{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KSU4EQGR2DXCN3YRYSND4E5HTE","short_pith_number":"pith:KSU4EQGR","canonical_record":{"source":{"id":"2507.15272","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-21T06:20:27Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"acb20e9ac761bea9883d6bbdf2fc8472813ff403d65c9228255564fc3dd45537","abstract_canon_sha256":"b1959f91b3a055f241696ddfecb14609539514b8e6a8659d994da555f3de1f33"},"schema_version":"1.0"},"canonical_sha256":"54a9c240d1d0ee26ef11c49a3e13a7992e8bd4d8c94610c0dadfff452923ae78","source":{"kind":"arxiv","id":"2507.15272","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KSU4EQGR2DXCN3YRYSND4E5HTE","target":"record","payload":{"canonical_record":{"source":{"id":"2507.15272","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-21T06:20:27Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"acb20e9ac761bea9883d6bbdf2fc8472813ff403d65c9228255564fc3dd45537","abstract_canon_sha256":"b1959f91b3a055f241696ddfecb14609539514b8e6a8659d994da555f3de1f33"},"schema_version":"1.0"},"canonical_sha256":"54a9c240d1d0ee26ef11c49a3e13a7992e8bd4d8c94610c0dadfff452923ae78","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:21.593159Z","signature_b64":"tMQLQQOF3T9aYYRVatG1oSx5xhqS4CWcEWdYBRjFaje3jFdekdbxSFfsPR/vhxB2ze7yLciW2umfEgHvH/p2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54a9c240d1d0ee26ef11c49a3e13a7992e8bd4d8c94610c0dadfff452923ae78","last_reissued_at":"2026-07-05T11:40:21.592631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:21.592631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.15272","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8n1NpSyJAVM2hGvz6C9uOWnGOilKYb6tz598SErMIu8thO5zz1kyzpiRlDKy7l6Srm4+6V/VAvqb5fLE7ZAnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:59:50.623566Z"},"content_sha256":"088069226b883a9a049a903a27515e56af2acc30b0415cb58b8713196e13c177","schema_version":"1.0","event_id":"sha256:088069226b883a9a049a903a27515e56af2acc30b0415cb58b8713196e13c177"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KSU4EQGR2DXCN3YRYSND4E5HTE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A2TTS: TTS for Low Resource Indian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Abhishek Nikunj Shinde, Ayush Singh Bhadoriya, Ganesh Ramakrishnan, Isha Pandey","submitted_at":"2025-07-21T06:20:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15272","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/2507.15272/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XjgkekcLK/4UiBlFU/SAFjujfFpeemtu27L9g6LrEPElI5S/aKyBVR7aBlEAGGbDKhabDoYbhzSp2uBrilO1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:59:50.624408Z"},"content_sha256":"24ff8be93a7a90d7066641e36754fe125919f4b5b8f10ddfee76655e5f3041b7","schema_version":"1.0","event_id":"sha256:24ff8be93a7a90d7066641e36754fe125919f4b5b8f10ddfee76655e5f3041b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KSU4EQGR2DXCN3YRYSND4E5HTE/bundle.json","state_url":"https://pith.science/pith/KSU4EQGR2DXCN3YRYSND4E5HTE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KSU4EQGR2DXCN3YRYSND4E5HTE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T00:59:50Z","links":{"resolver":"https://pith.science/pith/KSU4EQGR2DXCN3YRYSND4E5HTE","bundle":"https://pith.science/pith/KSU4EQGR2DXCN3YRYSND4E5HTE/bundle.json","state":"https://pith.science/pith/KSU4EQGR2DXCN3YRYSND4E5HTE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KSU4EQGR2DXCN3YRYSND4E5HTE/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9O/9m3axFhlKJ2Imza5VgdXoiylXNnV8VQFgI+qDWDOc9xxJd86OZSGXZY8vaj5TfcX8xnOSKRvb/v4ZidePBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:59:50.645920Z","bundle_sha256":"76849c3d6ce10c65513160d5be2783c3bc56903627374fd6e19ab21d3c8ad430"}}