{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LAOL5YD5LQSCNLNPRIXQRRXPNX","short_pith_number":"pith:LAOL5YD5","schema_version":"1.0","canonical_sha256":"581cbee07d5c2426adaf8a2f08c6ef6dce3c03bf3262e9241a470b4ecc46099b","source":{"kind":"arxiv","id":"2503.12589","version":1},"attestation_state":"computed","paper":{"title":"Context-Aware Two-Step Training Scheme for Domain Invariant Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haizhou Li, Jingru Lin, Shuai Wang, Wupeng Wang, Zexu Pan","submitted_at":"2025-03-16T17:49:07Z","abstract_excerpt":"Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as real-world speech mixtures. To address this, we introduce a novel context-aware, two-stage training scheme for speech separation models. In this training scheme, the conventional end-to-end architecture is replaced with a framework that contains a context extractor and a segregator. The two modules are trained step by step to simulate the speech separation process 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":"2503.12589","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-03-16T17:49:07Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"eff26b5358a4be2ad551717b57d9f7d2323b629d903ef7a684e2a6ab56d07791","abstract_canon_sha256":"a6ee342a5ef17e3f76dea693704c5da4e2fa53960ae1c1a3c3d5111c94cc6d73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:16.634653Z","signature_b64":"k46quiR2TWyr62qQGu1xKbuZvSVC8apIYTfplGk7gAjmwPLPemUZG52B3Cc0Y6voMMZQmTJoh0C9vophZwKBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"581cbee07d5c2426adaf8a2f08c6ef6dce3c03bf3262e9241a470b4ecc46099b","last_reissued_at":"2026-07-05T10:32:16.633979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:16.633979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Aware Two-Step Training Scheme for Domain Invariant Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haizhou Li, Jingru Lin, Shuai Wang, Wupeng Wang, Zexu Pan","submitted_at":"2025-03-16T17:49:07Z","abstract_excerpt":"Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as real-world speech mixtures. To address this, we introduce a novel context-aware, two-stage training scheme for speech separation models. In this training scheme, the conventional end-to-end architecture is replaced with a framework that contains a context extractor and a segregator. The two modules are trained step by step to simulate the speech separation process of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12589","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/2503.12589/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":"2503.12589","created_at":"2026-07-05T10:32:16.634057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12589v1","created_at":"2026-07-05T10:32:16.634057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12589","created_at":"2026-07-05T10:32:16.634057+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAOL5YD5LQSC","created_at":"2026-07-05T10:32:16.634057+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAOL5YD5LQSCNLNP","created_at":"2026-07-05T10:32:16.634057+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAOL5YD5","created_at":"2026-07-05T10:32:16.634057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03166","citing_title":"Adversarial Stress Testing of Role-Playing Language Agents using Multi-Agent Evaluation","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LAOL5YD5LQSCNLNPRIXQRRXPNX","json":"https://pith.science/pith/LAOL5YD5LQSCNLNPRIXQRRXPNX.json","graph_json":"https://pith.science/api/pith-number/LAOL5YD5LQSCNLNPRIXQRRXPNX/graph.json","events_json":"https://pith.science/api/pith-number/LAOL5YD5LQSCNLNPRIXQRRXPNX/events.json","paper":"https://pith.science/paper/LAOL5YD5"},"agent_actions":{"view_html":"https://pith.science/pith/LAOL5YD5LQSCNLNPRIXQRRXPNX","download_json":"https://pith.science/pith/LAOL5YD5LQSCNLNPRIXQRRXPNX.json","view_paper":"https://pith.science/paper/LAOL5YD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12589&json=true","fetch_graph":"https://pith.science/api/pith-number/LAOL5YD5LQSCNLNPRIXQRRXPNX/graph.json","fetch_events":"https://pith.science/api/pith-number/LAOL5YD5LQSCNLNPRIXQRRXPNX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAOL5YD5LQSCNLNPRIXQRRXPNX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAOL5YD5LQSCNLNPRIXQRRXPNX/action/storage_attestation","attest_author":"https://pith.science/pith/LAOL5YD5LQSCNLNPRIXQRRXPNX/action/author_attestation","sign_citation":"https://pith.science/pith/LAOL5YD5LQSCNLNPRIXQRRXPNX/action/citation_signature","submit_replication":"https://pith.science/pith/LAOL5YD5LQSCNLNPRIXQRRXPNX/action/replication_record"}},"created_at":"2026-07-05T10:32:16.634057+00:00","updated_at":"2026-07-05T10:32:16.634057+00:00"}