公开(公告)号：US11568886B2

公开(公告)日：2023-01-31

申请号：US17202841

申请日：2021-03-16

Applicant: Spotify AB

Inventor： Juan José Bosch Vicente ,  François Pachet ,  Pierre Roy ,  Mathieu Ramona ,  Tristan Jehan

IPC: G10L25/51 ,  G06N3/04 ,  G06N3/08 ,  G10L25/30 ,  G06F16/632

Abstract: Methods, systems and computer program products are provided for determining acoustic feature vectors of query and target items in a first vector space, and mapping the acoustic feature vectors to a second vector space having a lower dimension. The distribution of vectors in the second vector space can then be used to identify items from the same songs, and/or items that are complementary. A mapping function is trained using a machine learning algorithm, such that complementary audio items are closer in the second vector space than the first, according to a given distance metric.

公开(公告)号：US20210090536A1

公开(公告)日：2021-03-25

申请号：US16575889

申请日：2019-09-19

Applicant: Spotify AB

Inventor： François Pachet ,  Pierre Roy ,  Mathieu Ramona ,  Tristan Jehan ,  Juan José Bosch Vicente

IPC: G10H1/00 ,  G06N20/00 ,  G06K9/62 ,  G06F16/635 ,  G06F16/632

Abstract: Methods, systems and computer program products are provided for identifying an audio stem. Audio stems (t1, . . . , tN) are stored on a stem database and songs (S1, . . . , SP) made with at least a subset of the plurality of the audio stems (t1, . . . , tN) are stored on a song database. At least partially composed song (S*) having a predetermined number of pre-selected stems (k) are received. In turn, a probability vector (or relevance value or ranking) is produced for each stem (t1, . . . , tN) to be complementary to the at least partially composed song (S*).

公开(公告)号：US11651758B2

公开(公告)日：2023-05-16

申请号：US17063347

申请日：2020-10-05

Applicant: Spotify AB

Inventor： François Pachet ,  Pierre Roy ,  Benoit Jean Carré

IPC: G10H1/00

CPC classification number: G10H1/0066 ,  G10H1/0025 ,  G10H2240/021 ,  G10H2240/056 ,  G10H2240/305

Abstract: An electronic device segments a first and second MIDI files into pluralities of source segments and target segments. For each of a plurality of consecutive pairs of first and second target segments, the electronic device identifies a first source segment corresponding to the first target segment of the consecutive pair and identifies a second source segment corresponding to the second target segment of the consecutive pair, where the first and second source segments are identified by determining that the first and second source segments are harmonically conformant to the corresponding first and second target segments, and determining that a transition between the first and second source segments is graphically conformant to a transition between a consecutive pair of source segments. The electronic device generates a third MIDI file using the identified first and second source segments for each of the plurality of consecutive pairs of first and second target segments.

公开(公告)号：US20210312941A1

公开(公告)日：2021-10-07

申请号：US17202841

申请日：2021-03-16

Applicant: Spotify AB

Inventor： Juan José Bosch Vicente ,  François Pachet ,  Pierre Roy ,  Mathieu Ramona ,  Tristan Jehan

IPC: G10L25/51 ,  G06F16/632 ,  G06N3/04 ,  G06N3/08 ,  G10L25/30

Abstract: Methods, systems and computer program products are provided for determining acoustic feature vectors of query and target items in a first vector space, and mapping the acoustic feature vectors to a second vector space having a lower dimension. The distribution of vectors in the second vector space can then be used to identify items from the same songs, and/or items that are complementary. A mapping function is trained using a machine learning algorithm, such that complementary audio items are closer in the second vector space than the first, according to a given distance metric.

公开(公告)号：US10997986B2

公开(公告)日：2021-05-04

申请号：US16575926

申请日：2019-09-19

Applicant: Spotify AB

Inventor： Juan José Bosch Vicente ,  François Pachet ,  Pierre Roy ,  Mathieu Ramona ,  Tristan Jehan

IPC: G10L25/51 ,  G10L25/30 ,  G06N3/08 ,  G06N3/04 ,  G06F16/632

Abstract: Methods, systems and computer program products are provided for determining acoustic feature vectors of query and target items in a first vector space, and mapping the acoustic feature vectors to a second vector space having a lower dimension. The distribution of vectors in the second vector space can then be used to identify items from the same songs, and/or items that are complementary. A mapping function is trained using a machine learning algorithm, such that complementary audio items are closer in the second vector space than the first, according to a given distance metric.

