{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HL2NG5V4DCZJVY2KA27SNL2JYW","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":"71792bbbe8d4b7d9e4c4c0ec61a9c3640d79284e49afbcbeb8a4cc14153b0e89","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-20T13:28:42Z","title_canon_sha256":"193eb92278586fa4910fb0004a270ca28c29593152844513c7a041acdbc6ac33"},"schema_version":"1.0","source":{"id":"2411.13314","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13314","created_at":"2026-07-05T12:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13314v4","created_at":"2026-07-05T12:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13314","created_at":"2026-07-05T12:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"HL2NG5V4DCZJ","created_at":"2026-07-05T12:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"HL2NG5V4DCZJVY2K","created_at":"2026-07-05T12:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"HL2NG5V4","created_at":"2026-07-05T12:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:219ecd1bc4c83b41fe0825da5f770990d998b4d874559e5285c554c9e89f79ad","target":"graph","created_at":"2026-07-05T12:03:44Z","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/2411.13314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Controlling the style and characteristics of speech synthesis is crucial for adapting the output to specific contexts and user requirements. Previous Text-to-speech (TTS) works have focused primarily on the technical aspects of producing natural-sounding speech, such as intonation, rhythm, and clarity. However, they overlook the fact that there is a growing emphasis on spatial perception of synthesized speech, which may provide immersive experience in gaming and virtual reality. To solve this issue, in this paper, we present a novel multi-modal TTS approach, namely Image-indicated Immersive Te","authors_text":"Jiaran Gao, Jiawei Zhang, Jun Wang, Tian-Hao Zhang, Xinyuan Qian, Xu-Cheng Yin","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-20T13:28:42Z","title":"I2TTS: Image-indicated Immersive Text-to-speech Synthesis with Spatial Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13314","kind":"arxiv","version":4},"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:c6a2fcb051ee74c1f97b52a8b8d9096a59252dd96c60fa6808fdb2a4ce8293cf","target":"record","created_at":"2026-07-05T12:03:44Z","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":"71792bbbe8d4b7d9e4c4c0ec61a9c3640d79284e49afbcbeb8a4cc14153b0e89","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-20T13:28:42Z","title_canon_sha256":"193eb92278586fa4910fb0004a270ca28c29593152844513c7a041acdbc6ac33"},"schema_version":"1.0","source":{"id":"2411.13314","kind":"arxiv","version":4}},"canonical_sha256":"3af4d376bc18b29ae34a06bf26af49c5ac458e9f30195f193f30bb8946bdebfd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3af4d376bc18b29ae34a06bf26af49c5ac458e9f30195f193f30bb8946bdebfd","first_computed_at":"2026-07-05T12:03:44.244777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:44.244777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6eGMf1BOtZnF+HLV5a8ZXLMi/iXmCKpWTEOZkd5hpAx4uhBTA8c+P1tmM47Gnkn7Kr5szwWEof1OeOFz5v3OBg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:44.245282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.13314","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6a2fcb051ee74c1f97b52a8b8d9096a59252dd96c60fa6808fdb2a4ce8293cf","sha256:219ecd1bc4c83b41fe0825da5f770990d998b4d874559e5285c554c9e89f79ad"],"state_sha256":"cffd2f6da8662839638189525db033d773f1288374ae121dbd6df1c0bb8589d8"}