{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EHO4PVSYXLPPTUHR47IY7J5HYG","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":"b0bead319a8f1f7a6a3109bfb0769e625bd140b6510f09e4f56c61b5907d9141","cross_cats_sorted":["cs.HC","cs.SD","eess.AS"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T13:35:05Z","title_canon_sha256":"7a6c663b3e277e8f4ccd06d85a64a8311969016b5a2e18190eccadb7cec03489"},"schema_version":"1.0","source":{"id":"2506.16310","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16310","created_at":"2026-07-05T11:24:34Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16310v1","created_at":"2026-07-05T11:24:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16310","created_at":"2026-07-05T11:24:34Z"},{"alias_kind":"pith_short_12","alias_value":"EHO4PVSYXLPP","created_at":"2026-07-05T11:24:34Z"},{"alias_kind":"pith_short_16","alias_value":"EHO4PVSYXLPPTUHR","created_at":"2026-07-05T11:24:34Z"},{"alias_kind":"pith_short_8","alias_value":"EHO4PVSY","created_at":"2026-07-05T11:24:34Z"}],"graph_snapshots":[{"event_id":"sha256:d3a86a46b7ca1a0d0b798d2140b2b6615984457ccbb46cb0028dd14940c713ba","target":"graph","created_at":"2026-07-05T11:24:34Z","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/2506.16310/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art text-to-speech (TTS) systems realize high naturalness in monolingual environments, synthesizing speech with correct multilingual accents (especially for Indic languages) and context-relevant emotions still poses difficulty owing to cultural nuance discrepancies in current frameworks. This paper introduces a new TTS architecture integrating accent along with preserving transliteration with multi-scale emotion modelling, in particularly tuned for Hindi and Indian English accent. Our approach extends the Parler-TTS model by integrating A language-specific phoneme alignment hybrid","authors_text":"Aditya Dubey, Akshansh Dwivedi, Himanshu Gohil, Jenish Boricha, Pranav Pawar","cross_cats":["cs.HC","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T13:35:05Z","title":"Optimizing Multilingual Text-To-Speech with Accents & Emotions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16310","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":"sha256:6f20d83a6343611e1040173d2cd9509e3bf4e6643fb0ac6ab623f71e10435214","target":"record","created_at":"2026-07-05T11:24:34Z","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":"b0bead319a8f1f7a6a3109bfb0769e625bd140b6510f09e4f56c61b5907d9141","cross_cats_sorted":["cs.HC","cs.SD","eess.AS"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T13:35:05Z","title_canon_sha256":"7a6c663b3e277e8f4ccd06d85a64a8311969016b5a2e18190eccadb7cec03489"},"schema_version":"1.0","source":{"id":"2506.16310","kind":"arxiv","version":1}},"canonical_sha256":"21ddc7d658badef9d0f1e7d18fa7a7c1877d41102958f6a1227b9de24ec15007","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21ddc7d658badef9d0f1e7d18fa7a7c1877d41102958f6a1227b9de24ec15007","first_computed_at":"2026-07-05T11:24:34.363941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:34.363941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wDcD2mXLwf07AjkAnMQc9lW/zMbwZa9TnMOV9VwBVd7n0k3vJOb2/VHatc2Mn/AYV9a1/YjsXFOz+he1QiTgCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:34.364441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16310","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f20d83a6343611e1040173d2cd9509e3bf4e6643fb0ac6ab623f71e10435214","sha256:d3a86a46b7ca1a0d0b798d2140b2b6615984457ccbb46cb0028dd14940c713ba"],"state_sha256":"39bd18dd2f00f657cd649d619f442134d12050e11368c5d6c35c99f5c5f9d4dd"}