musiccaps
6 rows where aspect_list contains "powerful" and aspect_list contains "reverberant"
This data as json, CSV (advanced)
aspect_list (array) 29 ✖
- powerful · 6 ✖
- reverberant · 6 ✖
- low quality 5
- epic 4
- passionate 4
- live performance 3
- noisy 3
- emotional 2
- mono 2
- brass quartet 1
- drum rolls 1
- gospel 1
- harmonizing mixed choir vocals 1
- huge church organ chords progression 1
- loud 1
- loud bagpipe melody 1
- loud brass section melody 1
- mellow woodwinds melody 1
- muffled 1
- muffled percussion 1
- orchestra 1
- passionate male vocal 1
- playback instrumental 1
- shimmering cymbals 1
- shoe tapping 1
- soulful 1
- straight piano chords 1
- suspenseful violin melody 1
- synchronized trombone melody 1
ytid ▼ | url | caption | aspect_list | audioset_names | author_id | start_s | end_s | is_balanced_subset | is_audioset_eval | audioset_ids |
---|---|---|---|---|---|---|---|---|---|---|
2_mFg42LlUI | The low quality recording features a huge church organ chord progression, followed by shimmering cymbals, played in a huge reverberant space - most likely a church. It sounds epic and powerful. | ["shimmering cymbals", "huge church organ chords progression", "reverberant", "low quality", "powerful", "epic"] | ["Organ", "Hammond organ", "Keyboard (musical)", "Piano"] | 4 | 70 | 80 | 0 | 0 | ["/m/013y1f", "/m/03gvt", "/m/05148p4", "/m/05r5c"] | |
73YTz8RC2Fo | The low quality recording features a passionate male vocal singing over playback instrumental that consists of straight piano chord progression. It is noisy and reverberant, as the singer is singing in a larger room. It sounds emotional, passionate and powerful. | ["low quality", "passionate male vocal", "playback instrumental", "straight piano chords", "reverberant", "loud", "noisy", "live performance", "passionate", "powerful", "emotional"] | ["Music", "/t/dd00003"] | 4 | 30 | 40 | 0 | 1 | ["/m/04rlf", "/t/dd00003"] | |
IizUHzmcPGA | The recording features a brass quartet playing in a reverberant space. It consists of synchronized trombone melody and it sounds passionate, epic and powerful. | ["brass quartet", "synchronized trombone melody", "reverberant", "passionate", "epic", "powerful"] | ["Brass instrument", "Trombone"] | 4 | 30 | 40 | 0 | 0 | ["/m/01kcd", "/m/07c6l"] | |
NJ_Ha89QjiI | The low quality recording features shoe tapping sounds alongside loud bagpipe melody and drum rolls. It sounds like it was recorded outside and therefore it is reverberant, epic and powerful. The recording is in mono and a bit noisy. | ["drum rolls", "shoe tapping", "loud bagpipe melody", "epic", "powerful", "low quality", "mono", "noisy", "reverberant"] | ["Bagpipes", "Wind instrument, woodwind instrument"] | 4 | 70 | 80 | 0 | 0 | ["/m/0192l", "/m/085jw"] | |
UinQGYfmZhE | The low quality recording features a live performance of a gospel song and it consists of harmonizing mixed choir vocals singing in a very large space. It sounds passionate, emotional, soulful and powerful. | ["low quality", "reverberant", "live performance", "gospel", "harmonizing mixed choir vocals", "powerful", "soulful", "passionate", "emotional"] | ["Music", "Choir"] | 4 | 120 | 130 | 0 | 0 | ["/m/04rlf", "/m/0l14jd"] | |
cJ80eZY03Yg | The low quality recording features a live performance of an orchestra and it consists of loud brass melody, mellow woodwinds melody, suspenseful violin melody and muffled percussion. It sounds epic, powerful and passionate. The recording is in mono, a bit noisy and it is reverberant as it was performed in a large concert hall. | ["low quality", "live performance", "noisy", "mono", "reverberant", "orchestra", "muffled", "epic", "powerful", "passionate", "suspenseful violin melody", "muffled percussion", "loud brass section melody", "mellow woodwinds melody"] | ["String section", "Orchestra"] | 4 | 200 | 210 | 0 | 0 | ["/m/02qmj0d", "/m/05pd6"] |
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 );