{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B6P3BNMYG4BAO6NHZDPJD4N363","short_pith_number":"pith:B6P3BNMY","schema_version":"1.0","canonical_sha256":"0f9fb0b59837020779a7c8de91f1bbf6fa6a1c879b5c501b84b2aea15480246d","source":{"kind":"arxiv","id":"2110.06467","version":5},"attestation_state":"computed","paper":{"title":"Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andong Li, Chengshi Zheng, Guochen Yu, Hui Wang, Yinuo Guo, Yutian Wang","submitted_at":"2021-10-13T03:03:49Z","abstract_excerpt":"Curriculum learning begins to thrive in the speech enhancement area, which decouples the original spectrum estimation task into multiple easier sub-tasks to achieve better performance. Motivated by that, we propose a dual-branch attention-in-attention transformer dubbed DB-AIAT to handle both coarse- and fine-grained regions of the spectrum in parallel. From a complementary perspective, a magnitude masking branch is proposed to coarsely estimate the overall magnitude spectrum, and simultaneously a complex refining branch is elaborately designed to compensate for the missing spectral details an"},"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":"2110.06467","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-13T03:03:49Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"917fa5bf7f386141c2d8c3e43dead71d5b5eec2ab4d7e067c1b4b84861ca1382","abstract_canon_sha256":"f23d04d21de99dcc08db07bde5b2ae1a4daa12224168c6ea3533280c34bb3a23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:31.632904Z","signature_b64":"oOj8/WYouShwoJs2mwhUgqYlpMiz4gZHZ2q/bhMXJuBN3gsUMB0GmLddmLJlinl/zooCTb3/j6BrWdb+DXQiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f9fb0b59837020779a7c8de91f1bbf6fa6a1c879b5c501b84b2aea15480246d","last_reissued_at":"2026-07-05T03:56:31.632420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:31.632420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andong Li, Chengshi Zheng, Guochen Yu, Hui Wang, Yinuo Guo, Yutian Wang","submitted_at":"2021-10-13T03:03:49Z","abstract_excerpt":"Curriculum learning begins to thrive in the speech enhancement area, which decouples the original spectrum estimation task into multiple easier sub-tasks to achieve better performance. Motivated by that, we propose a dual-branch attention-in-attention transformer dubbed DB-AIAT to handle both coarse- and fine-grained regions of the spectrum in parallel. From a complementary perspective, a magnitude masking branch is proposed to coarsely estimate the overall magnitude spectrum, and simultaneously a complex refining branch is elaborately designed to compensate for the missing spectral details an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06467","kind":"arxiv","version":5},"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/2110.06467/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":"2110.06467","created_at":"2026-07-05T03:56:31.632473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.06467v5","created_at":"2026-07-05T03:56:31.632473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06467","created_at":"2026-07-05T03:56:31.632473+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6P3BNMYG4BA","created_at":"2026-07-05T03:56:31.632473+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6P3BNMYG4BAO6NH","created_at":"2026-07-05T03:56:31.632473+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6P3BNMY","created_at":"2026-07-05T03:56:31.632473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.21003","citing_title":"Query-Based Asymmetric Modeling with Decoupled Input-Output Rates for Speech Restoration","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B6P3BNMYG4BAO6NHZDPJD4N363","json":"https://pith.science/pith/B6P3BNMYG4BAO6NHZDPJD4N363.json","graph_json":"https://pith.science/api/pith-number/B6P3BNMYG4BAO6NHZDPJD4N363/graph.json","events_json":"https://pith.science/api/pith-number/B6P3BNMYG4BAO6NHZDPJD4N363/events.json","paper":"https://pith.science/paper/B6P3BNMY"},"agent_actions":{"view_html":"https://pith.science/pith/B6P3BNMYG4BAO6NHZDPJD4N363","download_json":"https://pith.science/pith/B6P3BNMYG4BAO6NHZDPJD4N363.json","view_paper":"https://pith.science/paper/B6P3BNMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.06467&json=true","fetch_graph":"https://pith.science/api/pith-number/B6P3BNMYG4BAO6NHZDPJD4N363/graph.json","fetch_events":"https://pith.science/api/pith-number/B6P3BNMYG4BAO6NHZDPJD4N363/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6P3BNMYG4BAO6NHZDPJD4N363/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6P3BNMYG4BAO6NHZDPJD4N363/action/storage_attestation","attest_author":"https://pith.science/pith/B6P3BNMYG4BAO6NHZDPJD4N363/action/author_attestation","sign_citation":"https://pith.science/pith/B6P3BNMYG4BAO6NHZDPJD4N363/action/citation_signature","submit_replication":"https://pith.science/pith/B6P3BNMYG4BAO6NHZDPJD4N363/action/replication_record"}},"created_at":"2026-07-05T03:56:31.632473+00:00","updated_at":"2026-07-05T03:56:31.632473+00:00"}