musiccaps
4 rows where aspect_list contains "addictive" and aspect_list contains "messy"
This data as json, CSV (advanced)
aspect_list (array) 40 ✖
- addictive · 4 ✖
- low quality 4
- messy · 4 ✖
- punchy kick 3
- punchy snare 3
- energetic 2
- groovy bass 2
- addictive female vocal 1
- arpeggiated piano melody 1
- bad mix 1
- boomy bass 1
- boomy kick 1
- claps 1
- distorted 1
- distorted bass 1
- easygoing 1
- electric guitar melody 1
- emotional 1
- filtered background male vocal 1
- flat double male vocals 1
- flat male vocal 1
- harmonizing background female vocals 1
- harsh 1
- hip hop 1
- live performance 1
- muddy 1
- passionate 1
- passionate female vocal 1
- r&b 1
- repetitive synth lead melody 1
- rock 1
- shimmering cymbals 1
- shimmering hi hats 1
- snare roll 1
- soft crash cymbal 1
- string melody 1
- traditional pop 1
- uptempo hi hats 1
- wide acoustic guitar chords 1
- wooden percussions 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
7RtQpW2dSU4 | The low quality recording features a rock song that consists of a passionate female vocal, alongside harmonizing background female vocals, singing over wide acoustic guitar chords, groovy bass, punchy kick and snare hits. It sounds addictive and easygoing, even though the recording is a bit messy. | ["low quality", "rock", "wide acoustic guitar chords", "groovy bass", "harmonizing background female vocals", "passionate female vocal", "punchy kick", "punchy snare", "shimmering hi hats", "addictive", "easygoing", "messy"] | ["Music", "Happy music"] | 4 | 10 | 20 | 0 | 0 | ["/m/04rlf", "/t/dd00031"] | |
SG24NL2Xi3A | The low quality recording features a hip hop song sung with an addictive flow by flat double male vocals over arpeggiated piano melody, boomy, layered bass and kick hits, soft crash cymbal and claps. It sounds muddy and messy as the mix of the song is bad making the frequencies clash with each other - especially in the low end. | ["low quality", "hip hop", "arpeggiated piano melody", "boomy kick", "claps", "soft crash cymbal", "flat double male vocals", "boomy bass", "muddy", "messy", "bad mix", "addictive"] | ["Music", "Independent music", "Rhythm and blues", "Song"] | 4 | 30 | 40 | 1 | 1 | ["/m/04rlf", "/m/05rwpb", "/m/06j6l", "/m/074ft"] | |
eISYX9koocM | The low quality recording features a live performance of a traditional pop song and it consists of an addictive female vocal singing over punchy kick and snare hits, groovy bass, electric guitar melody, strings melody and wooden percussion. There is a short snare roll, right before the bass drops. It sounds messy, a bit harsh, distorted, but also passionate, addictive and energetic. | ["live performance", "low quality", "traditional pop", "addictive female vocal", "punchy snare", "wooden percussions", "snare roll", "groovy bass", "string melody", "electric guitar melody", "punchy kick", "messy", "distorted", "harsh", "passionate", "addictive", "energetic"] | ["Music of Asia", "Music", "Salsa music"] | 4 | 30 | 40 | 0 | 0 | ["/m/028sqc", "/m/04rlf", "/m/0ln16"] | |
nSLxQLYYoNE | The low quality recording features a R&B song that consists of flat male vocals, alongside filtered background male vocals, singing over punchy kick and snare hits, shimmering cymbals, uptempo hi hats, distorted bass and repetitive synth lead melody. It sounds messy, as the frequencies are clashing with each other, but also energetic, emotional and addictive - like something you would quickly learn to sing along. | ["low quality", "r&b", "uptempo hi hats", "distorted bass", "repetitive synth lead melody", "filtered background male vocal", "punchy snare", "shimmering cymbals", "punchy kick", "flat male vocal", "energetic", "emotional", "addictive", "messy"] | ["Music", "Rapping", "Zing", "Hip hop music"] | 4 | 40 | 50 | 0 | 0 | ["/m/04rlf", "/m/06bxc", "/m/07p78v5", "/m/0glt670"] |
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 );