公开(公告)号：US20200372882A1

公开(公告)日：2020-11-26

申请号：US16802308

申请日：2020-02-26

Applicant: Spotify AB

Inventor： François Pachet ,  Pierre Roy

IPC: G10H1/00 ,  G10H1/38

Abstract: Methods, systems and computer program products are provided for testing a lead sheet for plagiarism. A test lead sheet receiving having a plurality of passages is received at receiving a plagiarism detector. A set of annotations describing a level of plagiarism of a plurality of elements (e.g., chord sequence, subsequences, melodic fragments (i.e., notes), rhythm, harmony, etc.) of the test lead sheet in relation to the preexisting lead sheets are generated and output via an output device.

公开(公告)号：US20230223037A1

公开(公告)日：2023-07-13

申请号：US18090228

申请日：2022-12-28

Applicant: Spotify AB

Inventor： Juan José Bosch Vicente ,  François Pachet ,  Pierre Roy ,  Mathieu Ramona ,  Tristan Jehan

IPC: G10L25/51 ,  G10L25/30 ,  G06N3/04 ,  G06F16/632 ,  G06N3/08

CPC classification number: G10L25/51 ,  G10L25/30 ,  G06N3/04 ,  G06F16/634 ,  G06N3/08

Abstract: Methods, systems and computer program products are provided for determining acoustic feature vectors of query and target items in a first vector space, and mapping the acoustic feature vectors to a second vector space having a lower dimension. The distribution of vectors in the second vector space can then be used to identify items from the same songs, and/or items that are complementary. A mapping function is trained using a machine learning algorithm, such that complementary audio items are closer in the second vector space than the first, according to a given distance metric.

公开(公告)号：US11145285B2

公开(公告)日：2021-10-12

申请号：US16805385

申请日：2020-02-28

Applicant: Spotify AB

Inventor： Pierre Roy ,  François Pachet

IPC: G10H1/00

Abstract: The present disclosure relates to a method of editing an audio stream (S) having at least one tone (T1) extending over time in said stream. The method comprises cutting the stream at a first time point of the stream, producing a first cut (A) having a left cutting end (AL) and a right cutting end (AR); allocating a respective memory cell to each of the cutting ends; in each of the memory cells, storing information about the tone; and, for one of the cutting ends, concatenating the cutting end with a further stream cutting end which also has an allocated memory cell with information stored therein about any tones extending to said further cutting end. The concatenating comprises using the information stored in the memory cells for adjusting any of the tones extending to the cutting ends.

公开(公告)号：US20210090590A1

公开(公告)日：2021-03-25

申请号：US16575926

申请日：2019-09-19

Applicant: Spotify AB

Inventor： Juan José Bosch Vicente ,  François Pachet ,  Pierre Roy ,  Mathieu Ramona ,  Tristan Jehan

IPC: G10L25/51 ,  G10L25/30 ,  G06N3/04 ,  G06N3/08 ,  G06F16/632

Abstract: Methods, systems and computer program products are provided for determining acoustic feature vectors of query and target items in a first vector space, and mapping the acoustic feature vectors to a second vector space having a lower dimension. The distribution of vectors in the second vector space can then be used to identify items from the same songs, and/or items that are complementary. A mapping function is trained using a machine learning algorithm, such that complementary audio items are closer in the second vector space than the first, according to a given distance metric.

公开(公告)号：US12164826B2

公开(公告)日：2024-12-10

申请号：US17569181

申请日：2022-01-05

Applicant: Spotify AB

Inventor： François Pachet ,  Pierre Roy

IPC: G06F3/16 ,  G05B15/02 ,  G06F16/68 ,  G06F16/9538 ,  H04N21/442

Abstract: A skip behavior analyzer is part of a media delivery system that allows for unbiased A/B testing of a plurality of versions of a song. The media delivery system stores a plurality of versions of a song and randomly selects, for each requesting device, a version of the song to associate with that device. Each time the device requests the song, thereafter, the media delivery system will provide the same version of the song for consistency. The media delivery system then gathers song play and skip information, calculates the differences in distribution of the skip behavior, and provides the skip information to allow a music composer to better determine which version of a song is more popular and why that is so.