{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KSU4EQGR2DXCN3YRYSND4E5HTE","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":"b1959f91b3a055f241696ddfecb14609539514b8e6a8659d994da555f3de1f33","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-21T06:20:27Z","title_canon_sha256":"acb20e9ac761bea9883d6bbdf2fc8472813ff403d65c9228255564fc3dd45537"},"schema_version":"1.0","source":{"id":"2507.15272","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15272","created_at":"2026-07-05T11:40:21Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15272v1","created_at":"2026-07-05T11:40:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15272","created_at":"2026-07-05T11:40:21Z"},{"alias_kind":"pith_short_12","alias_value":"KSU4EQGR2DXC","created_at":"2026-07-05T11:40:21Z"},{"alias_kind":"pith_short_16","alias_value":"KSU4EQGR2DXCN3YR","created_at":"2026-07-05T11:40:21Z"},{"alias_kind":"pith_short_8","alias_value":"KSU4EQGR","created_at":"2026-07-05T11:40:21Z"}],"graph_snapshots":[{"event_id":"sha256:24ff8be93a7a90d7066641e36754fe125919f4b5b8f10ddfee76655e5f3041b7","target":"graph","created_at":"2026-07-05T11:40:21Z","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/2507.15272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a speaker conditioned text-to-speech (TTS) system aimed at addressing challenges in generating speech for unseen speakers and supporting diverse Indian languages. Our method leverages a diffusion-based TTS architecture, where a speaker encoder extracts embeddings from short reference audio samples to condition the DDPM decoder for multispeaker generation. To further enhance prosody and naturalness, we employ a cross-attention based duration prediction mechanism that utilizes reference audio, enabling more accurate and speaker consistent timing. This results in speech that closely re","authors_text":"Abhishek Nikunj Shinde, Ayush Singh Bhadoriya, Ganesh Ramakrishnan, Isha Pandey","cross_cats":["cs.AI","cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-21T06:20:27Z","title":"A2TTS: TTS for Low Resource Indian Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15272","kind":"arxiv","version":1},"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":"sha256:088069226b883a9a049a903a27515e56af2acc30b0415cb58b8713196e13c177","target":"record","created_at":"2026-07-05T11:40:21Z","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":"b1959f91b3a055f241696ddfecb14609539514b8e6a8659d994da555f3de1f33","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-21T06:20:27Z","title_canon_sha256":"acb20e9ac761bea9883d6bbdf2fc8472813ff403d65c9228255564fc3dd45537"},"schema_version":"1.0","source":{"id":"2507.15272","kind":"arxiv","version":1}},"canonical_sha256":"54a9c240d1d0ee26ef11c49a3e13a7992e8bd4d8c94610c0dadfff452923ae78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54a9c240d1d0ee26ef11c49a3e13a7992e8bd4d8c94610c0dadfff452923ae78","first_computed_at":"2026-07-05T11:40:21.592631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:21.592631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tMQLQQOF3T9aYYRVatG1oSx5xhqS4CWcEWdYBRjFaje3jFdekdbxSFfsPR/vhxB2ze7yLciW2umfEgHvH/p2Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:21.593159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15272","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:088069226b883a9a049a903a27515e56af2acc30b0415cb58b8713196e13c177","sha256:24ff8be93a7a90d7066641e36754fe125919f4b5b8f10ddfee76655e5f3041b7"],"state_sha256":"1cf85a88ca73f7ea6bf2342dcba1cb804fd7eb19bede6329024b8f055d128d56"}