{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TPJED2A75EAUMUZ4II3UO74X23","short_pith_number":"pith:TPJED2A7","schema_version":"1.0","canonical_sha256":"9bd241e81fe90146533c4237477f97d6fddf99b51d71a4b881b47e47f1b3b284","source":{"kind":"arxiv","id":"2505.04885","version":1},"attestation_state":"computed","paper":{"title":"A Multi-Agent AI Framework for Immersive Audiobook Production through Spatial Audio and Neural Narration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.MA","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Nia D'Souza Ganapathy, Shaja Arul Selvamani","submitted_at":"2025-05-08T01:48:06Z","abstract_excerpt":"This research introduces an innovative AI-driven multi-agent framework specifically designed for creating immersive audiobooks. Leveraging neural text-to-speech synthesis with FastSpeech 2 and VALL-E for expressive narration and character-specific voices, the framework employs advanced language models to automatically interpret textual narratives and generate realistic spatial audio effects. These sound effects are dynamically synchronized with the storyline through sophisticated temporal integration methods, including Dynamic Time Warping (DTW) and recurrent neural networks (RNNs). Diffusion-"},"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":"2505.04885","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-08T01:48:06Z","cross_cats_sorted":["cs.HC","cs.MA","cs.MM","eess.AS"],"title_canon_sha256":"357cf608071473a2e06317c1c928bde87c1f8c26a0e45d2742e29da10a76ce89","abstract_canon_sha256":"ead7ccbd28e4659885a2465cb6bafad7e9ab9c2a14b239c59f16dfdb1e4f7d29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:15.086488Z","signature_b64":"GV+mMMGQfFddSVoDH4ifn+mtvXw2jZMm2qIqVqnFiRvZrE8h4qILGM/1WEpg5UN1MIXPfONhDdR9x/bxJGDqDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bd241e81fe90146533c4237477f97d6fddf99b51d71a4b881b47e47f1b3b284","last_reissued_at":"2026-07-05T11:00:15.085909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:15.085909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multi-Agent AI Framework for Immersive Audiobook Production through Spatial Audio and Neural Narration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.MA","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Nia D'Souza Ganapathy, Shaja Arul Selvamani","submitted_at":"2025-05-08T01:48:06Z","abstract_excerpt":"This research introduces an innovative AI-driven multi-agent framework specifically designed for creating immersive audiobooks. Leveraging neural text-to-speech synthesis with FastSpeech 2 and VALL-E for expressive narration and character-specific voices, the framework employs advanced language models to automatically interpret textual narratives and generate realistic spatial audio effects. These sound effects are dynamically synchronized with the storyline through sophisticated temporal integration methods, including Dynamic Time Warping (DTW) and recurrent neural networks (RNNs). Diffusion-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04885","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/2505.04885/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":"2505.04885","created_at":"2026-07-05T11:00:15.085969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04885v1","created_at":"2026-07-05T11:00:15.085969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04885","created_at":"2026-07-05T11:00:15.085969+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPJED2A75EAU","created_at":"2026-07-05T11:00:15.085969+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPJED2A75EAUMUZ4","created_at":"2026-07-05T11:00:15.085969+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPJED2A7","created_at":"2026-07-05T11:00:15.085969+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/TPJED2A75EAUMUZ4II3UO74X23","json":"https://pith.science/pith/TPJED2A75EAUMUZ4II3UO74X23.json","graph_json":"https://pith.science/api/pith-number/TPJED2A75EAUMUZ4II3UO74X23/graph.json","events_json":"https://pith.science/api/pith-number/TPJED2A75EAUMUZ4II3UO74X23/events.json","paper":"https://pith.science/paper/TPJED2A7"},"agent_actions":{"view_html":"https://pith.science/pith/TPJED2A75EAUMUZ4II3UO74X23","download_json":"https://pith.science/pith/TPJED2A75EAUMUZ4II3UO74X23.json","view_paper":"https://pith.science/paper/TPJED2A7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04885&json=true","fetch_graph":"https://pith.science/api/pith-number/TPJED2A75EAUMUZ4II3UO74X23/graph.json","fetch_events":"https://pith.science/api/pith-number/TPJED2A75EAUMUZ4II3UO74X23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPJED2A75EAUMUZ4II3UO74X23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPJED2A75EAUMUZ4II3UO74X23/action/storage_attestation","attest_author":"https://pith.science/pith/TPJED2A75EAUMUZ4II3UO74X23/action/author_attestation","sign_citation":"https://pith.science/pith/TPJED2A75EAUMUZ4II3UO74X23/action/citation_signature","submit_replication":"https://pith.science/pith/TPJED2A75EAUMUZ4II3UO74X23/action/replication_record"}},"created_at":"2026-07-05T11:00:15.085969+00:00","updated_at":"2026-07-05T11:00:15.085969+00:00"}