musiccaps
2 rows where aspect_list contains "grand piano", aspect_list contains "live performance" and aspect_list contains "male vocal"
This data as json, CSV (advanced)
aspect_list (array) 16 ✖
- grand piano · 2 ✖
- live performance · 2 ✖
- male vocal · 2 ✖
- art song 1
- cabaret 1
- comedic 1
- english 1
- light music 1
- lullaby 1
- melodic singing 1
- merry tune 1
- playful 1
- sarcastic 1
- story-telling mood 1
- theatrical 1
- theatrical singing 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
RD-oizm_35M | This is the live performance of a sarcastic lullaby. Although the piece is written as if it is a lullaby, the words are about illegal alcohol production. The male vocalist in the lead is singing melodically in the style of a cabaret. There is a grand piano playing an accompanying tune in the background. The atmosphere is comedic. This piece could be playing at a radio station in a movie/TV show for a hidden comedic effect. | ["lullaby", "live performance", "male vocal", "melodic singing", "grand piano", "cabaret", "playful", "comedic", "sarcastic", "theatrical"] | ["Music", "Lullaby"] | 9 | 14 | 24 | 0 | 1 | ["/m/04rlf", "/m/07pkxdp"] | |
dztizAgcQ08 | This is a live performance of an art song piece. There is a male vocalist singing as if he is performing a role at a theater play. The grand piano is playing a melodic accompaniment piece in the background to support the vocals. The words are derived from English literature. | ["art song", "live performance", "male vocal", "theatrical singing", "grand piano", "merry tune", "story-telling mood", "light music", "english"] | ["Music", "Opera"] | 9 | 30 | 40 | 0 | 1 | ["/m/04rlf", "/m/05lls"] |
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 );