{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:73EUH655BQC2TVDOS5V2IT34QA","short_pith_number":"pith:73EUH655","schema_version":"1.0","canonical_sha256":"fec943fbbd0c05a9d46e976ba44f7c8005c16ab059057d94632874ff270f3410","source":{"kind":"arxiv","id":"2406.06403","version":1},"attestation_state":"computed","paper":{"title":"Meta Learning Text-to-Speech Synthesis in over 7000 Languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Emanu\\\"el A. P. Habets, Florian Lux, Frank Zalkow, Lyonel Behringer, Matt Coler, Ngoc Thang Vu, Phat Do, Sarina Meyer","submitted_at":"2024-06-10T15:56:52Z","abstract_excerpt":"In this work, we take on the challenging task of building a single text-to-speech synthesis system that is capable of generating speech in over 7000 languages, many of which lack sufficient data for traditional TTS development. By leveraging a novel integration of massively multilingual pretraining and meta learning to approximate language representations, our approach enables zero-shot speech synthesis in languages without any available data. We validate our system's performance through objective measures and human evaluation across a diverse linguistic landscape. By releasing our code and mo"},"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":"2406.06403","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T15:56:52Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"f7d952548b4d38ec89eb4ba6cdbf1fa1115a9d559abc9e805dbfb750d7f73f6a","abstract_canon_sha256":"064e0bf9e28209b7e0f3fa0a1caa94dc3d1e7cef4f65a80ef38a9adeafdef099"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:41.968645Z","signature_b64":"wX8PhMi4HNlqrjLd+aJN25WxLLxcr1zvyGRMtKoUFJZhppA2QxjJKYacyBebzCGkixkxN7WarOdCTKf2EFjfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fec943fbbd0c05a9d46e976ba44f7c8005c16ab059057d94632874ff270f3410","last_reissued_at":"2026-07-05T08:29:41.968133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:41.968133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta Learning Text-to-Speech Synthesis in over 7000 Languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Emanu\\\"el A. P. Habets, Florian Lux, Frank Zalkow, Lyonel Behringer, Matt Coler, Ngoc Thang Vu, Phat Do, Sarina Meyer","submitted_at":"2024-06-10T15:56:52Z","abstract_excerpt":"In this work, we take on the challenging task of building a single text-to-speech synthesis system that is capable of generating speech in over 7000 languages, many of which lack sufficient data for traditional TTS development. By leveraging a novel integration of massively multilingual pretraining and meta learning to approximate language representations, our approach enables zero-shot speech synthesis in languages without any available data. We validate our system's performance through objective measures and human evaluation across a diverse linguistic landscape. By releasing our code and mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06403","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/2406.06403/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":"2406.06403","created_at":"2026-07-05T08:29:41.968199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06403v1","created_at":"2026-07-05T08:29:41.968199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06403","created_at":"2026-07-05T08:29:41.968199+00:00"},{"alias_kind":"pith_short_12","alias_value":"73EUH655BQC2","created_at":"2026-07-05T08:29:41.968199+00:00"},{"alias_kind":"pith_short_16","alias_value":"73EUH655BQC2TVDO","created_at":"2026-07-05T08:29:41.968199+00:00"},{"alias_kind":"pith_short_8","alias_value":"73EUH655","created_at":"2026-07-05T08:29:41.968199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17513","citing_title":"What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73EUH655BQC2TVDOS5V2IT34QA","json":"https://pith.science/pith/73EUH655BQC2TVDOS5V2IT34QA.json","graph_json":"https://pith.science/api/pith-number/73EUH655BQC2TVDOS5V2IT34QA/graph.json","events_json":"https://pith.science/api/pith-number/73EUH655BQC2TVDOS5V2IT34QA/events.json","paper":"https://pith.science/paper/73EUH655"},"agent_actions":{"view_html":"https://pith.science/pith/73EUH655BQC2TVDOS5V2IT34QA","download_json":"https://pith.science/pith/73EUH655BQC2TVDOS5V2IT34QA.json","view_paper":"https://pith.science/paper/73EUH655","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06403&json=true","fetch_graph":"https://pith.science/api/pith-number/73EUH655BQC2TVDOS5V2IT34QA/graph.json","fetch_events":"https://pith.science/api/pith-number/73EUH655BQC2TVDOS5V2IT34QA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73EUH655BQC2TVDOS5V2IT34QA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73EUH655BQC2TVDOS5V2IT34QA/action/storage_attestation","attest_author":"https://pith.science/pith/73EUH655BQC2TVDOS5V2IT34QA/action/author_attestation","sign_citation":"https://pith.science/pith/73EUH655BQC2TVDOS5V2IT34QA/action/citation_signature","submit_replication":"https://pith.science/pith/73EUH655BQC2TVDOS5V2IT34QA/action/replication_record"}},"created_at":"2026-07-05T08:29:41.968199+00:00","updated_at":"2026-07-05T08:29:41.968199+00:00"}