公开(公告)号：US12105754B2

公开(公告)日：2024-10-01

申请号：US18406840

申请日：2024-01-08

Applicant: Gracenote, Inc.

Inventor： Zafar Rafii ,  Prem Seetharaman

IPC: G06F16/68 ,  G06F16/61 ,  G06F17/14 ,  G10L25/27 ,  G10L25/51

CPC classification number: G06F16/686 ,  G06F16/61 ,  G06F17/14 ,  G10L25/27 ,  G10L25/51

Abstract: Example systems and methods are audio identification based on data structure are disclosed. An example apparatus includes memory, and one or more processors to execute instructions to execute a constant Q transform on query time slices of query audio, binarize the constant Q transformed query time slices, execute a two-dimensional Fourier transform on query time windows within the binarized and constant Q transformed query time slices to generate two-dimensional Fourier transforms of the query time windows, sequentially order the two-dimensional Fourier transforms in a query data structure, and identify the query audio as a cover rendition of reference audio based on a comparison between the query data structure and a reference data structure associated with the reference audio.

公开(公告)号：US20210034665A1

公开(公告)日：2021-02-04

申请号：US17065479

申请日：2020-10-07

Applicant: Gracenote, Inc.

Inventor： Markus K. Cremer ,  Zafar Rafii ,  Robert Coover ,  Prem Seetharaman

IPC: G06F16/683

Abstract: Example systems and methods for automated cover song identification are disclosed. An example apparatus includes memory, and one or more processors to execute instructions to identify query audio from a content source based on a search query using rights metadata associated with the query audio, execute a constant Q transform on query time slices of the query audio, binarize the constant Q transformed query time slices, execute a two-dimensional Fourier transform on query time windows within the binarized and constant Q transformed query time slices to generate two-dimensional Fourier transforms of the query time windows, generate a query data structure based on a sequential order of the two-dimensional Fourier transforms, select a subset including reference audio of a reference database based on the rights metadata, and identify the query audio as a cover rendition of the reference audio based on a comparison between the query and reference data structures.

公开(公告)号：US11461390B2

公开(公告)日：2022-10-04

申请号：US17065479

申请日：2020-10-07

Applicant: Gracenote, Inc.

Inventor： Markus K. Cremer ,  Zafar Rafii ,  Robert Coover ,  Prem Seetharaman

IPC: G06F16/683 ,  G06Q50/18

Abstract: Example systems and methods for automated cover song identification are disclosed. An example apparatus includes memory, and one or more processors to execute instructions to identify query audio from a content source based on a search query using rights metadata associated with the query audio, execute a constant Q transform on query time slices of the query audio, binarize the constant Q transformed query time slices, execute a two-dimensional Fourier transform on query time windows within the binarized and constant Q transformed query time slices to generate two-dimensional Fourier transforms of the query time windows, generate a query data structure based on a sequential order of the two-dimensional Fourier transforms, select a subset including reference audio of a reference database based on the rights metadata, and identify the query audio as a cover rendition of the reference audio based on a comparison between the query and reference data structures.

公开(公告)号：US20200342024A1

公开(公告)日：2020-10-29

申请号：US16927577

申请日：2020-07-13

Applicant: Gracenote, Inc.

Inventor： Zafar Rafii ,  Prem Seetharaman

IPC: G06F16/68 ,  G06F17/14 ,  G10L25/27 ,  G10L25/51 ,  G06F16/61

Abstract: Example systems and methods are audio identification based on data structure are disclosed. An example apparatus includes memory, and one or more processors to execute instructions to execute a constant Q transform on query time slices of query audio, binarize the constant Q transformed query time slices, execute a two-dimensional Fourier transform on query time windows within the binarized and constant Q transformed query time slices to generate two-dimensional Fourier transforms of the query time windows, sequentially order the two-dimensional Fourier transforms in a query data structure, and identify the query audio as a cover rendition of reference audio based on a comparison between the query data structure and a reference data structure associated with the reference audio.

公开(公告)号：US10803119B2

公开(公告)日：2020-10-13

申请号：US15698557

申请日：2017-09-07

Applicant: Gracenote, Inc.

Inventor： Markus K. Cremer ,  Zafar Rafii ,  Robert Coover ,  Prem Seetharaman

IPC: G06F16/30 ,  G06F16/683 ,  G06Q50/18

Abstract: Example systems and methods represent audio using a sequence of two-dimensional (2D) Fourier transforms (2DFTs), and such a sequence may be used by a specially configured machine to perform audio identification, such as for automated cover song identification. Such systems and methods are robust to timbral changes, time skews, and pitch skews that occur in cover songs found in content repositories. The systems and methods allow copyright holders to search the content repositories for unlicensed cover song.

