公开(公告)号：US20230326479A1

公开(公告)日：2023-10-12

申请号：US18335618

申请日：2023-06-15

Applicant: Gracenote, Inc.

Inventor： Alexander Berrian ,  Todd J. Hodges ,  Robert Coover ,  Matthew James Wilkinson ,  Zafar Rafii

IPC: G10L25/54 ,  G10L25/27 ,  G10L25/72 ,  G10L19/018

CPC classification number: G10L25/54 ,  G10L25/27 ,  G10L25/72 ,  G10L19/018 ,  G10L25/18

Abstract: A method implemented by a computing system comprises generating, by the computing system, a fingerprint comprising a plurality of bin samples associated with audio content. Each bin sample is specified within a frame of the fingerprint and is associated with one of a plurality of non-overlapping frequency ranges and a value indicative of a magnitude of energy associated with a corresponding frequency range. The computing system removes, from the fingerprint, a plurality of bin samples associated with a frequency sweep in the audio content.

公开(公告)号：US20220208214A1

公开(公告)日：2022-06-30

申请号：US17315820

申请日：2021-05-10

Applicant: Gracenote, Inc.

Inventor： Alexander Berrian ,  Todd J. Hodges ,  Robert Coover ,  Matthew James Wilkinson ,  Zafar Rafii

IPC: G10L25/54 ,  G10L19/018 ,  G10L25/72 ,  G10L25/27

Abstract: A method implemented by a computing system comprises generating, by the computing system, a fingerprint comprising a plurality of bin samples associated with audio content. Each bin sample is specified within a frame of the fingerprint and is associated with one of a plurality of non-overlapping frequency ranges and a value indicative of a magnitude of energy associated with a corresponding frequency range. The computing system removes, from the fingerprint, a plurality of bin samples associated with a frequency sweep in the audio content.

公开(公告)号：US20210157838A1

公开(公告)日：2021-05-27

申请号：US16696874

申请日：2019-11-26

Applicant: Gracenote, Inc.

Inventor： Alexander Berrian ,  Matthew James Wilkinson ,  Robert Coover

IPC: G06F16/683 ,  G10L25/21 ,  G10L25/51

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to fingerprint an audio signal via exponential normalization. An example apparatus includes an audio segmenter to divide an audio signal into a plurality of audio segments including a first audio segment and a second audio segment, the first audio segment including a first time-frequency bin, the second audio segment including a second time-frequency bin, a mean calculator to determine a first exponential mean value associated with the first time frequency bin based on a first magnitude of the audio signal associated with the first time frequency bin and a second exponential mean value associated with the second time frequency bin based on a second magnitude of the audio signal associated with the second time frequency bin and the first exponential mean value. The example apparatus further includes a bin normalizer to normalize the first time-frequency bin based on the second exponential mean value and a fingerprint generator to generate a fingerprint of the audio signal based on the normalized first time-frequency bins.

公开(公告)号：US12235896B2

公开(公告)日：2025-02-25

申请号：US18674678

申请日：2024-05-24

Applicant: Gracenote, Inc.

Inventor： Alexander Berrian ,  Matthew James Wilkinson ,  Robert Coover

IPC: G10L25/51 ,  G06F16/683 ,  G10L25/21

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to fingerprint an audio signal via exponential normalization. An example apparatus includes an audio segmenter to divide an audio signal into a plurality of audio segments including a first audio segment and a second audio segment, the first audio segment including a first time-frequency bin, the second audio segment including a second time-frequency bin, a mean calculator to determine a first exponential mean value associated with the first time frequency bin based on a first magnitude of the audio signal associated with the first time frequency bin and a second exponential mean value associated with the second time frequency bin based on a second magnitude of the audio signal associated with the second time frequency bin and the first exponential mean value. The example apparatus further includes a bin normalizer to normalize the first time-frequency bin based on the second exponential mean value and a fingerprint generator to generate a fingerprint of the audio signal based on the normalized first time-frequency bins.

公开(公告)号：US12094486B2

公开(公告)日：2024-09-17

申请号：US18335618

申请日：2023-06-15

Applicant: Gracenote, Inc.

Inventor： Alexander Berrian ,  Todd J. Hodges ,  Robert Coover ,  Matthew James Wilkinson ,  Zafar Rafii

IPC: G10L19/018 ,  G10L25/27 ,  G10L25/54 ,  G10L25/72 ,  G10L19/028 ,  G10L25/18

CPC classification number: G10L25/54 ,  G10L19/018 ,  G10L25/27 ,  G10L25/72 ,  G10L19/028 ,  G10L25/18

Abstract: A method implemented by a computing system comprises generating, by the computing system, a fingerprint comprising a plurality of bin samples associated with audio content. Each bin sample is specified within a frame of the fingerprint and is associated with one of a plurality of non-overlapping frequency ranges and a value indicative of a magnitude of energy associated with a corresponding frequency range. The computing system removes, from the fingerprint, a plurality of bin samples associated with a frequency sweep in the audio content.

