musiccaps
3 rows where aspect_list contains "incoherent music" and aspect_list contains "vocal backup"
This data as json, CSV (advanced)
aspect_list (array) 49 ✖
- incoherent music · 3 ✖
- vocal backup · 3 ✖
- amateur recording 2
- clapping 2
- female singer 2
- live performance 2
- medium tempo 2
- ambient auditorium sounds 1
- ambient sounds 1
- chant like 1
- chanting 1
- christmas concert 1
- christmas song 1
- christmas time 1
- classical music 1
- classical song 1
- droning 1
- emphatic vocals 1
- enthusiastic 1
- extemporaneous 1
- folk song 1
- foreign language 1
- heavy reverb 1
- home videos 1
- hynoptic 1
- inferior audio quality 1
- karaoke 1
- keyboard harmony 1
- lao folk music 1
- laos classical song 1
- laos folk song 1
- laotian classical music 1
- lilting 1
- live audience 1
- male singer 1
- meditative 1
- medium fast tempo 1
- melodic 1
- off key singing 1
- people talking 1
- piano accompaniment 1
- poor audio quality 1
- small hand cymbals 1
- soothing 1
- steady drumming 1
- teen singer 1
- violin harmony 1
- xylophone like instrument 1
- youthful 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
8MbxazeMw2E | A female vocalist sings this loud chant like folk song in a foreign language. The tempo is medium fast with vocal backup, rhythmic small hand cymbals and xylophone like instruments. The audio quality is inferior so the music is incoherent. This song is a live performance or concert with ambient sounds. The song is loud, lilting, chant-like, meditative, droning, hynoptic, melodious and classical. This song is a Classical Laos Folk song. | ["female singer", "medium fast tempo", "lilting", "chant like", "droning", "hynoptic", "folk song", "classical song", "laos classical song", "laos folk song", "melodic", "extemporaneous", "incoherent music", "live performance", "ambient auditorium sounds", "people talking", "clapping", "amateur recording", "lao folk music", "vocal backup", "small hand cymbals", "xylophone like instrument", "classical music", "laotian classical music", "chanting", "meditative", "soothing"] | ["Folk music", "Music", "Musical instrument", "Rattle (instrument)", "Percussion"] | 7 | 430 | 440 | 0 | 0 | ["/m/02w4v", "/m/04rlf", "/m/04szw", "/m/05r5wn", "/m/0l14md"] | |
ZNGJN30LCwM | A male vocalist sings this Christmas song. The tempo is medium with minimal instruments like keyboard harmony and steady drumming. The audio quality is inferior so the music is incoherent. This is a live performance with ambient sounds of people clapping and cheering. This is a contemporary Christmas Song. | ["male singer", "teen singer", "medium tempo", "vocal backup", "keyboard harmony", "steady drumming", "poor audio quality", "incoherent music", "emphatic vocals", "live performance", "ambient sounds", "clapping", "christmas song", "christmas time", "christmas concert", "live performance", "live audience", "heavy reverb"] | ["Christmas music", "Singing", "Music", "Choir"] | 7 | 30 | 40 | 0 | 0 | ["/m/0140xf", "/m/015lz1", "/m/04rlf", "/m/0l14jd"] | |
jKWl63gozLE | A female vocalist sings this pop song in a foreign language. The tempo is medium with karaoke music and vocal backup. The audio quality is inferior and the music is incoherent except for a violin harmony and piano accompaniment. This song is an amateur home video. | ["female singer", "medium tempo", "foreign language", "violin harmony", "piano accompaniment", "karaoke", "off key singing", "vocal backup", "incoherent music", "amateur recording", "inferior audio quality", "enthusiastic", "youthful", "home videos"] | ["Music of Asia", "Music", "/t/dd00004"] | 7 | 50 | 60 | 0 | 0 | ["/m/028sqc", "/m/04rlf", "/t/dd00004"] |
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 );