{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:62H6SFF74HMVKJD7PEGKHUZ7LF","short_pith_number":"pith:62H6SFF7","schema_version":"1.0","canonical_sha256":"f68fe914bfe1d955247f790ca3d33f595043271ab83849eb49bad6f48e83929f","source":{"kind":"arxiv","id":"2508.07426","version":1},"attestation_state":"computed","paper":{"title":"Scalable Controllable Accented TTS","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ashi Garg, Henry Li Xinyuan, Kevin Duh, Leibny Paola Garc\\'ia-Perera, Matthew Wiesner, Nicholas Andrews, Sanjeev Khudanpur, Zexin Cai","submitted_at":"2025-08-10T16:56:39Z","abstract_excerpt":"We tackle the challenge of scaling accented TTS systems, expanding their capabilities to include much larger amounts of training data and a wider variety of accent labels, even for accents that are poorly represented or unlabeled in traditional TTS datasets. To achieve this, we employ two strategies: 1. Accent label discovery via a speech geolocation model, which automatically infers accent labels from raw speech data without relying solely on human annotation; 2. Timbre augmentation through kNN voice conversion to increase data diversity and model robustness. These strategies are validated on"},"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":"2508.07426","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-10T16:56:39Z","cross_cats_sorted":[],"title_canon_sha256":"d229125f7132a49a755e187c0c17d0c582e036ec08c5412b4cfd0875e3d5eeeb","abstract_canon_sha256":"decef0dd3face7024a4d732fb469c69e10074b5c986118f3421d86c685bfcf0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:46.058767Z","signature_b64":"NYYr3LA6ZVcY8OOmXirqWDMPH6Q8nSSWSysaBgunPJA3WP/D/WbjYgccYaK0PyK0vOPzH5H3EpVNYyM7y66pDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f68fe914bfe1d955247f790ca3d33f595043271ab83849eb49bad6f48e83929f","last_reissued_at":"2026-07-05T11:51:46.058273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:46.058273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Controllable Accented TTS","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ashi Garg, Henry Li Xinyuan, Kevin Duh, Leibny Paola Garc\\'ia-Perera, Matthew Wiesner, Nicholas Andrews, Sanjeev Khudanpur, Zexin Cai","submitted_at":"2025-08-10T16:56:39Z","abstract_excerpt":"We tackle the challenge of scaling accented TTS systems, expanding their capabilities to include much larger amounts of training data and a wider variety of accent labels, even for accents that are poorly represented or unlabeled in traditional TTS datasets. To achieve this, we employ two strategies: 1. Accent label discovery via a speech geolocation model, which automatically infers accent labels from raw speech data without relying solely on human annotation; 2. Timbre augmentation through kNN voice conversion to increase data diversity and model robustness. These strategies are validated on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07426","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/2508.07426/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":"2508.07426","created_at":"2026-07-05T11:51:46.058338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07426v1","created_at":"2026-07-05T11:51:46.058338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07426","created_at":"2026-07-05T11:51:46.058338+00:00"},{"alias_kind":"pith_short_12","alias_value":"62H6SFF74HMV","created_at":"2026-07-05T11:51:46.058338+00:00"},{"alias_kind":"pith_short_16","alias_value":"62H6SFF74HMVKJD7","created_at":"2026-07-05T11:51:46.058338+00:00"},{"alias_kind":"pith_short_8","alias_value":"62H6SFF7","created_at":"2026-07-05T11:51:46.058338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25403","citing_title":"CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/62H6SFF74HMVKJD7PEGKHUZ7LF","json":"https://pith.science/pith/62H6SFF74HMVKJD7PEGKHUZ7LF.json","graph_json":"https://pith.science/api/pith-number/62H6SFF74HMVKJD7PEGKHUZ7LF/graph.json","events_json":"https://pith.science/api/pith-number/62H6SFF74HMVKJD7PEGKHUZ7LF/events.json","paper":"https://pith.science/paper/62H6SFF7"},"agent_actions":{"view_html":"https://pith.science/pith/62H6SFF74HMVKJD7PEGKHUZ7LF","download_json":"https://pith.science/pith/62H6SFF74HMVKJD7PEGKHUZ7LF.json","view_paper":"https://pith.science/paper/62H6SFF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07426&json=true","fetch_graph":"https://pith.science/api/pith-number/62H6SFF74HMVKJD7PEGKHUZ7LF/graph.json","fetch_events":"https://pith.science/api/pith-number/62H6SFF74HMVKJD7PEGKHUZ7LF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62H6SFF74HMVKJD7PEGKHUZ7LF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62H6SFF74HMVKJD7PEGKHUZ7LF/action/storage_attestation","attest_author":"https://pith.science/pith/62H6SFF74HMVKJD7PEGKHUZ7LF/action/author_attestation","sign_citation":"https://pith.science/pith/62H6SFF74HMVKJD7PEGKHUZ7LF/action/citation_signature","submit_replication":"https://pith.science/pith/62H6SFF74HMVKJD7PEGKHUZ7LF/action/replication_record"}},"created_at":"2026-07-05T11:51:46.058338+00:00","updated_at":"2026-07-05T11:51:46.058338+00:00"}