{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OQMLJG4WYKW4CGITVUFSB4NTDL","short_pith_number":"pith:OQMLJG4W","schema_version":"1.0","canonical_sha256":"7418b49b96c2adc11913ad0b20f1b31ada8c72460a5697e599c20bcb9b56211b","source":{"kind":"arxiv","id":"1811.02641","version":1},"attestation_state":"computed","paper":{"title":"Building Corpora for Single-Channel Speech Separation Across Multiple Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gregory Sell, Leibny Paola Garcia-Perera, Matthew Maciejewski, Sanjeev Khudanpur, Shinji Watanabe","submitted_at":"2018-11-06T20:59:54Z","abstract_excerpt":"To date, the bulk of research on single-channel speech separation has been conducted using clean, near-field, read speech, which is not representative of many modern applications. In this work, we develop a procedure for constructing high-quality synthetic overlap datasets, necessary for most deep learning-based separation frameworks. We produced datasets that are more representative of realistic applications using the CHiME-5 and Mixer 6 corpora and evaluate standard methods on this data to demonstrate the shortcomings of current source-separation performance. We also demonstrate the value of"},"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":"1811.02641","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-06T20:59:54Z","cross_cats_sorted":[],"title_canon_sha256":"aaea6c63e45da8c084068a05a62fde7c1cc0a96503d6f909d837930d3f262f78","abstract_canon_sha256":"2456c5fb430b5009a8f834f4cd59181174e79f6a61be52d1870b304cdfa3fd9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:43.048266Z","signature_b64":"4CxjqZEGPPlbrRRqzPQjmEpBBdfnSK2USnkFhzMGPhuCwDtUZgLwu6zvs0A6FhJbZeQFjeUZrBAoFFjGVMqrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7418b49b96c2adc11913ad0b20f1b31ada8c72460a5697e599c20bcb9b56211b","last_reissued_at":"2026-07-05T09:27:43.047788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:43.047788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building Corpora for Single-Channel Speech Separation Across Multiple Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gregory Sell, Leibny Paola Garcia-Perera, Matthew Maciejewski, Sanjeev Khudanpur, Shinji Watanabe","submitted_at":"2018-11-06T20:59:54Z","abstract_excerpt":"To date, the bulk of research on single-channel speech separation has been conducted using clean, near-field, read speech, which is not representative of many modern applications. In this work, we develop a procedure for constructing high-quality synthetic overlap datasets, necessary for most deep learning-based separation frameworks. We produced datasets that are more representative of realistic applications using the CHiME-5 and Mixer 6 corpora and evaluate standard methods on this data to demonstrate the shortcomings of current source-separation performance. We also demonstrate the value of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02641","kind":"arxiv","version":1},"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/1811.02641/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":"1811.02641","created_at":"2026-07-05T09:27:43.047845+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.02641v1","created_at":"2026-07-05T09:27:43.047845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02641","created_at":"2026-07-05T09:27:43.047845+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQMLJG4WYKW4","created_at":"2026-07-05T09:27:43.047845+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQMLJG4WYKW4CGIT","created_at":"2026-07-05T09:27:43.047845+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQMLJG4W","created_at":"2026-07-05T09:27:43.047845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.08375","citing_title":"Developing an Effective Training Dataset to Enhance the Performance of AI-based Speaker Separation Systems","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQMLJG4WYKW4CGITVUFSB4NTDL","json":"https://pith.science/pith/OQMLJG4WYKW4CGITVUFSB4NTDL.json","graph_json":"https://pith.science/api/pith-number/OQMLJG4WYKW4CGITVUFSB4NTDL/graph.json","events_json":"https://pith.science/api/pith-number/OQMLJG4WYKW4CGITVUFSB4NTDL/events.json","paper":"https://pith.science/paper/OQMLJG4W"},"agent_actions":{"view_html":"https://pith.science/pith/OQMLJG4WYKW4CGITVUFSB4NTDL","download_json":"https://pith.science/pith/OQMLJG4WYKW4CGITVUFSB4NTDL.json","view_paper":"https://pith.science/paper/OQMLJG4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.02641&json=true","fetch_graph":"https://pith.science/api/pith-number/OQMLJG4WYKW4CGITVUFSB4NTDL/graph.json","fetch_events":"https://pith.science/api/pith-number/OQMLJG4WYKW4CGITVUFSB4NTDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQMLJG4WYKW4CGITVUFSB4NTDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQMLJG4WYKW4CGITVUFSB4NTDL/action/storage_attestation","attest_author":"https://pith.science/pith/OQMLJG4WYKW4CGITVUFSB4NTDL/action/author_attestation","sign_citation":"https://pith.science/pith/OQMLJG4WYKW4CGITVUFSB4NTDL/action/citation_signature","submit_replication":"https://pith.science/pith/OQMLJG4WYKW4CGITVUFSB4NTDL/action/replication_record"}},"created_at":"2026-07-05T09:27:43.047845+00:00","updated_at":"2026-07-05T09:27:43.047845+00:00"}