11568256Abstract: 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: GrantFiled: March 18, 2021Date of Patent: January 31, 2023Assignee: Spotify ABInventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung, Rachel M. Bittner
-
Publication number: 20210279588Abstract: 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: ApplicationFiled: March 18, 2021Publication date: September 9, 2021Applicant: Spotify ABInventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung, Rachel M. Bittner
-
Publication number: 20210256994Abstract: 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: ApplicationFiled: December 28, 2020Publication date: August 19, 2021Applicant: Spotify ABInventors: Andreas Simon Thore JANSSON, Angus William Sackfield, Ching Chuan Sung
-
Publication number: 20210256995Abstract: 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: ApplicationFiled: December 28, 2020Publication date: August 19, 2021Inventors: Andreas Simon Thore JANSSON, Angus William Sackfield, Ching Chuan Sung
-
Patent number: 10991385Abstract: 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: GrantFiled: October 19, 2018Date of Patent: April 27, 2021Assignee: Spotify ABInventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung, David Rubinstein
-
Patent number: 10977555Abstract: 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: GrantFiled: July 25, 2019Date of Patent: April 13, 2021Assignee: Spotify ABInventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung, Rachel M. Bittner
-
Patent number: 10923142Abstract: 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: GrantFiled: January 8, 2019Date of Patent: February 16, 2021Assignee: Spotify ABInventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung
-
Patent number: 10923141Abstract: 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: GrantFiled: August 6, 2018Date of Patent: February 16, 2021Assignee: Spotify ABInventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung
-
Publication number: 20200043517Abstract: 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: ApplicationFiled: October 19, 2018Publication date: February 6, 2020Applicant: Spotify ABInventor: Andreas Simon Thore JANSSON
-
Publication number: 20200043518Abstract: 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: ApplicationFiled: January 8, 2019Publication date: February 6, 2020Applicant: Spotify ABInventors: Andreas Simon Thore JANSSON, Angus William Sackfield, Ching Chuan Sung
-
Publication number: 20200043516Abstract: 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: ApplicationFiled: August 6, 2018Publication date: February 6, 2020Applicant: Spotify ABInventors: Andreas Simon Thore JANSSON, Angus William Sackfield, Ching Chuan Sung
-
Publication number: 20200042879Abstract: 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: ApplicationFiled: July 25, 2019Publication date: February 6, 2020Inventors: Andreas Simon Thore Jansson, Angus William Sackfield, Ching Chuan Sung, Rachel M. Bittner