-
公开(公告)号：US20250087232A1
公开(公告)日：2025-03-13
申请号：US18956913
申请日：2024-11-22
Applicant: Spotify AB
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.
-
公开(公告)号：US11862191B2
公开(公告)日：2024-01-02
申请号：US17135127
申请日：2020-12-28
Applicant: Spotify AB
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.
-
公开(公告)号：US20210256995A1
公开(公告)日：2021-08-19
申请号：US17135127
申请日：2020-12-28
Applicant: Spotify AB
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.
-
公开(公告)号：US11003419B2
公开(公告)日：2021-05-11
申请号：US16421590
申请日：2019-05-24
Applicant: Spotify AB
Inventor： Philip Glenny Edmonds , Matthew Joseph Kane , Joshua Pham , Eder G. Bastos , Marcus Daniel Better , Adithya Kalyan Tammavarapu , Amilcar Andrade Garcia , Chen Ye Li , Adam Jonathan Shonkoff , Aaron Paul Harmon , Christopher Phair , Ching Chuan Sung
IPC: G06F3/16 , G06F16/435 , G06F16/438 , G06F16/432 , G06F3/0482
Abstract: A system for refinement of a voice query interpretation interprets a voice query received at a voice-enabled device to identify commands responsive to the voice query for execution at the voice-enabled device, and enables refinement of the interpretation of the voice query through a graphical user interface generated and displayed at a GUI-capable device. The graphical user interface includes a set of selectable options relating to the voice query and identifying a refinement of the interpretation of the voice query to enable control and/or adjustment of commands to be executed by the voice-enabled device. For example, if one of the selectable options is selected, then a command associated with the selected option is identified and executed by the voice-enabled device.
-
公开(公告)号：US12079541B2
公开(公告)日：2024-09-03
申请号：US17833475
申请日：2022-06-06
Applicant: Spotify AB
Inventor： Philip Glenny Edmonds , Matthew Joseph Kane , Joshua Pham , Eder G. Bastos , Marcus Daniel Better , Adithya Kalyan Tammavarapu , Amilcar Andrade Garcia , Chen Ye Li , Adam Jonathan Shonkoff , Aaron Paul Harmon , Christopher Phair , Ching Chuan Sung
IPC: G06F3/048 , G06F3/0482 , G06F3/16 , G06F16/432 , G06F16/435 , G06F16/438
CPC classification number: G06F3/167 , G06F3/0482 , G06F16/433 , G06F16/435 , G06F16/438
Abstract: A system for refinement of a voice query interpretation interprets a voice query received at a voice-enabled device to identify commands responsive to the voice query for execution at the voice-enabled device, and enables refinement of the interpretation of the voice query through a graphical user interface generated and displayed at a GUI-capable device. The graphical user interface includes a set of selectable options relating to the voice query and identifying a refinement of the interpretation of the voice query to enable control and/or adjustment of commands to be executed by the voice-enabled device. For example, if one of the selectable options is selected, then a command associated with the selected option is identified and executed by the voice-enabled device.
-
Patent Agency Ranking
公开(公告)号：US11568256B2
公开(公告)日：2023-01-31
申请号：US17205296
申请日：2021-03-18
Applicant: Spotify AB
Inventor： Andreas Simon Thore Jansson , Angus William Sackfield , Ching Chuan Sung , Rachel M. Bittner
IPC: G06F15/00 , G10L25/00 , G06N3/08 , G06K9/62 , G06N3/04 , G10H1/00 , G10L21/0272 , G10L21/028
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, Θ). The audio signal includes one or more of vocal content and/or musical instrument content, and each output f(X, Θ) corresponds to a respective one of the different content types. The method also comprises comparing individual outputs f(X, Θ) of the neural network system to corresponding target signals. For each compared output f(X, Θ), at least one parameter of the system is adjusted to reduce a result of the comparing performed for the output f(X, Θ), 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.
-
公开(公告)号：US10923141B2
公开(公告)日：2021-02-16
申请号：US16055870
申请日：2018-08-06
Applicant: Spotify AB
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.
-
公开(公告)号：US20200043516A1
公开(公告)日：2020-02-06
申请号：US16055870
申请日：2018-08-06
Applicant: Spotify AB
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.
-
公开(公告)号：US20200042879A1
公开(公告)日：2020-02-06
申请号：US16521756
申请日：2019-07-25
Applicant: Spotify AB
Inventor： Andreas Simon Thore Jansson , Angus William Sackfield , Ching Chuan Sung , Rachel M. Bittner
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, Θ). The audio signal includes one or more of vocal content and/or musical instrument content, and each output f(X, Θ) corresponds to a respective one of the different content types. The method also comprises comparing individual outputs f(X, Θ) of the neural network system to corresponding target signals. For each compared output f(X, Θ), at least one parameter of the system is adjusted to reduce a result of the comparing performed for the output f(X, Θ), 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.
-
公开(公告)号：US20240161770A1
公开(公告)日：2024-05-16
申请号：US18514289
申请日：2023-11-20
Applicant: Spotify AB
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.
-
-
-
-
-
-
-
-
-
Search Results
23
records
(took 0.018 seconds)
