{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WBQWCC76HJMZ7BWSB3HOVENZN7","short_pith_number":"pith:WBQWCC76","schema_version":"1.0","canonical_sha256":"b061610bfe3a599f86d20eceea91b96fe801e808a8730c4e6e71e4d373d342cc","source":{"kind":"arxiv","id":"2502.07345","version":1},"attestation_state":"computed","paper":{"title":"Advanced Zero-Shot Text-to-Speech for Background Removal and Preservation with Controllable Masked Speech Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Leying Zhang, Wangyou Zhang, Yanmin Qian, Zhengyang Chen","submitted_at":"2025-02-11T08:17:07Z","abstract_excerpt":"The acoustic background plays a crucial role in natural conversation. It provides context and helps listeners understand the environment, but a strong background makes it difficult for listeners to understand spoken words. The appropriate handling of these backgrounds is situation-dependent: Although it may be necessary to remove background to ensure speech clarity, preserving the background is sometimes crucial to maintaining the contextual integrity of the speech. Despite recent advancements in zero-shot Text-to-Speech technologies, current systems often struggle with speech prompts containi"},"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":"2502.07345","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-11T08:17:07Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"2dbe192647bb65882b575ba3efd986a2ade8a8b5fa8185e90e8543453d8709a7","abstract_canon_sha256":"212c163b0ff55e683d06da9b88567c2e28f059bd6e08ef429f85b27361e00249"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:36.297508Z","signature_b64":"S+hwTp78s+xvItX9QqMTRSvHUG6KjXNRDY7hAayDQy0x+f0pFRIndv4+QPwNdJWVxFErOPpKLLEtL4ooaSS3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b061610bfe3a599f86d20eceea91b96fe801e808a8730c4e6e71e4d373d342cc","last_reissued_at":"2026-07-05T10:12:36.297033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:36.297033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advanced Zero-Shot Text-to-Speech for Background Removal and Preservation with Controllable Masked Speech Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Leying Zhang, Wangyou Zhang, Yanmin Qian, Zhengyang Chen","submitted_at":"2025-02-11T08:17:07Z","abstract_excerpt":"The acoustic background plays a crucial role in natural conversation. It provides context and helps listeners understand the environment, but a strong background makes it difficult for listeners to understand spoken words. The appropriate handling of these backgrounds is situation-dependent: Although it may be necessary to remove background to ensure speech clarity, preserving the background is sometimes crucial to maintaining the contextual integrity of the speech. Despite recent advancements in zero-shot Text-to-Speech technologies, current systems often struggle with speech prompts containi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07345","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/2502.07345/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":"2502.07345","created_at":"2026-07-05T10:12:36.297089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07345v1","created_at":"2026-07-05T10:12:36.297089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07345","created_at":"2026-07-05T10:12:36.297089+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBQWCC76HJMZ","created_at":"2026-07-05T10:12:36.297089+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBQWCC76HJMZ7BWS","created_at":"2026-07-05T10:12:36.297089+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBQWCC76","created_at":"2026-07-05T10:12:36.297089+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/WBQWCC76HJMZ7BWSB3HOVENZN7","json":"https://pith.science/pith/WBQWCC76HJMZ7BWSB3HOVENZN7.json","graph_json":"https://pith.science/api/pith-number/WBQWCC76HJMZ7BWSB3HOVENZN7/graph.json","events_json":"https://pith.science/api/pith-number/WBQWCC76HJMZ7BWSB3HOVENZN7/events.json","paper":"https://pith.science/paper/WBQWCC76"},"agent_actions":{"view_html":"https://pith.science/pith/WBQWCC76HJMZ7BWSB3HOVENZN7","download_json":"https://pith.science/pith/WBQWCC76HJMZ7BWSB3HOVENZN7.json","view_paper":"https://pith.science/paper/WBQWCC76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07345&json=true","fetch_graph":"https://pith.science/api/pith-number/WBQWCC76HJMZ7BWSB3HOVENZN7/graph.json","fetch_events":"https://pith.science/api/pith-number/WBQWCC76HJMZ7BWSB3HOVENZN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBQWCC76HJMZ7BWSB3HOVENZN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBQWCC76HJMZ7BWSB3HOVENZN7/action/storage_attestation","attest_author":"https://pith.science/pith/WBQWCC76HJMZ7BWSB3HOVENZN7/action/author_attestation","sign_citation":"https://pith.science/pith/WBQWCC76HJMZ7BWSB3HOVENZN7/action/citation_signature","submit_replication":"https://pith.science/pith/WBQWCC76HJMZ7BWSB3HOVENZN7/action/replication_record"}},"created_at":"2026-07-05T10:12:36.297089+00:00","updated_at":"2026-07-05T10:12:36.297089+00:00"}