{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6OOMKLUURZGQ3YZ2QUHCWHTRUU","short_pith_number":"pith:6OOMKLUU","schema_version":"1.0","canonical_sha256":"f39cc52e948e4d0de33a850e2b1e71a52b436e20d857644a469d44aa349a26ca","source":{"kind":"arxiv","id":"2603.29097","version":2},"attestation_state":"computed","paper":{"title":"Asymmetric Encoder-Decoder Based on Time-Frequency Correlation for Speech Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"SR-CorrNet separates speech by splitting coarse separation into the encoder and progressive reconstruction into a shared-weight decoder that interacts across speakers.","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hyung-Min Park, Ui-Hyeop Shin","submitted_at":"2026-03-31T00:37:15Z","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"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2603.29097","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-03-31T00:37:15Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"95ddab5de4dad70024e0d67343ae4af64b98351d04ad3b72b3bb7700c506e4be","abstract_canon_sha256":"996cdfdeaeda70f5ab6d67852da8c007b858dcbd85d0751264d53581d0532087"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:04.353579Z","signature_b64":"B/gmYqi7Os1j2cBvskgfYBPNHsrL/sen6SGhc2LZUMaLzgiiDdT1/PhfOKtAhGcvl0ftGkSlKgLNWH/mdKLIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f39cc52e948e4d0de33a850e2b1e71a52b436e20d857644a469d44aa349a26ca","last_reissued_at":"2026-05-17T23:39:04.352814Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:04.352814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asymmetric Encoder-Decoder Based on Time-Frequency Correlation for Speech Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"SR-CorrNet separates speech by splitting coarse separation into the encoder and progressive reconstruction into a shared-weight decoder that interacts across speakers.","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hyung-Min Park, Ui-Hyeop Shin","submitted_at":"2026-03-31T00:37:15Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SR-CorrNet separates speech by splitting coarse separation into the encoder and progressive reconstruction into a shared-weight decoder that interacts across speakers.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"edf3a4d68f78da21e5d33975980b7107558cd774809cb2e0947fd54374d8aed6"},"source":{"id":"2603.29097","kind":"arxiv","version":2},"verdict":{"id":"85cfdbdc-aa2d-49f6-b763-d9bc3ec42054","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T06:34:25.998525Z","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.","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","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.","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."},"references":{"count":79,"sample":[{"doi":"","year":2018,"title":"TasNet: time-domain audio separation network for real-time, single-channel speech separation,","work_id":"92026762-7c3d-4b91-8f94-2cc0eaa86251","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Conv-TasNet: Surpassing ideal time–frequency magnitude mask- ing for speech separation,","work_id":"2c10b83f-aa19-4a3c-8b4e-09553a379c35","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Dual-Path RNN: Efficient long sequence modeling for time-domain single-channel speech separation,","work_id":"8174ce5e-4aba-4966-b659-384472cd849f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Attention is all you need in speech separation,","work_id":"b9ae55b7-b39c-4c6b-b4da-783227775cbd","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"TFPSNet: Time-frequency domain path scanning network for speech separation,","work_id":"25d4eb93-0d65-47ae-b8da-73d80cdc5a47","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":79,"snapshot_sha256":"f97fc82a667b1b9eea78ad1096c5549e2e24f26c579d0b3026ec3a50665a02f0","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":"2603.29097","created_at":"2026-05-17T23:39:04.352944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.29097v2","created_at":"2026-05-17T23:39:04.352944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.29097","created_at":"2026-05-17T23:39:04.352944+00:00"},{"alias_kind":"pith_short_12","alias_value":"6OOMKLUURZGQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"6OOMKLUURZGQ3YZ2","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"6OOMKLUU","created_at":"2026-05-18T12:33:37.589309+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/6OOMKLUURZGQ3YZ2QUHCWHTRUU","json":"https://pith.science/pith/6OOMKLUURZGQ3YZ2QUHCWHTRUU.json","graph_json":"https://pith.science/api/pith-number/6OOMKLUURZGQ3YZ2QUHCWHTRUU/graph.json","events_json":"https://pith.science/api/pith-number/6OOMKLUURZGQ3YZ2QUHCWHTRUU/events.json","paper":"https://pith.science/paper/6OOMKLUU"},"agent_actions":{"view_html":"https://pith.science/pith/6OOMKLUURZGQ3YZ2QUHCWHTRUU","download_json":"https://pith.science/pith/6OOMKLUURZGQ3YZ2QUHCWHTRUU.json","view_paper":"https://pith.science/paper/6OOMKLUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.29097&json=true","fetch_graph":"https://pith.science/api/pith-number/6OOMKLUURZGQ3YZ2QUHCWHTRUU/graph.json","fetch_events":"https://pith.science/api/pith-number/6OOMKLUURZGQ3YZ2QUHCWHTRUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6OOMKLUURZGQ3YZ2QUHCWHTRUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6OOMKLUURZGQ3YZ2QUHCWHTRUU/action/storage_attestation","attest_author":"https://pith.science/pith/6OOMKLUURZGQ3YZ2QUHCWHTRUU/action/author_attestation","sign_citation":"https://pith.science/pith/6OOMKLUURZGQ3YZ2QUHCWHTRUU/action/citation_signature","submit_replication":"https://pith.science/pith/6OOMKLUURZGQ3YZ2QUHCWHTRUU/action/replication_record"}},"created_at":"2026-05-17T23:39:04.352944+00:00","updated_at":"2026-05-17T23:39:04.352944+00:00"}