{"id":15677105,"url":"https://github.com/yoyolicoris/eva","last_synced_at":"2025-05-07T00:43:51.003Z","repository":{"id":140051629,"uuid":"138189909","full_name":"yoyolicoris/eva","owner":"yoyolicoris","description":"A screaming vocal samples dataset.","archived":false,"fork":false,"pushed_at":"2023-04-14T20:51:35.000Z","size":4939,"stargazers_count":13,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-05-04T16:58:30.884Z","etag":null,"topics":["dataset","screaming","svm-classifier","vocal"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/yoyolicoris.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2018-06-21T15:36:05.000Z","updated_at":"2023-09-03T12:54:52.000Z","dependencies_parsed_at":null,"dependency_job_id":"55aa4436-a166-4a9c-8732-0c548fec24ea","html_url":"https://github.com/yoyolicoris/eva","commit_stats":{"total_commits":8,"total_committers":2,"mean_commits":4.0,"dds":0.125,"last_synced_commit":"3fc1cd9e40e93b1b375e2e024293394877762c04"},"previous_names":["yoyolicoris/eva","yoyololicon/eva"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yoyolicoris%2Feva","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yoyolicoris%2Feva/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yoyolicoris%2Feva/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yoyolicoris%2Feva/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yoyolicoris","download_url":"https://codeload.github.com/yoyolicoris/eva/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252793561,"owners_count":21805053,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["dataset","screaming","svm-classifier","vocal"],"created_at":"2024-10-03T16:08:32.536Z","updated_at":"2025-05-07T00:43:50.990Z","avatar_url":"https://github.com/yoyolicoris.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# EVA: The Extreme Vocals Archive Dataset\n\nThis is the final project I did when I was studying the MIR course in NTHU. \nI decided to do make a dataset full of screaming vocals samples, because this kind of vocals is less concerned in the MIR field.\nThe making of this dataset may be a starting point for future research.\n\n## Raw audio\n\nI pick up 16 songs as listed below  from [The 'Mixing Secrets' Free Multitrack Download Library](http://www.cambridge-mt.com/ms-mtk.htm), \nand used audacity to slice vocal tracks into small clips, ended up with 565 of samples.\n\n```\nThe Apprehended: 'Still Flyin'\nCnoc An Tursa: 'Bannockburn'\nThe Complainiacs: 'Etc'\t\nDark Ride: 'Burning Bridges'\nDark Ride: 'Hammer Down'\nDark Ride: 'Piece Of Me'\nDeath Of A Romantic: 'The Well'\nDecypher: 'Unseen'\nHeadwound Harry: 'XXXV'\nHollow Ground: 'Ill Fate'\nHollow Ground: 'Left Blind'\nLast Legacy: 'Who's Who In Hell'\nStorm Of Particles: 'Of Ice And Hopeless Fate'\nTimboz: 'Pony'\nTitanium: 'Haunted Age'\nWall Of Death: 'Femme'\n```\n\nI named each clips using initials, so the first clips from the track `43_Vox18.wav` in _The Apprehended - Still Flyin_ \nis named as `TA_SF_43_Vox18_01.wav`, etc. I can't provide the raw audio, but you can use the files in [mark_time](mark_time) \nwhich contain the start time and end time of each clips, to manually recreate them.\n\n## Data\n\n* [annotations](annotations.csv): the vocal techniques of each samples, labeled by metal youtuber [Edward].\n* [features](features.csv): audio features (except chroma related) extracted with [librosa].\n\n[Edward]: https://www.youtube.com/channel/UCu1FDV-RQS8V3s82RuNmOWg\n[librosa]: https://librosa.github.io/librosa/\n\n## Code\n\nRequire pandas, sklearn, matplotlib and librosa be installed.\n\n1. [get_features](get_features.py): features extraction from the audio (used to create `features.csv`). \nMost of the code are borrowed from [FMA](https://github.com/mdeff/fma/blob/master/features.py).\n2. [analysis](analysis.py): show the melspectrogram of some samples. Require raw audio files.\n3. [baseline](baseline_svm.py): baseline svm model for vocal techniques recognition.\n\n## Melspectrogram of some samples\n\n![](images/compare1.png)\n![](images/compare2.png)\n![](images/compare3.png)\n![](images/compare4.png)\n![](images/compare5.png)\n![](images/compare6.png)\n\n## Samples distribution after dimension reduction using LDA\n\n![](images/LDA1.png)\n![](images/LDA2.png)\n\n## Environment\n\n* ubuntu 16.04 LTS\n* python3.5.2 (using Pycharm 2018.1.4)\n\nI also wrote a [report](report.pdf) in chinese about the making process.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyoyolicoris%2Feva","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyoyolicoris%2Feva","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyoyolicoris%2Feva/lists"}