{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KSU4EQGR2DXCN3YRYSND4E5HTE","short_pith_number":"pith:KSU4EQGR","schema_version":"1.0","canonical_sha256":"54a9c240d1d0ee26ef11c49a3e13a7992e8bd4d8c94610c0dadfff452923ae78","source":{"kind":"arxiv","id":"2507.15272","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.15272","created_at":"2026-07-05T11:40:21.592699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.15272v1","created_at":"2026-07-05T11:40:21.592699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15272","created_at":"2026-07-05T11:40:21.592699+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSU4EQGR2DXC","created_at":"2026-07-05T11:40:21.592699+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSU4EQGR2DXCN3YR","created_at":"2026-07-05T11:40:21.592699+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSU4EQGR","created_at":"2026-07-05T11:40:21.592699+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25441","citing_title":"Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Cost","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSU4EQGR2DXCN3YRYSND4E5HTE","json":"https://pith.science/pith/KSU4EQGR2DXCN3YRYSND4E5HTE.json","graph_json":"https://pith.science/api/pith-number/KSU4EQGR2DXCN3YRYSND4E5HTE/graph.json","events_json":"https://pith.science/api/pith-number/KSU4EQGR2DXCN3YRYSND4E5HTE/events.json","paper":"https://pith.science/paper/KSU4EQGR"},"agent_actions":{"view_html":"https://pith.science/pith/KSU4EQGR2DXCN3YRYSND4E5HTE","download_json":"https://pith.science/pith/KSU4EQGR2DXCN3YRYSND4E5HTE.json","view_paper":"https://pith.science/paper/KSU4EQGR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.15272&json=true","fetch_graph":"https://pith.science/api/pith-number/KSU4EQGR2DXCN3YRYSND4E5HTE/graph.json","fetch_events":"https://pith.science/api/pith-number/KSU4EQGR2DXCN3YRYSND4E5HTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSU4EQGR2DXCN3YRYSND4E5HTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSU4EQGR2DXCN3YRYSND4E5HTE/action/storage_attestation","attest_author":"https://pith.science/pith/KSU4EQGR2DXCN3YRYSND4E5HTE/action/author_attestation","sign_citation":"https://pith.science/pith/KSU4EQGR2DXCN3YRYSND4E5HTE/action/citation_signature","submit_replication":"https://pith.science/pith/KSU4EQGR2DXCN3YRYSND4E5HTE/action/replication_record"}},"created_at":"2026-07-05T11:40:21.592699+00:00","updated_at":"2026-07-05T11:40:21.592699+00:00"}