公开(公告)号：US20240395279A1

公开(公告)日：2024-11-28

申请号：US18790749

申请日：2024-07-31

Applicant: Gracenote, Inc.

Inventor： Alexander Berrian ,  Todd J. Hodges ,  Robert Coover ,  Matthew James Wilkinson ,  Zafar Rafii

IPC: G10L25/54 ,  G10L19/018 ,  G10L19/028 ,  G10L25/18 ,  G10L25/27 ,  G10L25/72

Abstract: A method implemented by a computing system comprises generating, by the computing system, a fingerprint comprising a plurality of bin samples associated with audio content. Each bin sample is specified within a frame of the fingerprint and is associated with one of a plurality of non-overlapping frequency ranges and a value indicative of a magnitude of energy associated with a corresponding frequency range. The computing system removes, from the fingerprint, a plurality of bin samples associated with a frequency sweep in the audio content.

公开(公告)号：US20240386051A1

公开(公告)日：2024-11-21

申请号：US18674678

申请日：2024-05-24

Applicant: Gracenote, Inc.

Inventor： Alexander Berrian ,  Matthew James Wilkinson ,  Robert Coover

IPC: G06F16/683 ,  G10L25/21 ,  G10L25/51

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to fingerprint an audio signal via exponential normalization. An example apparatus includes an audio segmenter to divide an audio signal into a plurality of audio segments including a first audio segment and a second audio segment, the first audio segment including a first time-frequency bin, the second audio segment including a second time-frequency bin, a mean calculator to determine a first exponential mean value associated with the first time frequency bin based on a first magnitude of the audio signal associated with the first time frequency bin and a second exponential mean value associated with the second time frequency bin based on a second magnitude of the audio signal associated with the second time frequency bin and the first exponential mean value. The example apparatus further includes a bin normalizer to normalize the first time-frequency bin based on the second exponential mean value and a fingerprint generator to generate a fingerprint of the audio signal based on the normalized first time-frequency bins.

公开(公告)号：US12032628B2

公开(公告)日：2024-07-09

申请号：US16696874

申请日：2019-11-26

Applicant: Gracenote, Inc.

Inventor： Alexander Berrian ,  Matthew James Wilkinson ,  Robert Coover

IPC: G10L25/51 ,  G06F16/683 ,  G10L25/21

CPC classification number: G06F16/683 ,  G10L25/21 ,  G10L25/51

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to fingerprint an audio signal via exponential normalization. An example apparatus includes an audio segmenter to divide an audio signal into a plurality of audio segments including a first audio segment and a second audio segment, the first audio segment including a first time-frequency bin, the second audio segment including a second time-frequency bin, a mean calculator to determine a first exponential mean value associated with the first time frequency bin based on a first magnitude of the audio signal associated with the first time frequency bin and a second exponential mean value associated with the second time frequency bin based on a second magnitude of the audio signal associated with the second time frequency bin and the first exponential mean value. The example apparatus further includes a bin normalizer to normalize the first time-frequency bin based on the second exponential mean value and a fingerprint generator to generate a fingerprint of the audio signal based on the normalized first time-frequency bins.

公开(公告)号：US11727953B2

公开(公告)日：2023-08-15

申请号：US17315820

申请日：2021-05-10

Applicant: Gracenote, Inc.

Inventor： Alexander Berrian ,  Todd J. Hodges ,  Robert Coover ,  Matthew James Wilkinson ,  Zafar Rafii

IPC: G10L19/018 ,  G10L25/54 ,  G10L25/27 ,  G10L25/72 ,  G10L25/18 ,  G10L19/028

CPC classification number: G10L25/54 ,  G10L19/018 ,  G10L25/27 ,  G10L25/72 ,  G10L19/028 ,  G10L25/18

Abstract: A method implemented by a computing system comprises generating, by the computing system, a fingerprint comprising a plurality of bin samples associated with audio content. Each bin sample is specified within a frame of the fingerprint and is associated with one of a plurality of non-overlapping frequency ranges and a value indicative of a magnitude of energy associated with a corresponding frequency range. The computing system removes, from the fingerprint, a plurality of bin samples associated with a frequency sweep in the audio content.