{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UWVKMLHS5D57HW4SEVAGYSPVB6","short_pith_number":"pith:UWVKMLHS","schema_version":"1.0","canonical_sha256":"a5aaa62cf2e8fbf3db9225406c49f50fbff4acbc9d67ef1c1ee7be36031c338b","source":{"kind":"arxiv","id":"2509.24395","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Single-Channel Speech Separation with Diffusion under Speaker-Embedding Guidance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chang Li, Jiang Wang, Kai Li, Kazuhiro Nakadai, Ragib Amin Nihal, Runwu Shi, Sihan Tan, Yiyan Wang","submitted_at":"2025-09-29T07:42:54Z","abstract_excerpt":"Speech separation is a fundamental task in audio processing, typically addressed with fully supervised systems trained on paired mixtures. While effective, such systems typically rely on synthetic data pipelines, which may not reflect real-world conditions. Instead, we revisit the source-model paradigm, training a diffusion generative model solely on anechoic speech and formulating separation as a diffusion inverse problem. However, unconditional diffusion models lack speaker-level conditioning, they can capture local acoustic structure but produce temporally inconsistent speaker identities in"},"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":"2509.24395","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-09-29T07:42:54Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"d81d1fb6b0e9c604eb1503aecb1cc89f218933dee555f707166fd7926e52b829","abstract_canon_sha256":"e770263e8fbd9597a93a2a32d8e1d86e63327026fc2cf26e0195efd53405776f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:11:58.027517Z","signature_b64":"C8IgAR4JDZ+IR2cotE+bf3TvnQax+rb4xNGVazCIPFhrNTIdARwi+I0VKx7sztfSpFc3nTDodHq09rPJC0plBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5aaa62cf2e8fbf3db9225406c49f50fbff4acbc9d67ef1c1ee7be36031c338b","last_reissued_at":"2026-08-03T01:11:58.025858Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:11:58.025858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Single-Channel Speech Separation with Diffusion under Speaker-Embedding Guidance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chang Li, Jiang Wang, Kai Li, Kazuhiro Nakadai, Ragib Amin Nihal, Runwu Shi, Sihan Tan, Yiyan Wang","submitted_at":"2025-09-29T07:42:54Z","abstract_excerpt":"Speech separation is a fundamental task in audio processing, typically addressed with fully supervised systems trained on paired mixtures. While effective, such systems typically rely on synthetic data pipelines, which may not reflect real-world conditions. Instead, we revisit the source-model paradigm, training a diffusion generative model solely on anechoic speech and formulating separation as a diffusion inverse problem. However, unconditional diffusion models lack speaker-level conditioning, they can capture local acoustic structure but produce temporally inconsistent speaker identities in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.24395","kind":"arxiv","version":2},"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/2509.24395/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":"2509.24395","created_at":"2026-08-03T01:11:58.026883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.24395v2","created_at":"2026-08-03T01:11:58.026883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.24395","created_at":"2026-08-03T01:11:58.026883+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWVKMLHS5D57","created_at":"2026-08-03T01:11:58.026883+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWVKMLHS5D57HW4S","created_at":"2026-08-03T01:11:58.026883+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWVKMLHS","created_at":"2026-08-03T01:11:58.026883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UWVKMLHS5D57HW4SEVAGYSPVB6","json":"https://pith.science/pith/UWVKMLHS5D57HW4SEVAGYSPVB6.json","graph_json":"https://pith.science/api/pith-number/UWVKMLHS5D57HW4SEVAGYSPVB6/graph.json","events_json":"https://pith.science/api/pith-number/UWVKMLHS5D57HW4SEVAGYSPVB6/events.json","paper":"https://pith.science/paper/UWVKMLHS"},"agent_actions":{"view_html":"https://pith.science/pith/UWVKMLHS5D57HW4SEVAGYSPVB6","download_json":"https://pith.science/pith/UWVKMLHS5D57HW4SEVAGYSPVB6.json","view_paper":"https://pith.science/paper/UWVKMLHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.24395&json=true","fetch_graph":"https://pith.science/api/pith-number/UWVKMLHS5D57HW4SEVAGYSPVB6/graph.json","fetch_events":"https://pith.science/api/pith-number/UWVKMLHS5D57HW4SEVAGYSPVB6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWVKMLHS5D57HW4SEVAGYSPVB6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWVKMLHS5D57HW4SEVAGYSPVB6/action/storage_attestation","attest_author":"https://pith.science/pith/UWVKMLHS5D57HW4SEVAGYSPVB6/action/author_attestation","sign_citation":"https://pith.science/pith/UWVKMLHS5D57HW4SEVAGYSPVB6/action/citation_signature","submit_replication":"https://pith.science/pith/UWVKMLHS5D57HW4SEVAGYSPVB6/action/replication_record"}},"created_at":"2026-08-03T01:11:58.026883+00:00","updated_at":"2026-08-03T01:11:58.026883+00:00"}