{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2021-06-28T16:32:51.225268+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 1, "enabled": true, "entries": { "CommonLanguage.tar.gz": { "checksum": "md5:d3d9f7bac56cbb3db526406d6a21d5b0", "ext": "gz", "id": "5daef69f-e04f-4134-bbcb-143fffcb6c99", "key": "CommonLanguage.tar.gz", "metadata": null, "mimetype": "application/gzip", "size": 3761951178 } }, "order": [], "total_bytes": 3761951178 }, "id": "5036977", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/5036977/access", "access_links": "https://zenodo.org/api/records/5036977/access/links", "access_request": "https://zenodo.org/api/records/5036977/access/request", "access_users": "https://zenodo.org/api/records/5036977/access/users", "archive": "https://zenodo.org/api/records/5036977/files-archive", "archive_media": "https://zenodo.org/api/records/5036977/media-files-archive", "communities": "https://zenodo.org/api/records/5036977/communities", "communities-suggestions": "https://zenodo.org/api/records/5036977/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.5036977", "draft": "https://zenodo.org/api/records/5036977/draft", "files": "https://zenodo.org/api/records/5036977/files", "latest": "https://zenodo.org/api/records/5036977/versions/latest", "latest_html": "https://zenodo.org/records/5036977/latest", "media_files": "https://zenodo.org/api/records/5036977/media-files", "parent": "https://zenodo.org/api/records/5036976", "parent_doi": "https://zenodo.org/doi/10.5281/zenodo.5036976", "parent_html": "https://zenodo.org/records/5036976", "requests": "https://zenodo.org/api/records/5036977/requests", "reserve_doi": "https://zenodo.org/api/records/5036977/draft/pids/doi", "self": "https://zenodo.org/api/records/5036977", "self_doi": "https://zenodo.org/doi/10.5281/zenodo.5036977", "self_html": "https://zenodo.org/records/5036977", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:5036977/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:5036977/sequence/default", "versions": "https://zenodo.org/api/records/5036977/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "creators": [ { "person_or_org": { "family_name": "Ganesh Sinisetty", "name": "Ganesh Sinisetty", "type": "personal" } }, { "affiliations": [ { "name": "Mila - Universit\u00e9 de Montr\u00e9al" } ], "person_or_org": { "family_name": "Pavlo Ruban", "name": "Pavlo Ruban", "type": "personal" } }, { "affiliations": [ { "name": "Mila - Universit\u00e9 de Montr\u00e9al" } ], "person_or_org": { "family_name": "Oleksandr Dymov", "name": "Oleksandr Dymov", "type": "personal" } }, { "affiliations": [ { "name": "Mila - Universit\u00e9 de Montr\u00e9al" } ], "person_or_org": { "family_name": "Mirco Ravanelli", "name": "Mirco Ravanelli", "type": "personal" } } ], "description": "
CommonLanguage Dataset \n\nThis dataset is composed of speech recordings from of languages that were carefully selected from the CommonVoice database. The total duration of audio recordings is 45.1 hours (i.e., 1 hour of material for each language). The dataset is already balanced and split into train, dev (validation) and test sets. The dataset has been extracted from CommonVoice to train easily language-id systems.\n\nThe baselines for language-id are available in the SpeechBrain toolkit (see recipes/CommonLanguage):\nhttps://github.com/speechbrain/speechbrain\n\nStatistics of CommonLanguage:\n\n| Name | Train | Dev | Test |\n|:---------------------------------:|:------:|:------:|:-----:|\n| **# of utterances** | 177552 | 47104 | 47704 |\n| **# unique speakers** | 11189 | 1297 | 1322 |\n| **Total duration, hr** | 30.04 | 7.53 | 7.53 |\n| **Min duration, sec** | 0.86 | 0.98 | 0.89 |\n| **Mean duration, sec** | 4.87 | 4.61 | 4.55 |\n| **Max duration, sec** | 21.72 | 105.67 | 29.83 |\n| **Duration per language, min** | ~40 | ~10 | ~10 |\n\n## List of languages:\n* Arabic\n* Basque\n* Breton\n* Catalan\n* Chinese_China\n* Chinese_Hongkong\n* Chinese_Taiwan\n* Chuvash\n* Czech\n* Dhivehi\n* Dutch\n* English\n* Esperanto\n* Estonian\n* French\n* Frisian\n* Georgian\n* German\n* Greek\n* Hakha_Chin\n* Indonesian\n* Interlingua\n* Italian\n* Japanese\n* Kabyle\n* Kinyarwanda\n* Kyrgyz\n* Latvian\n* Maltese\n* Mangolian\n* Persian\n* Polish\n* Portuguese\n* Romanian\n* Romansh_Sursilvan\n* Russian\n* Sakha\n* Slovenian\n* Spanish\n* Swedish\n* Tamil\n* Tatar\n* Turkish\n* Ukranian\n* Welsh\n\n## Other information\nIn addition to the language label, the datapoints have `age`, `gender` and `utterance transcription` associated with each utterance.", "publication_date": "2021-06-28", "publisher": "Zenodo", "references": [ { "reference": "Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and Fran\u00e7ois Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio, \"SpeechBrain: A General-Purpose Speech Toolkit\", 2021, arXiv" } ], "resource_type": { "id": "dataset", "title": { "de": "Datensatz", "en": "Dataset" } }, "rights": [ { "description": { "en": "The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited." }, "icon": "cc-by-icon", "id": "cc-by-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution 4.0 International" } } ], "subjects": [ { "subject": "speechbrain" }, { "subject": "language identification" }, { "subject": "CommonVoice" }, { "subject": "speech recognition" }, { "subject": "multiple languages" }, { "subject": "speaker recognition" }, { "subject": "language recognition" }, { "subject": "open-source" } ], "title": "CommonLanguage", "version": "0.1" }, "parent": { "access": { "owned_by": { "user": 195067 } }, "communities": {}, "id": "5036976", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.5036976", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.5036977", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:5036977", "provider": "oai" } }, "revision_id": 2, "stats": { "all_versions": { "data_volume": 65134422695892.0, "downloads": 17314, "unique_downloads": 4082, "unique_views": 2883, "views": 3044 }, "this_version": { "data_volume": 65093041232934.0, "downloads": 17303, "unique_downloads": 4072, "unique_views": 2879, "views": 3040 } }, "status": "published", "updated": "2021-06-29T01:48:20.152668+00:00", "versions": { "index": 1, "is_latest": true } }