公开(公告)号：US11907288B2

公开(公告)日：2024-02-20

申请号：US16927577

申请日：2020-07-13

Applicant: Gracenote, Inc.

Inventor： Zafar Rafii ,  Prem Seetharaman

IPC: G06F16/68 ,  G06F17/14 ,  G10L25/27 ,  G10L25/51 ,  G06F16/61

CPC classification number: G06F16/686 ,  G06F16/61 ,  G06F17/14 ,  G10L25/27 ,  G10L25/51

Abstract: Example systems and methods are audio identification based on data structure are disclosed. An example apparatus includes memory, and one or more processors to execute instructions to execute a constant Q transform on query time slices of query audio, binarize the constant Q transformed query time slices, execute a two-dimensional Fourier transform on query time windows within the binarized and constant Q transformed query time slices to generate two-dimensional Fourier transforms of the query time windows, sequentially order the two-dimensional Fourier transforms in a query data structure, and identify the query audio as a cover rendition of reference audio based on a comparison between the query data structure and a reference data structure associated with the reference audio.

公开(公告)号：US20230008776A1

公开(公告)日：2023-01-12

申请号：US17946915

申请日：2022-09-16

Applicant: Gracenote, Inc.

Inventor： Markus K. Cremer ,  Zafar Rafii ,  Robert Coover ,  Prem Seetharaman

IPC: G06F16/683

Abstract: Example systems and methods for automated cover song identification are disclosed. An example apparatus includes at least one memory, machine-readable instructions, and one or more processors to execute the machine-readable instructions to at least execute a constant Q transform on time slices of first audio data to output constant Q transformed time slices, binarize the constant Q transformed time slices to output binarized and constant Q transformed time slices, execute a two-dimensional Fourier transform on time windows within the binarized and constant Q transformed time slices to output two-dimensional Fourier transforms of the time windows, generate a reference data structure based on a sequential order of the two-dimensional Fourier transforms, store the reference data structure in a database, and identify a query data structure associated with query audio data as a cover rendition of the audio data based on a comparison of the query and reference data structures.

公开(公告)号：US20180189390A1

公开(公告)日：2018-07-05

申请号：US15698557

申请日：2017-09-07

Applicant: Gracenote, Inc.

Inventor： Markus K. Cremer ,  Zafar Rafii ,  Robert Coover ,  Prem Seetharaman

IPC: G06F17/30

CPC classification number: G06F16/683 ,  G06Q50/184

Abstract: Example systems and methods represent audio using a sequence of two-dimensional (2D) Fourier transforms (2DFTs), and such a sequence may be used by a specially configured machine to perform audio identification, such as for automated cover song identification. Such systems and methods are robust to timbral changes, time skews, and pitch skews that occur in cover songs found in content repositories. The systems and methods allow copyright holders to search the content repositories for unlicensed cover song.

公开(公告)号：US20240427819A1

公开(公告)日：2024-12-26

申请号：US18824127

申请日：2024-09-04

Applicant: Gracenote, Inc.

Inventor： Zafar Rafii ,  Prem Seetharaman

IPC: G06F16/68 ,  G06F16/61 ,  G06F17/14 ,  G10L25/27 ,  G10L25/51

Abstract: Example systems and methods are audio identification based on data structure are disclosed. An example apparatus includes memory, and one or more processors to execute instructions to execute a constant Q transform on query time slices of query audio, binarize the constant Q transformed query time slices, execute a two-dimensional Fourier transform on query time windows within the binarized and constant Q transformed query time slices to generate two-dimensional Fourier transforms of the query time windows, sequentially order the two-dimensional Fourier transforms in a query data structure, and identify the query audio as a cover rendition of reference audio based on a comparison between the query data structure and a reference data structure associated with the reference audio.

公开(公告)号：US20240394304A1

公开(公告)日：2024-11-28

申请号：US18790730

申请日：2024-07-31

Applicant: Gracenote, Inc.

Inventor： Markus K. Cremer ,  Zafar Rafii ,  Robert Coover ,  Prem Seetharaman

IPC: G06F16/683 ,  G06Q50/18

Abstract: Example systems and methods for automated cover song identification are disclosed. An example apparatus includes at least one memory, machine-readable instructions, and one or more processors to execute the machine-readable instructions to at least execute a constant Q transform on time slices of first audio data to output constant Q transformed time slices, binarize the constant Q transformed time slices to output binarized and constant Q transformed time slices, execute a two-dimensional Fourier transform on time windows within the binarized and constant Q transformed time slices to output two-dimensional Fourier transforms of the time windows, generate a reference data structure based on a sequential order of the two-dimensional Fourier transforms, store the reference data structure in a database, and identify a query data structure associated with query audio data as a cover rendition of the audio data based on a comparison of the query and reference data structures.