musiccaps
2 rows where aspect_list contains "male voices singing" and aspect_list contains "rock&roll"
This data as json, CSV (advanced)
aspect_list (array) 12 ✖
- e-bass 2
- male voices singing · 2 ✖
- rock&roll · 2 ✖
- acoustic drums 1
- background cheering and screaming 1
- e-guitar 1
- good mood 1
- harmony 1
- moderate tempo 1
- uplifting mood 1
- uptempo 1
- violin 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
Vt3HzkNtOP4 | An acoustic drum is playing a light Rock&Roll groove with crash hits and emphasis on kick and snare along with a e-bass enhancing the fast paces mood and giving reasons to move the body along to the beat. Strings like a violin are adding some atmosphere with hits in the background and playing a crescendo to break into the next part of the song while male voices are singing together. This song may be playing when having or wanting a good mood. | ["rock&roll", "e-bass", "acoustic drums", "male voices singing", "violin", "uptempo", "good mood"] | ["Music", "Roll", "Rock and roll"] | 6 | 30 | 40 | 1 | 1 | ["/m/04rlf", "/m/07s8j8t", "/m/07sbbz2"] | |
kjcXM60HrRA | Two male voices are singing loudly together: One backing the other one. A e-guitar can be heard at the end of the phrase. In the background a e-bass and an acoustic drum can be heard but they get overthrown by the sound of the cheering and Screaming crowd. This song may be playing at a live concert. | ["rock&roll", "male voices singing", "harmony", "background cheering and screaming", "e-bass", "e-guitar", "moderate tempo", "uplifting mood"] | ["Music of Asia", "Music", "Pop music", "Yell"] | 6 | 30 | 40 | 0 | 1 | ["/m/028sqc", "/m/04rlf", "/m/064t9", "/m/07sr1lc"] |
Advanced export
JSON shape: default, array, newline-delimited, object
CREATE TABLE [musiccaps] ( [ytid] TEXT PRIMARY KEY, [url] TEXT, [caption] TEXT, [aspect_list] TEXT, [audioset_names] TEXT, [author_id] TEXT, [start_s] TEXT, [end_s] TEXT, [is_balanced_subset] INTEGER, [is_audioset_eval] INTEGER, [audioset_ids] TEXT );