{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6OOMKLUURZGQ3YZ2QUHCWHTRUU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"996cdfdeaeda70f5ab6d67852da8c007b858dcbd85d0751264d53581d0532087","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-03-31T00:37:15Z","title_canon_sha256":"95ddab5de4dad70024e0d67343ae4af64b98351d04ad3b72b3bb7700c506e4be"},"schema_version":"1.0","source":{"id":"2603.29097","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.29097","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"arxiv_version","alias_value":"2603.29097v2","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.29097","created_at":"2026-05-17T23:39:04Z"},{"alias_kind":"pith_short_12","alias_value":"6OOMKLUURZGQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6OOMKLUURZGQ3YZ2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6OOMKLUU","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:f9328df78b91e318813dcaf0cc0f7b48d7c60ff1b409468fa96b12cb77c3deca","target":"graph","created_at":"2026-05-17T23:39:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experimental results on WSJ0-{2,3,4,5}Mix, WHAMR!, and LibriCSS demonstrate consistent improvements across anechoic, noisy-reverberant, and real-recorded conditions in both single- and multi-channel settings, highlighting the effectiveness of TF-domain SepRe with correlation-based filter estimation for speech separation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the proposed asymmetric encoder-decoder with SepRe strategy and cross-speaker interaction in the decoder will reliably avoid information bottlenecks and yield better speaker discriminability than late-split architectures under adverse conditions, without the gains depending on dataset-specific tuning or post-hoc architectural choices."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SR-CorrNet introduces an asymmetric TF-domain architecture with separation-reconstruction strategy and correlation-to-filter estimation that yields consistent gains on WSJ0-Mix, WHAMR!, and LibriCSS under anechoic, noisy-reverberant, and real-recorded conditions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"SR-CorrNet separates speech by splitting coarse separation into the encoder and progressive reconstruction into a shared-weight decoder that interacts across speakers."}],"snapshot_sha256":"edf3a4d68f78da21e5d33975980b7107558cd774809cb2e0947fd54374d8aed6"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Speech separation in realistic acoustic environments remains challenging because overlapping speakers, background noise, and reverberation must be resolved simultaneously. Although recent time-frequency (TF) domain models have shown strong performance, most still rely on late-split architectures, where speaker disentanglement is deferred to the final stage, creating an information bottleneck and weakening discriminability under adverse conditions. To address this issue, we propose SR-CorrNet, an asymmetric encoder-decoder framework that introduces the separation-reconstruction (SepRe) strategy","authors_text":"Hyung-Min Park, Ui-Hyeop Shin","cross_cats":["cs.SD"],"headline":"SR-CorrNet separates speech by splitting coarse separation into the encoder and progressive reconstruction into a shared-weight decoder that interacts across speakers.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-03-31T00:37:15Z","title":"Asymmetric Encoder-Decoder Based on Time-Frequency Correlation for Speech Separation"},"references":{"count":79,"internal_anchors":0,"resolved_work":79,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"TasNet: time-domain audio separation network for real-time, single-channel speech separation,","work_id":"92026762-7c3d-4b91-8f94-2cc0eaa86251","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Conv-TasNet: Surpassing ideal time–frequency magnitude mask- ing for speech separation,","work_id":"2c10b83f-aa19-4a3c-8b4e-09553a379c35","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Dual-Path RNN: Efficient long sequence modeling for time-domain single-channel speech separation,","work_id":"8174ce5e-4aba-4966-b659-384472cd849f","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Attention is all you need in speech separation,","work_id":"b9ae55b7-b39c-4c6b-b4da-783227775cbd","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"TFPSNet: Time-frequency domain path scanning network for speech separation,","work_id":"25d4eb93-0d65-47ae-b8da-73d80cdc5a47","year":2022}],"snapshot_sha256":"f97fc82a667b1b9eea78ad1096c5549e2e24f26c579d0b3026ec3a50665a02f0"},"source":{"id":"2603.29097","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T06:34:25.998525Z","id":"85cfdbdc-aa2d-49f6-b763-d9bc3ec42054","model_set":{"reader":"grok-4.3"},"one_line_summary":"SR-CorrNet introduces an asymmetric TF-domain architecture with separation-reconstruction strategy and correlation-to-filter estimation that yields consistent gains on WSJ0-Mix, WHAMR!, and LibriCSS under anechoic, noisy-reverberant, and real-recorded conditions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"SR-CorrNet separates speech by splitting coarse separation into the encoder and progressive reconstruction into a shared-weight decoder that interacts across speakers.","strongest_claim":"Experimental results on WSJ0-{2,3,4,5}Mix, WHAMR!, and LibriCSS demonstrate consistent improvements across anechoic, noisy-reverberant, and real-recorded conditions in both single- and multi-channel settings, highlighting the effectiveness of TF-domain SepRe with correlation-based filter estimation for speech separation.","weakest_assumption":"That the proposed asymmetric encoder-decoder with SepRe strategy and cross-speaker interaction in the decoder will reliably avoid information bottlenecks and yield better speaker discriminability than late-split architectures under adverse conditions, without the gains depending on dataset-specific tuning or post-hoc architectural choices."}},"verdict_id":"85cfdbdc-aa2d-49f6-b763-d9bc3ec42054"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:21fd5a175b205eb6491f897e7e8939137e1557ac36f13c1d0cc7a843dd1aa505","target":"record","created_at":"2026-05-17T23:39:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"996cdfdeaeda70f5ab6d67852da8c007b858dcbd85d0751264d53581d0532087","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-03-31T00:37:15Z","title_canon_sha256":"95ddab5de4dad70024e0d67343ae4af64b98351d04ad3b72b3bb7700c506e4be"},"schema_version":"1.0","source":{"id":"2603.29097","kind":"arxiv","version":2}},"canonical_sha256":"f39cc52e948e4d0de33a850e2b1e71a52b436e20d857644a469d44aa349a26ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f39cc52e948e4d0de33a850e2b1e71a52b436e20d857644a469d44aa349a26ca","first_computed_at":"2026-05-17T23:39:04.352814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:04.352814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B/gmYqi7Os1j2cBvskgfYBPNHsrL/sen6SGhc2LZUMaLzgiiDdT1/PhfOKtAhGcvl0ftGkSlKgLNWH/mdKLIDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:04.353579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.29097","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21fd5a175b205eb6491f897e7e8939137e1557ac36f13c1d0cc7a843dd1aa505","sha256:f9328df78b91e318813dcaf0cc0f7b48d7c60ff1b409468fa96b12cb77c3deca"],"state_sha256":"4d89bcc6438da83b380a7415d58a6195fd9b90c59c56de391ac716adc56c8e8c"}