{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2018-04-16T12:52:11.908292+00:00", "custom_fields": { "meeting:meeting": { "acronym": "ICASSP 2018", "place": "Calgary, Canada" } }, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 1, "enabled": true, "entries": { "LibriCount10-0dB.zip": { "checksum": "md5:30c8f844dc59fa65d216d53db9dc37e2", "ext": "zip", "id": "ba3d294e-a3e7-429f-a71d-6efb60aeea94", "key": "LibriCount10-0dB.zip", "metadata": null, "mimetype": "application/zip", "size": 832499962 } }, "order": [], "total_bytes": 832499962 }, "id": "1216072", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/1216072/access", "access_links": "https://zenodo.org/api/records/1216072/access/links", "access_request": "https://zenodo.org/api/records/1216072/access/request", "access_users": "https://zenodo.org/api/records/1216072/access/users", "archive": "https://zenodo.org/api/records/1216072/files-archive", "archive_media": "https://zenodo.org/api/records/1216072/media-files-archive", "communities": "https://zenodo.org/api/records/1216072/communities", "communities-suggestions": "https://zenodo.org/api/records/1216072/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.1216072", "draft": "https://zenodo.org/api/records/1216072/draft", "files": "https://zenodo.org/api/records/1216072/files", "latest": "https://zenodo.org/api/records/1216072/versions/latest", "latest_html": "https://zenodo.org/records/1216072/latest", "media_files": "https://zenodo.org/api/records/1216072/media-files", "parent": "https://zenodo.org/api/records/1216071", "parent_doi": "https://zenodo.org/doi/10.5281/zenodo.1216071", "parent_html": "https://zenodo.org/records/1216071", "requests": "https://zenodo.org/api/records/1216072/requests", "reserve_doi": "https://zenodo.org/api/records/1216072/draft/pids/doi", "self": "https://zenodo.org/api/records/1216072", "self_doi": "https://zenodo.org/doi/10.5281/zenodo.1216072", "self_html": "https://zenodo.org/records/1216072", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:1216072/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:1216072/sequence/default", "versions": "https://zenodo.org/api/records/1216072/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "creators": [ { "affiliations": [ { "name": "Internation Audio Laboratories Erlangen" } ], "person_or_org": { "family_name": "Fabian-Robert St\u00f6ter", "identifiers": [ { "identifier": "0000-0002-2534-1165", "scheme": "orcid" } ], "name": "Fabian-Robert St\u00f6ter", "type": "personal" } }, { "affiliations": [ { "name": "Internation Audio Laboratories Erlangen" } ], "person_or_org": { "family_name": "Soumitro Chakrabarty", "name": "Soumitro Chakrabarty", "type": "personal" } }, { "affiliations": [ { "name": "Internation Audio Laboratories Erlangen" } ], "person_or_org": { "family_name": "Emanu\u00ebl Habets", "identifiers": [ { "identifier": "0000-0002-2613-8046", "scheme": "orcid" } ], "name": "Emanu\u00ebl Habets", "type": "personal" } }, { "affiliations": [ { "name": "Internation Audio Laboratories Erlangen" } ], "person_or_org": { "family_name": "Bernd Edler", "name": "Bernd Edler", "type": "personal" } } ], "description": "
LibriCount10 0dB Dataset
\n\nThis is the description to the LibriCount10 synthetic dataset for speaker count estimation.
\n\nTherefore for each recording we provide the ground truth number of speakers within the file name, where `k` in, `k_uniquefile.wav` is the maximum number of concurrent speakers with the 5 seconds of recording.
\n\nThe dataset contains a simulated cocktail party environment of [0..10] speakers, mixed with 0dB SNR from random utterances of different speakers from the LibriSpeech `CleanTest` dataset.
\n\nAll recordings are of 5s durations, and all speakers are active for the most part of the recording.
\n\nFor each unique recording, we provide the audio wave file (16bits, 16kHz, mono) and an annotation `json` file with the same name as the recording.
\n\nMetadata
\n\nIn the annotation file we provide information about the speakers sex, their unique speaker_id, and vocal activity within the mixture recording in samples. Note that these were automatically generated using a voice activity detection system.
\n\nIn the following example the annotation shows a speaker count of 3 speakers as can be extracted from the number of elements in the list:
\n\n[\n {\n \"sex\": \"F\",\n \"activity\": [[0, 51076], [51396, 55400], [56681, 80000]], \n \"speaker_id\": 1221\n },\n {\n \"sex\": \"F\",\n \"activity\": [[0, 51877], [56201, 80000]],\n \"speaker_id\": 3570\n },\n {\n \"sex\": \"M\",\n \"activity\": [[0, 15681], [16161, 68213], [73498, 80000]], \n \"speaker_id\": 5105\n }\n]
\n\n
\n