{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CZ5EFEQXF56VA7OIRDL3FX4GSV","short_pith_number":"pith:CZ5EFEQX","schema_version":"1.0","canonical_sha256":"167a4292172f7d507dc888d7b2df8695410340453ea0d9039bf39075f8a036f6","source":{"kind":"arxiv","id":"2506.09874","version":2},"attestation_state":"computed","paper":{"title":"UmbraTTS: Adapting Text-to-Speech to Environmental Contexts with Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Asaf Buchnick, Aviv Navon, Aviv Shamsian, Gil Hetz, Hilit Segev, Joseph Keshet, Menachem Pirchi, Neta Glazer, Yael Segal","submitted_at":"2025-06-11T15:43:08Z","abstract_excerpt":"Recent advances in Text-to-Speech (TTS) have enabled highly natural speech synthesis, yet integrating speech with complex background environments remains challenging. We introduce UmbraTTS, a flow-matching based TTS model that jointly generates both speech and environmental audio, conditioned on text and acoustic context. Our model allows fine-grained control over background volume and produces diverse, coherent, and context-aware audio scenes. A key challenge is the lack of data with speech and background audio aligned in natural context. To overcome the lack of paired training data, we propo"},"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":"2506.09874","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-11T15:43:08Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"09cca03e35d715b68621a7b279ff3c565f5f552a69afa4233065c8d9511e2564","abstract_canon_sha256":"4d6b3690fb63cb10bec0ec635f1f9cdf81fcc30ba7482a7ec7198a302e7199fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:14.346426Z","signature_b64":"nq+eV3S68jxZm2IYMKc/JNhKBur+X2WiMBd/mMJfy3L3fwovK/t0wpY9r1K3IFqU+Z0I3LB29gPKl07SoVW+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"167a4292172f7d507dc888d7b2df8695410340453ea0d9039bf39075f8a036f6","last_reissued_at":"2026-07-05T11:35:14.345883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:14.345883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UmbraTTS: Adapting Text-to-Speech to Environmental Contexts with Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Asaf Buchnick, Aviv Navon, Aviv Shamsian, Gil Hetz, Hilit Segev, Joseph Keshet, Menachem Pirchi, Neta Glazer, Yael Segal","submitted_at":"2025-06-11T15:43:08Z","abstract_excerpt":"Recent advances in Text-to-Speech (TTS) have enabled highly natural speech synthesis, yet integrating speech with complex background environments remains challenging. We introduce UmbraTTS, a flow-matching based TTS model that jointly generates both speech and environmental audio, conditioned on text and acoustic context. Our model allows fine-grained control over background volume and produces diverse, coherent, and context-aware audio scenes. A key challenge is the lack of data with speech and background audio aligned in natural context. To overcome the lack of paired training data, we propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09874","kind":"arxiv","version":2},"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/2506.09874/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":"2506.09874","created_at":"2026-07-05T11:35:14.345954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09874v2","created_at":"2026-07-05T11:35:14.345954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09874","created_at":"2026-07-05T11:35:14.345954+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZ5EFEQXF56V","created_at":"2026-07-05T11:35:14.345954+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZ5EFEQXF56VA7OI","created_at":"2026-07-05T11:35:14.345954+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZ5EFEQX","created_at":"2026-07-05T11:35:14.345954+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30965","citing_title":"ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZ5EFEQXF56VA7OIRDL3FX4GSV","json":"https://pith.science/pith/CZ5EFEQXF56VA7OIRDL3FX4GSV.json","graph_json":"https://pith.science/api/pith-number/CZ5EFEQXF56VA7OIRDL3FX4GSV/graph.json","events_json":"https://pith.science/api/pith-number/CZ5EFEQXF56VA7OIRDL3FX4GSV/events.json","paper":"https://pith.science/paper/CZ5EFEQX"},"agent_actions":{"view_html":"https://pith.science/pith/CZ5EFEQXF56VA7OIRDL3FX4GSV","download_json":"https://pith.science/pith/CZ5EFEQXF56VA7OIRDL3FX4GSV.json","view_paper":"https://pith.science/paper/CZ5EFEQX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09874&json=true","fetch_graph":"https://pith.science/api/pith-number/CZ5EFEQXF56VA7OIRDL3FX4GSV/graph.json","fetch_events":"https://pith.science/api/pith-number/CZ5EFEQXF56VA7OIRDL3FX4GSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZ5EFEQXF56VA7OIRDL3FX4GSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZ5EFEQXF56VA7OIRDL3FX4GSV/action/storage_attestation","attest_author":"https://pith.science/pith/CZ5EFEQXF56VA7OIRDL3FX4GSV/action/author_attestation","sign_citation":"https://pith.science/pith/CZ5EFEQXF56VA7OIRDL3FX4GSV/action/citation_signature","submit_replication":"https://pith.science/pith/CZ5EFEQXF56VA7OIRDL3FX4GSV/action/replication_record"}},"created_at":"2026-07-05T11:35:14.345954+00:00","updated_at":"2026-07-05T11:35:14.345954+00:00"}