{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CZ5EFEQXF56VA7OIRDL3FX4GSV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4d6b3690fb63cb10bec0ec635f1f9cdf81fcc30ba7482a7ec7198a302e7199fd","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-11T15:43:08Z","title_canon_sha256":"09cca03e35d715b68621a7b279ff3c565f5f552a69afa4233065c8d9511e2564"},"schema_version":"1.0","source":{"id":"2506.09874","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09874","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09874v2","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09874","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"pith_short_12","alias_value":"CZ5EFEQXF56V","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"pith_short_16","alias_value":"CZ5EFEQXF56VA7OI","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"pith_short_8","alias_value":"CZ5EFEQX","created_at":"2026-07-05T11:35:14Z"}],"graph_snapshots":[{"event_id":"sha256:971063def4cf4d477639cbc3a4f1dcbc4104a69e924413069ea4232fe64c592a","target":"graph","created_at":"2026-07-05T11:35:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.09874/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Asaf Buchnick, Aviv Navon, Aviv Shamsian, Gil Hetz, Hilit Segev, Joseph Keshet, Menachem Pirchi, Neta Glazer, Yael Segal","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-11T15:43:08Z","title":"UmbraTTS: Adapting Text-to-Speech to Environmental Contexts with Flow Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09874","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:270dc2ef4c748f1445df75c0d8de0decaf77158cab793c90fe243a35ea5e52a9","target":"record","created_at":"2026-07-05T11:35:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4d6b3690fb63cb10bec0ec635f1f9cdf81fcc30ba7482a7ec7198a302e7199fd","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-11T15:43:08Z","title_canon_sha256":"09cca03e35d715b68621a7b279ff3c565f5f552a69afa4233065c8d9511e2564"},"schema_version":"1.0","source":{"id":"2506.09874","kind":"arxiv","version":2}},"canonical_sha256":"167a4292172f7d507dc888d7b2df8695410340453ea0d9039bf39075f8a036f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"167a4292172f7d507dc888d7b2df8695410340453ea0d9039bf39075f8a036f6","first_computed_at":"2026-07-05T11:35:14.345883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:14.345883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nq+eV3S68jxZm2IYMKc/JNhKBur+X2WiMBd/mMJfy3L3fwovK/t0wpY9r1K3IFqU+Z0I3LB29gPKl07SoVW+Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:14.346426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09874","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:270dc2ef4c748f1445df75c0d8de0decaf77158cab793c90fe243a35ea5e52a9","sha256:971063def4cf4d477639cbc3a4f1dcbc4104a69e924413069ea4232fe64c592a"],"state_sha256":"28309f2490648f8941870fc4eca96d3bc88c779c08f89b50e7b8c35b539a0b64"}