公开(公告)号：US20190180787A1

公开(公告)日：2019-06-13

申请号：US16275808

申请日：2019-02-14

Applicant: Spotify AB

Inventor： Tristan JEHAN ,  Frej CONNOLY ,  Miles LENNON ,  Rachel BITTNER ,  Mateo RANDO ,  Ulf KARLSSON

IPC: G11B27/034 ,  G11B27/031

Abstract: A method comprises obtaining a playlist that comprises a plurality of audio items. The playlist is divided into a plurality of coherent groups. Each coherent group comprises a respective sequence of audio items of the plurality of audio items with a common attribute. For a respective coherent group of the plurality of coherent groups, a parameter value of a first audio item of the respective sequence is determined, a parameter value of a second audio item of the respective sequence is adjusted based on the determined parameter value of the first audio item, and a transition media item is formed. The transition media item corresponds to a transition between the first and second audio items that are adjacent in the respective sequence. The transition media item is provided to a second electronic device.

公开(公告)号：US20180095715A1

公开(公告)日：2018-04-05

申请号：US15399594

申请日：2017-01-05

Applicant: Spotify AB

Inventor： Tristan JEHAN ,  Frej CONNOLY ,  Miles LENNON ,  Rachel BITTNER ,  Mateo RANDO ,  Ulf KARLSSON

IPC: G06F3/16

CPC classification number: G11B27/034 ,  G06F17/30772 ,  G10H7/008 ,  G10H2210/145 ,  G10H2210/385 ,  G11B27/031

Abstract: A method comprises obtaining a playlist that comprises a plurality of audio items, and dividing the playlist into a plurality of coherent groups, wherein each coherent group comprises a respective sequence of audio items of the plurality of audio items with a common attribute. For a respective coherent group of the plurality of coherent groups, the method comprises determining a parameter value of a first audio item of the respective sequence and adjusting a parameter value of a second audio item of the respective sequence based on the determined parameter value of the first audio item, to form a transition between the first and second audio items. The first and second audio items are adjacent in the respective sequence. The transition is provided to a second electronic device for playback.

公开(公告)号：US20190066641A1

公开(公告)日：2019-02-28

申请号：US16111580

申请日：2018-08-24

Applicant: Spotify AB

Inventor： Tahora H. NAZER ,  Tristan JEHAN

IPC: G10H1/00 ,  G10L15/14

Abstract: A lyrics analyzer generates tags and explicitness indicators for a set of tracks. These tags may indicate the genre, mood, occasion, or other features of each track. The lyrics analyzer does so by generating an n-dimensional vector relating to a set of topics extracted from the lyrics and then using those vectors to train a classifier to determine whether each tag applies to each track. The lyrics analyzer may also generate playlists for a user based on a single seed song by comparing the lyrics vector or the lyrics and acoustics vectors of the seed song to other songs to select songs that closely match the seed song. Such a playlist generator may also take into account the tags generated for each track.

公开(公告)号：US20190065469A1

公开(公告)日：2019-02-28

申请号：US16111614

申请日：2018-08-24

Applicant: Spotify AB

Inventor： Tahora H. NAZER ,  Tristan JEHAN

IPC: G06F17/27 ,  G06N99/00

Abstract: A lyrics analyzer generates tags and explicitness indicators for a set of tracks. These tags may indicate the genre, mood, occasion, or other features of each track. The lyrics analyzer does so by generating an n-dimensional vector relating to a set of topics extracted from the lyrics and then using those vectors to train a classifier to determine whether each tag applies to each track. The lyrics analyzer may also generate playlists for a user based on a single seed song by comparing the lyrics vector or the lyrics and acoustics vectors of the seed song to other songs to select songs that closely match the seed song. Such a playlist generator may also take into account the tags generated for each track.

公开(公告)号：US20190065468A1

公开(公告)日：2019-02-28

申请号：US16111596

申请日：2018-08-24

Applicant: Spotify AB

Inventor： Tahora H. NAZER ,  Tristan JEHAN

IPC: G06F17/27 ,  G06F17/30 ,  G06N99/00 ,  G06F17/18

Abstract: A lyrics analyzer generates tags and explicitness indicators for a set of tracks. These tags may indicate the genre, mood, occasion, or other features of each track. The lyrics analyzer does so by generating an n-dimensional vector relating to a set of topics extracted from the lyrics and then using those vectors to train a classifier to determine whether each tag applies to each track. The lyrics analyzer may also generate playlists for a user based on a single seed song by comparing the lyrics vector or the lyrics and acoustics vectors of the seed song to other songs to select songs that closely match the seed song. Such a playlist generator may also take into account the tags generated for each track.