{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VC2QATMDRV2OA3NMJPUH23BB3O","short_pith_number":"pith:VC2QATMD","schema_version":"1.0","canonical_sha256":"a8b5004d838d74e06dac4be87d6c21dbaff9185ab8c4d950c072212069924aba","source":{"kind":"arxiv","id":"1711.00541","version":2},"attestation_state":"computed","paper":{"title":"TasNet: time-domain audio separation network for real-time, single-channel speech separation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.NE","eess.AS"],"primary_cat":"cs.SD","authors_text":"Nima Mesgarani, Yi Luo","submitted_at":"2017-11-01T21:19:22Z","abstract_excerpt":"Robust speech processing in multi-talker environments requires effective speech separation. Recent deep learning systems have made significant progress toward solving this problem, yet it remains challenging particularly in real-time, short latency applications. Most methods attempt to construct a mask for each source in time-frequency representation of the mixture signal which is not necessarily an optimal representation for speech separation. In addition, time-frequency decomposition results in inherent problems such as phase/magnitude decoupling and long time window which is required to ach"},"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":"1711.00541","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2017-11-01T21:19:22Z","cross_cats_sorted":["cs.LG","cs.MM","cs.NE","eess.AS"],"title_canon_sha256":"fc1d056f465fb4deee6d63e0eb77fd2a75054ef7def7a03f0d8b8ef03d9c78c1","abstract_canon_sha256":"df9b888c1823cf188438b9f3ef58919e972bea646b5c10b146499b5ad543cb22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:09.391808Z","signature_b64":"OwR4uGLzjoLVrAMTqkMxZquoQQOb8RBF9dBUN7d2lwTJK7FFMj9/TYkRy2PVNMLk85jvZO4Wsz/TR4OWM4EcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8b5004d838d74e06dac4be87d6c21dbaff9185ab8c4d950c072212069924aba","last_reissued_at":"2026-05-18T00:18:09.391175Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:09.391175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TasNet: time-domain audio separation network for real-time, single-channel speech separation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.NE","eess.AS"],"primary_cat":"cs.SD","authors_text":"Nima Mesgarani, Yi Luo","submitted_at":"2017-11-01T21:19:22Z","abstract_excerpt":"Robust speech processing in multi-talker environments requires effective speech separation. Recent deep learning systems have made significant progress toward solving this problem, yet it remains challenging particularly in real-time, short latency applications. Most methods attempt to construct a mask for each source in time-frequency representation of the mixture signal which is not necessarily an optimal representation for speech separation. In addition, time-frequency decomposition results in inherent problems such as phase/magnitude decoupling and long time window which is required to ach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00541","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":""},"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":"1711.00541","created_at":"2026-05-18T00:18:09.391255+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.00541v2","created_at":"2026-05-18T00:18:09.391255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00541","created_at":"2026-05-18T00:18:09.391255+00:00"},{"alias_kind":"pith_short_12","alias_value":"VC2QATMDRV2O","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VC2QATMDRV2OA3NM","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VC2QATMD","created_at":"2026-05-18T12:31:49.984773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.10975","citing_title":"Survey of End-to-End Multi-Speaker Automatic Speech Recognition for Monaural Audio","ref_index":2017,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VC2QATMDRV2OA3NMJPUH23BB3O","json":"https://pith.science/pith/VC2QATMDRV2OA3NMJPUH23BB3O.json","graph_json":"https://pith.science/api/pith-number/VC2QATMDRV2OA3NMJPUH23BB3O/graph.json","events_json":"https://pith.science/api/pith-number/VC2QATMDRV2OA3NMJPUH23BB3O/events.json","paper":"https://pith.science/paper/VC2QATMD"},"agent_actions":{"view_html":"https://pith.science/pith/VC2QATMDRV2OA3NMJPUH23BB3O","download_json":"https://pith.science/pith/VC2QATMDRV2OA3NMJPUH23BB3O.json","view_paper":"https://pith.science/paper/VC2QATMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.00541&json=true","fetch_graph":"https://pith.science/api/pith-number/VC2QATMDRV2OA3NMJPUH23BB3O/graph.json","fetch_events":"https://pith.science/api/pith-number/VC2QATMDRV2OA3NMJPUH23BB3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VC2QATMDRV2OA3NMJPUH23BB3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VC2QATMDRV2OA3NMJPUH23BB3O/action/storage_attestation","attest_author":"https://pith.science/pith/VC2QATMDRV2OA3NMJPUH23BB3O/action/author_attestation","sign_citation":"https://pith.science/pith/VC2QATMDRV2OA3NMJPUH23BB3O/action/citation_signature","submit_replication":"https://pith.science/pith/VC2QATMDRV2OA3NMJPUH23BB3O/action/replication_record"}},"created_at":"2026-05-18T00:18:09.391255+00:00","updated_at":"2026-05-18T00:18:09.391255+00:00"}