{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4DAMEIXAJRISYLYYSMK66NTYJY","short_pith_number":"pith:4DAMEIXA","schema_version":"1.0","canonical_sha256":"e0c0c222e04c512c2f189315ef36784e34323c1c98070dd51eb005d2b54fa852","source":{"kind":"arxiv","id":"2306.15354","version":3},"attestation_state":"computed","paper":{"title":"3D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hui Wang, Luyao Cheng, Qian Chen, Siqi Zheng, Yafeng Chen","submitted_at":"2023-06-27T10:09:43Z","abstract_excerpt":"Disentangling uncorrelated information in speech utterances is a crucial research topic within speech community. Different speech-related tasks focus on extracting distinct speech representations while minimizing the affects of other uncorrelated information. We present a large-scale speech corpus to facilitate the research of speech representation disentanglement. 3D-Speaker contains over 10,000 speakers, each of whom are simultaneously recorded by multiple Devices, locating at different Distances, and some speakers are speaking multiple Dialects. The controlled combinations of multi-dimensio"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.15354","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-27T10:09:43Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"e15cee6f6fc0a52af18d9c6908f58c4f1d4f0d0b2592d9527dc046c291245d06","abstract_canon_sha256":"ee7b7fd1ea51ff9e556403239d02d661aee1504df2a529b40304f11cd5f54b3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:41.520814Z","signature_b64":"IF6MBh3aGquE5uq2pKTbxHbpde3UOc4UYNRFhh4Y6lyzFXehZwER2n5aIX/d9E7j+iIGoWuc0eNIDkgdl2fkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0c0c222e04c512c2f189315ef36784e34323c1c98070dd51eb005d2b54fa852","last_reissued_at":"2026-07-05T06:53:41.520255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:41.520255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hui Wang, Luyao Cheng, Qian Chen, Siqi Zheng, Yafeng Chen","submitted_at":"2023-06-27T10:09:43Z","abstract_excerpt":"Disentangling uncorrelated information in speech utterances is a crucial research topic within speech community. Different speech-related tasks focus on extracting distinct speech representations while minimizing the affects of other uncorrelated information. We present a large-scale speech corpus to facilitate the research of speech representation disentanglement. 3D-Speaker contains over 10,000 speakers, each of whom are simultaneously recorded by multiple Devices, locating at different Distances, and some speakers are speaking multiple Dialects. The controlled combinations of multi-dimensio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15354","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.15354/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.15354","created_at":"2026-07-05T06:53:41.520339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.15354v3","created_at":"2026-07-05T06:53:41.520339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15354","created_at":"2026-07-05T06:53:41.520339+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DAMEIXAJRIS","created_at":"2026-07-05T06:53:41.520339+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DAMEIXAJRISYLYY","created_at":"2026-07-05T06:53:41.520339+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DAMEIXA","created_at":"2026-07-05T06:53:41.520339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22369","citing_title":"Kiwano: A Cutting-Edge Open-Source Toolkit for Speaker Verification","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02400","citing_title":"SoulX-Transcriber: A Robust End-to-End Framework for Multi-Speaker Speech Transcription","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22821","citing_title":"Audio2Tool: Speak, Call, Act -- A Dataset for Benchmarking Speech Tool Use","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4DAMEIXAJRISYLYYSMK66NTYJY","json":"https://pith.science/pith/4DAMEIXAJRISYLYYSMK66NTYJY.json","graph_json":"https://pith.science/api/pith-number/4DAMEIXAJRISYLYYSMK66NTYJY/graph.json","events_json":"https://pith.science/api/pith-number/4DAMEIXAJRISYLYYSMK66NTYJY/events.json","paper":"https://pith.science/paper/4DAMEIXA"},"agent_actions":{"view_html":"https://pith.science/pith/4DAMEIXAJRISYLYYSMK66NTYJY","download_json":"https://pith.science/pith/4DAMEIXAJRISYLYYSMK66NTYJY.json","view_paper":"https://pith.science/paper/4DAMEIXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.15354&json=true","fetch_graph":"https://pith.science/api/pith-number/4DAMEIXAJRISYLYYSMK66NTYJY/graph.json","fetch_events":"https://pith.science/api/pith-number/4DAMEIXAJRISYLYYSMK66NTYJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DAMEIXAJRISYLYYSMK66NTYJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DAMEIXAJRISYLYYSMK66NTYJY/action/storage_attestation","attest_author":"https://pith.science/pith/4DAMEIXAJRISYLYYSMK66NTYJY/action/author_attestation","sign_citation":"https://pith.science/pith/4DAMEIXAJRISYLYYSMK66NTYJY/action/citation_signature","submit_replication":"https://pith.science/pith/4DAMEIXAJRISYLYYSMK66NTYJY/action/replication_record"}},"created_at":"2026-07-05T06:53:41.520339+00:00","updated_at":"2026-07-05T06:53:41.520339+00:00"}