{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QPOIA7ESDYMGIHDCUB4YZOGEPW","short_pith_number":"pith:QPOIA7ES","schema_version":"1.0","canonical_sha256":"83dc807c921e18641c62a0798cb8c47d87738da53e2001b75f8988433b46ad19","source":{"kind":"arxiv","id":"2505.13094","version":1},"attestation_state":"computed","paper":{"title":"Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guo Chen, Kai Li, Runxuan Yang, Xiaolin Hu","submitted_at":"2025-05-19T13:25:51Z","abstract_excerpt":"Existing causal speech separation models often underperform compared to non-causal models due to difficulties in retaining historical information. To address this, we propose the Time-Frequency Attention Cache Memory (TFACM) model, which effectively captures spatio-temporal relationships through an attention mechanism and cache memory (CM) for historical information storage. In TFACM, an LSTM layer captures frequency-relative positions, while causal modeling is applied to the time dimension using local and global representations. The CM module stores past information, and the causal attention "},"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":"2505.13094","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-19T13:25:51Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"4fb922dcc8a664c3b7a1ea9e655989c9d57e8d531342c49954653a435dc42c96","abstract_canon_sha256":"acb23a9bba8ca92535d1c0b862e2cb32e6331edba0667c0812511075a9bcefff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:14.858375Z","signature_b64":"xDjI+KZBipxt5tuCiF2eokeaLkW0/bOLVCb5wmv9sP8oy4l1CfM9QgGr+3tjoGiBGLJc3xWs8QpKnog6DvsiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83dc807c921e18641c62a0798cb8c47d87738da53e2001b75f8988433b46ad19","last_reissued_at":"2026-07-05T11:05:14.857907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:14.857907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guo Chen, Kai Li, Runxuan Yang, Xiaolin Hu","submitted_at":"2025-05-19T13:25:51Z","abstract_excerpt":"Existing causal speech separation models often underperform compared to non-causal models due to difficulties in retaining historical information. To address this, we propose the Time-Frequency Attention Cache Memory (TFACM) model, which effectively captures spatio-temporal relationships through an attention mechanism and cache memory (CM) for historical information storage. In TFACM, an LSTM layer captures frequency-relative positions, while causal modeling is applied to the time dimension using local and global representations. The CM module stores past information, and the causal attention "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13094","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/2505.13094/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":"2505.13094","created_at":"2026-07-05T11:05:14.857962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13094v1","created_at":"2026-07-05T11:05:14.857962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13094","created_at":"2026-07-05T11:05:14.857962+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPOIA7ESDYMG","created_at":"2026-07-05T11:05:14.857962+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPOIA7ESDYMGIHDC","created_at":"2026-07-05T11:05:14.857962+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPOIA7ES","created_at":"2026-07-05T11:05:14.857962+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10046","citing_title":"Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPOIA7ESDYMGIHDCUB4YZOGEPW","json":"https://pith.science/pith/QPOIA7ESDYMGIHDCUB4YZOGEPW.json","graph_json":"https://pith.science/api/pith-number/QPOIA7ESDYMGIHDCUB4YZOGEPW/graph.json","events_json":"https://pith.science/api/pith-number/QPOIA7ESDYMGIHDCUB4YZOGEPW/events.json","paper":"https://pith.science/paper/QPOIA7ES"},"agent_actions":{"view_html":"https://pith.science/pith/QPOIA7ESDYMGIHDCUB4YZOGEPW","download_json":"https://pith.science/pith/QPOIA7ESDYMGIHDCUB4YZOGEPW.json","view_paper":"https://pith.science/paper/QPOIA7ES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13094&json=true","fetch_graph":"https://pith.science/api/pith-number/QPOIA7ESDYMGIHDCUB4YZOGEPW/graph.json","fetch_events":"https://pith.science/api/pith-number/QPOIA7ESDYMGIHDCUB4YZOGEPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPOIA7ESDYMGIHDCUB4YZOGEPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPOIA7ESDYMGIHDCUB4YZOGEPW/action/storage_attestation","attest_author":"https://pith.science/pith/QPOIA7ESDYMGIHDCUB4YZOGEPW/action/author_attestation","sign_citation":"https://pith.science/pith/QPOIA7ESDYMGIHDCUB4YZOGEPW/action/citation_signature","submit_replication":"https://pith.science/pith/QPOIA7ESDYMGIHDCUB4YZOGEPW/action/replication_record"}},"created_at":"2026-07-05T11:05:14.857962+00:00","updated_at":"2026-07-05T11:05:14.857962+00:00"}