musiccaps
2 rows where aspect_list contains "acoustic rhythm guitar" and aspect_list contains "harmonizing mixed vocals"
This data as json, CSV (advanced)
aspect_list (array) 17 ✖
- acoustic rhythm guitar · 2 ✖
- harmonizing mixed vocals · 2 ✖
- low quality 2
- accordion melody 1
- emotional 1
- fun 1
- groovy bass 1
- happy 1
- hollow male vocal 1
- joyful 1
- live performance 1
- mono 1
- noisy 1
- passionate 1
- passionate male vocal 1
- shimmering shakers 1
- thin 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
GBsate-JQAo | The low quality recording features a live performance sung by harmonizing mixed vocals and followed by acoustic rhythm guitar and shimmering shaker. In the second part, a hollow male vocal continues to sing over shaker and acoustic guitar. It sounds thin, but fun, happy and emotional - it was probably recorded with a phone or camera microphone. | ["low quality", "live performance", "shimmering shakers", "harmonizing mixed vocals", "hollow male vocal", "acoustic rhythm guitar", "fun", "happy", "emotional", "thin"] | ["Blues", "Singing", "Music"] | 4 | 120 | 130 | 0 | 1 | ["/m/0155w", "/m/015lz1", "/m/04rlf"] | |
_2P_EJsnBls | The low quality recording features a passionate male vocal, alongside harmonizing mixed vocals, singing over acoustic rhythm guitar, accordion melody and groovy bass. It sounds passionate and joyful. The recording is noisy and in mono - the sound is coming from the right channel only. | ["low quality", "noisy", "mono", "harmonizing mixed vocals", "passionate male vocal", "accordion melody", "acoustic rhythm guitar", "groovy bass", "passionate", "joyful"] | ["Singing", "Music", "Middle Eastern music"] | 4 | 80 | 90 | 0 | 0 | ["/m/015lz1", "/m/04rlf", "/m/06j64v"] |
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 );