{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SI435TWOMVGL36NJ5OAC4ZALN5","short_pith_number":"pith:SI435TWO","schema_version":"1.0","canonical_sha256":"9239becece654cbdf9a9eb802e640b6f5b4ed9e353e6cd520d7097c5fc0d0f9f","source":{"kind":"arxiv","id":"2310.08981","version":3},"attestation_state":"computed","paper":{"title":"Low-latency Speech Enhancement via Speech Token Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Huaying Xue, Xiulian Peng, Yan Lu","submitted_at":"2023-10-13T09:57:09Z","abstract_excerpt":"Existing deep learning based speech enhancement mainly employ a data-driven approach, which leverage large amounts of data with a variety of noise types to achieve noise removal from noisy signal. However, the high dependence on the data limits its generalization on the unseen complex noises in real-life environment. In this paper, we focus on the low-latency scenario and regard speech enhancement as a speech generation problem conditioned on the noisy signal, where we generate clean speech instead of identifying and removing noises. Specifically, we propose a conditional generative framework "},"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":"2310.08981","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-13T09:57:09Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"d4b6cc54dae33a6876f512d02aaa25071f8e59c080b32b567e291dd5b10ab323","abstract_canon_sha256":"e76ac2c7d1a244af31b5f982445168ac92a102959e67f4b4f06b8781bbfd6634"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:24.348969Z","signature_b64":"Rv/rLBrBefhkHf7arqBFYZUnyONWK7Lk+ouF5HwJxWk/7iEWdK0D+rU78kvBLtWQjz6halMSQp9ElkJdJrtsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9239becece654cbdf9a9eb802e640b6f5b4ed9e353e6cd520d7097c5fc0d0f9f","last_reissued_at":"2026-07-05T07:36:24.348560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:24.348560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-latency Speech Enhancement via Speech Token Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Huaying Xue, Xiulian Peng, Yan Lu","submitted_at":"2023-10-13T09:57:09Z","abstract_excerpt":"Existing deep learning based speech enhancement mainly employ a data-driven approach, which leverage large amounts of data with a variety of noise types to achieve noise removal from noisy signal. However, the high dependence on the data limits its generalization on the unseen complex noises in real-life environment. In this paper, we focus on the low-latency scenario and regard speech enhancement as a speech generation problem conditioned on the noisy signal, where we generate clean speech instead of identifying and removing noises. Specifically, we propose a conditional generative framework "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08981","kind":"arxiv","version":3},"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/2310.08981/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":"2310.08981","created_at":"2026-07-05T07:36:24.348611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08981v3","created_at":"2026-07-05T07:36:24.348611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08981","created_at":"2026-07-05T07:36:24.348611+00:00"},{"alias_kind":"pith_short_12","alias_value":"SI435TWOMVGL","created_at":"2026-07-05T07:36:24.348611+00:00"},{"alias_kind":"pith_short_16","alias_value":"SI435TWOMVGL36NJ","created_at":"2026-07-05T07:36:24.348611+00:00"},{"alias_kind":"pith_short_8","alias_value":"SI435TWO","created_at":"2026-07-05T07:36:24.348611+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/SI435TWOMVGL36NJ5OAC4ZALN5","json":"https://pith.science/pith/SI435TWOMVGL36NJ5OAC4ZALN5.json","graph_json":"https://pith.science/api/pith-number/SI435TWOMVGL36NJ5OAC4ZALN5/graph.json","events_json":"https://pith.science/api/pith-number/SI435TWOMVGL36NJ5OAC4ZALN5/events.json","paper":"https://pith.science/paper/SI435TWO"},"agent_actions":{"view_html":"https://pith.science/pith/SI435TWOMVGL36NJ5OAC4ZALN5","download_json":"https://pith.science/pith/SI435TWOMVGL36NJ5OAC4ZALN5.json","view_paper":"https://pith.science/paper/SI435TWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08981&json=true","fetch_graph":"https://pith.science/api/pith-number/SI435TWOMVGL36NJ5OAC4ZALN5/graph.json","fetch_events":"https://pith.science/api/pith-number/SI435TWOMVGL36NJ5OAC4ZALN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SI435TWOMVGL36NJ5OAC4ZALN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SI435TWOMVGL36NJ5OAC4ZALN5/action/storage_attestation","attest_author":"https://pith.science/pith/SI435TWOMVGL36NJ5OAC4ZALN5/action/author_attestation","sign_citation":"https://pith.science/pith/SI435TWOMVGL36NJ5OAC4ZALN5/action/citation_signature","submit_replication":"https://pith.science/pith/SI435TWOMVGL36NJ5OAC4ZALN5/action/replication_record"}},"created_at":"2026-07-05T07:36:24.348611+00:00","updated_at":"2026-07-05T07:36:24.348611+00:00"}