{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SA54XXT5MAVNRCXN5W4H6X5UBB","short_pith_number":"pith:SA54XXT5","schema_version":"1.0","canonical_sha256":"903bcbde7d602ad88aededb87f5fb40857f2b232e31a81c4d7b61ae570bb29f2","source":{"kind":"arxiv","id":"2505.13843","version":1},"attestation_state":"computed","paper":{"title":"A Semantic Information-based Hierarchical Speech Enhancement Method Using Factorized Codec and Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Canan Huang, Chao Zhang, Desheng Hu, Jingguang Tian, Xinhui Hu, Yang Xiang","submitted_at":"2025-05-20T02:38:29Z","abstract_excerpt":"Most current speech enhancement (SE) methods recover clean speech from noisy inputs by directly estimating time-frequency masks or spectrums. However, these approaches often neglect the distinct attributes, such as semantic content and acoustic details, inherent in speech signals, which can hinder performance in downstream tasks. Moreover, their effectiveness tends to degrade in complex acoustic environments. To overcome these challenges, we propose a novel, semantic information-based, step-by-step factorized SE method using factorized codec and diffusion model. Unlike traditional SE methods, "},"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":"2505.13843","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-20T02:38:29Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"49afb5b625ce52faef4cc4b7ca4695ae779fffa6825e13e32b14f16b59b23bc4","abstract_canon_sha256":"f646acb18eccc335c32a4685427c8885288a79041102d77710f020c085f264be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:51.880755Z","signature_b64":"rx9dF0IALolW54vLsTLdJKYDuJPw83wzdXPrdwgnOikCpOSVFAb5KIT8OSHuYz0PBR6fyqnCYZyUExRBjT0kCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"903bcbde7d602ad88aededb87f5fb40857f2b232e31a81c4d7b61ae570bb29f2","last_reissued_at":"2026-07-05T11:05:51.880239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:51.880239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Semantic Information-based Hierarchical Speech Enhancement Method Using Factorized Codec and Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Canan Huang, Chao Zhang, Desheng Hu, Jingguang Tian, Xinhui Hu, Yang Xiang","submitted_at":"2025-05-20T02:38:29Z","abstract_excerpt":"Most current speech enhancement (SE) methods recover clean speech from noisy inputs by directly estimating time-frequency masks or spectrums. However, these approaches often neglect the distinct attributes, such as semantic content and acoustic details, inherent in speech signals, which can hinder performance in downstream tasks. Moreover, their effectiveness tends to degrade in complex acoustic environments. To overcome these challenges, we propose a novel, semantic information-based, step-by-step factorized SE method using factorized codec and diffusion model. Unlike traditional SE methods, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13843","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/2505.13843/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":"2505.13843","created_at":"2026-07-05T11:05:51.880305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13843v1","created_at":"2026-07-05T11:05:51.880305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13843","created_at":"2026-07-05T11:05:51.880305+00:00"},{"alias_kind":"pith_short_12","alias_value":"SA54XXT5MAVN","created_at":"2026-07-05T11:05:51.880305+00:00"},{"alias_kind":"pith_short_16","alias_value":"SA54XXT5MAVNRCXN","created_at":"2026-07-05T11:05:51.880305+00:00"},{"alias_kind":"pith_short_8","alias_value":"SA54XXT5","created_at":"2026-07-05T11:05:51.880305+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13843","citing_title":"A Semantic Information-based Hierarchical Speech Enhancement Method Using Factorized Codec and Diffusion Model","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SA54XXT5MAVNRCXN5W4H6X5UBB","json":"https://pith.science/pith/SA54XXT5MAVNRCXN5W4H6X5UBB.json","graph_json":"https://pith.science/api/pith-number/SA54XXT5MAVNRCXN5W4H6X5UBB/graph.json","events_json":"https://pith.science/api/pith-number/SA54XXT5MAVNRCXN5W4H6X5UBB/events.json","paper":"https://pith.science/paper/SA54XXT5"},"agent_actions":{"view_html":"https://pith.science/pith/SA54XXT5MAVNRCXN5W4H6X5UBB","download_json":"https://pith.science/pith/SA54XXT5MAVNRCXN5W4H6X5UBB.json","view_paper":"https://pith.science/paper/SA54XXT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13843&json=true","fetch_graph":"https://pith.science/api/pith-number/SA54XXT5MAVNRCXN5W4H6X5UBB/graph.json","fetch_events":"https://pith.science/api/pith-number/SA54XXT5MAVNRCXN5W4H6X5UBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SA54XXT5MAVNRCXN5W4H6X5UBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SA54XXT5MAVNRCXN5W4H6X5UBB/action/storage_attestation","attest_author":"https://pith.science/pith/SA54XXT5MAVNRCXN5W4H6X5UBB/action/author_attestation","sign_citation":"https://pith.science/pith/SA54XXT5MAVNRCXN5W4H6X5UBB/action/citation_signature","submit_replication":"https://pith.science/pith/SA54XXT5MAVNRCXN5W4H6X5UBB/action/replication_record"}},"created_at":"2026-07-05T11:05:51.880305+00:00","updated_at":"2026-07-05T11:05:51.880305+00:00"}