{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QC77QTUK2R2Y6BMT62K4BYC4PT","short_pith_number":"pith:QC77QTUK","schema_version":"1.0","canonical_sha256":"80bff84e8ad4758f0593f695c0e05c7cf4e764d285e1d4e2c28205dbaa0f2d9f","source":{"kind":"arxiv","id":"2507.02562","version":1},"attestation_state":"computed","paper":{"title":"Multi-Utterance Speech Separation and Association Trained on Short Segments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Archontis Politis, Konstantinos Drossos, Tuomas Virtanen, Yuzhu Wang","submitted_at":"2025-07-03T12:12:34Z","abstract_excerpt":"Current deep neural network (DNN) based speech separation faces a fundamental challenge -- while the models need to be trained on short segments due to computational constraints, real-world applications typically require processing significantly longer recordings with multiple utterances per speaker than seen during training. In this paper, we investigate how existing approaches perform in this challenging scenario and propose a frequency-temporal recurrent neural network (FTRNN) that effectively bridges this gap. Our FTRNN employs a full-band module to model frequency dependencies within each"},"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":"2507.02562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-03T12:12:34Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"7a9a5f308d8f62da081924b6b08e1811b1bc2005a29a96e709b42a0b337e5237","abstract_canon_sha256":"35c080ed44869ac05fbc092b2cc92b70b86d19efc0ab57f7d5e2274338f2c846"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:30.922651Z","signature_b64":"Nz20Pvg81CarVX9o6TQjvWCoPPq7jTkmPbsgGMqHvsVziqUJSQQTtWWVx1xvLUizMfiuuQf/3T/PYU53OTlgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80bff84e8ad4758f0593f695c0e05c7cf4e764d285e1d4e2c28205dbaa0f2d9f","last_reissued_at":"2026-07-05T11:31:30.922147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:30.922147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Utterance Speech Separation and Association Trained on Short Segments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Archontis Politis, Konstantinos Drossos, Tuomas Virtanen, Yuzhu Wang","submitted_at":"2025-07-03T12:12:34Z","abstract_excerpt":"Current deep neural network (DNN) based speech separation faces a fundamental challenge -- while the models need to be trained on short segments due to computational constraints, real-world applications typically require processing significantly longer recordings with multiple utterances per speaker than seen during training. In this paper, we investigate how existing approaches perform in this challenging scenario and propose a frequency-temporal recurrent neural network (FTRNN) that effectively bridges this gap. Our FTRNN employs a full-band module to model frequency dependencies within each"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02562","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/2507.02562/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":"2507.02562","created_at":"2026-07-05T11:31:30.922207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02562v1","created_at":"2026-07-05T11:31:30.922207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02562","created_at":"2026-07-05T11:31:30.922207+00:00"},{"alias_kind":"pith_short_12","alias_value":"QC77QTUK2R2Y","created_at":"2026-07-05T11:31:30.922207+00:00"},{"alias_kind":"pith_short_16","alias_value":"QC77QTUK2R2Y6BMT","created_at":"2026-07-05T11:31:30.922207+00:00"},{"alias_kind":"pith_short_8","alias_value":"QC77QTUK","created_at":"2026-07-05T11:31:30.922207+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/QC77QTUK2R2Y6BMT62K4BYC4PT","json":"https://pith.science/pith/QC77QTUK2R2Y6BMT62K4BYC4PT.json","graph_json":"https://pith.science/api/pith-number/QC77QTUK2R2Y6BMT62K4BYC4PT/graph.json","events_json":"https://pith.science/api/pith-number/QC77QTUK2R2Y6BMT62K4BYC4PT/events.json","paper":"https://pith.science/paper/QC77QTUK"},"agent_actions":{"view_html":"https://pith.science/pith/QC77QTUK2R2Y6BMT62K4BYC4PT","download_json":"https://pith.science/pith/QC77QTUK2R2Y6BMT62K4BYC4PT.json","view_paper":"https://pith.science/paper/QC77QTUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02562&json=true","fetch_graph":"https://pith.science/api/pith-number/QC77QTUK2R2Y6BMT62K4BYC4PT/graph.json","fetch_events":"https://pith.science/api/pith-number/QC77QTUK2R2Y6BMT62K4BYC4PT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QC77QTUK2R2Y6BMT62K4BYC4PT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QC77QTUK2R2Y6BMT62K4BYC4PT/action/storage_attestation","attest_author":"https://pith.science/pith/QC77QTUK2R2Y6BMT62K4BYC4PT/action/author_attestation","sign_citation":"https://pith.science/pith/QC77QTUK2R2Y6BMT62K4BYC4PT/action/citation_signature","submit_replication":"https://pith.science/pith/QC77QTUK2R2Y6BMT62K4BYC4PT/action/replication_record"}},"created_at":"2026-07-05T11:31:30.922207+00:00","updated_at":"2026-07-05T11:31:30.922207+00:00"}