{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z6YUVSHYKCG34PTSLA447PI4EJ","short_pith_number":"pith:Z6YUVSHY","schema_version":"1.0","canonical_sha256":"cfb14ac8f8508dbe3e725839cfbd1c2243fd6ac7125993fb1de07aafd5175bbd","source":{"kind":"arxiv","id":"2502.02942","version":1},"attestation_state":"computed","paper":{"title":"GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chen Chen, EngSiong Chng, Hexin Liu, Jixun Yao, Lei Xie, Yuchen Hu","submitted_at":"2025-02-05T07:14:39Z","abstract_excerpt":"Semantic information refers to the meaning conveyed through words, phrases, and contextual relationships within a given linguistic structure. Humans can leverage semantic information, such as familiar linguistic patterns and contextual cues, to reconstruct incomplete or masked speech signals in noisy environments. However, existing speech enhancement (SE) approaches often overlook the rich semantic information embedded in speech, which is crucial for improving intelligibility, speaker consistency, and overall quality of enhanced speech signals. To enrich the SE model with semantic information,"},"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":"2502.02942","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-05T07:14:39Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"e1a164f3d4d5f67c514fb698f8a11c14f762b78b5e26cd756fe735275c3d6423","abstract_canon_sha256":"97a92421b32b7b9a2b283714af39131f7943a816d5c93968b51160fd0ebf64eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:57.195634Z","signature_b64":"t/rtXS8NWyHKZGGmj8JSxGlumNg0juPPIGZVoo3rfvnk8aZPEVENdfdKB77syfJeUc3JSlVCULjvoSCm7NvyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfb14ac8f8508dbe3e725839cfbd1c2243fd6ac7125993fb1de07aafd5175bbd","last_reissued_at":"2026-07-05T10:09:57.195183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:57.195183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chen Chen, EngSiong Chng, Hexin Liu, Jixun Yao, Lei Xie, Yuchen Hu","submitted_at":"2025-02-05T07:14:39Z","abstract_excerpt":"Semantic information refers to the meaning conveyed through words, phrases, and contextual relationships within a given linguistic structure. Humans can leverage semantic information, such as familiar linguistic patterns and contextual cues, to reconstruct incomplete or masked speech signals in noisy environments. However, existing speech enhancement (SE) approaches often overlook the rich semantic information embedded in speech, which is crucial for improving intelligibility, speaker consistency, and overall quality of enhanced speech signals. To enrich the SE model with semantic information,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02942","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/2502.02942/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":"2502.02942","created_at":"2026-07-05T10:09:57.195235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02942v1","created_at":"2026-07-05T10:09:57.195235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02942","created_at":"2026-07-05T10:09:57.195235+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6YUVSHYKCG3","created_at":"2026-07-05T10:09:57.195235+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6YUVSHYKCG34PTS","created_at":"2026-07-05T10:09:57.195235+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6YUVSHY","created_at":"2026-07-05T10:09:57.195235+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.24437","citing_title":"SwitchCodec: A High-Fidelity Nerual Audio Codec With Sparse Quantization","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14606","citing_title":"UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6YUVSHYKCG34PTSLA447PI4EJ","json":"https://pith.science/pith/Z6YUVSHYKCG34PTSLA447PI4EJ.json","graph_json":"https://pith.science/api/pith-number/Z6YUVSHYKCG34PTSLA447PI4EJ/graph.json","events_json":"https://pith.science/api/pith-number/Z6YUVSHYKCG34PTSLA447PI4EJ/events.json","paper":"https://pith.science/paper/Z6YUVSHY"},"agent_actions":{"view_html":"https://pith.science/pith/Z6YUVSHYKCG34PTSLA447PI4EJ","download_json":"https://pith.science/pith/Z6YUVSHYKCG34PTSLA447PI4EJ.json","view_paper":"https://pith.science/paper/Z6YUVSHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02942&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6YUVSHYKCG34PTSLA447PI4EJ/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6YUVSHYKCG34PTSLA447PI4EJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6YUVSHYKCG34PTSLA447PI4EJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6YUVSHYKCG34PTSLA447PI4EJ/action/storage_attestation","attest_author":"https://pith.science/pith/Z6YUVSHYKCG34PTSLA447PI4EJ/action/author_attestation","sign_citation":"https://pith.science/pith/Z6YUVSHYKCG34PTSLA447PI4EJ/action/citation_signature","submit_replication":"https://pith.science/pith/Z6YUVSHYKCG34PTSLA447PI4EJ/action/replication_record"}},"created_at":"2026-07-05T10:09:57.195235+00:00","updated_at":"2026-07-05T10:09:57.195235+00:00"}