{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6HMTTLLSKHZ32DX7IJBWYGREID","short_pith_number":"pith:6HMTTLLS","schema_version":"1.0","canonical_sha256":"f1d939ad7251f3bd0eff42436c1a2440ca40074b68994ff5b36c1f147326d53b","source":{"kind":"arxiv","id":"1904.06508","version":2},"attestation_state":"computed","paper":{"title":"End-to-end Text-to-speech for Low-resource Languages by Cross-Lingual Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Cheng-chieh Yeh, Hung-yi Lee, Tao Tu, Yuan-Jui Chen","submitted_at":"2019-04-13T08:51:11Z","abstract_excerpt":"End-to-end text-to-speech (TTS) has shown great success on large quantities of paired text plus speech data. However, laborious data collection remains difficult for at least 95% of the languages over the world, which hinders the development of TTS in different languages. In this paper, we aim to build TTS systems for such low-resource (target) languages where only very limited paired data are available. We show such TTS can be effectively constructed by transferring knowledge from a high-resource (source) language. Since the model trained on source language cannot be directly applied to targe"},"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":"1904.06508","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-13T08:51:11Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"741d6e9c08371c0d9396a469721260becb46d893ae6f4b1b6461b67bedea09dd","abstract_canon_sha256":"d96eb7341b126e5d7ccf1792a77081ff8da9ece288f82ad900510925fc18e693"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:42.388338Z","signature_b64":"l6n6SUTI47Hp21O1VjKT+FQGZCDGJldQowR0cWi5Jkfk/tzVGGH5qroYBdLQP8J2ozgl5bExfz04BblMFIqKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1d939ad7251f3bd0eff42436c1a2440ca40074b68994ff5b36c1f147326d53b","last_reissued_at":"2026-05-17T23:41:42.387885Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:42.387885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-end Text-to-speech for Low-resource Languages by Cross-Lingual Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Cheng-chieh Yeh, Hung-yi Lee, Tao Tu, Yuan-Jui Chen","submitted_at":"2019-04-13T08:51:11Z","abstract_excerpt":"End-to-end text-to-speech (TTS) has shown great success on large quantities of paired text plus speech data. However, laborious data collection remains difficult for at least 95% of the languages over the world, which hinders the development of TTS in different languages. In this paper, we aim to build TTS systems for such low-resource (target) languages where only very limited paired data are available. We show such TTS can be effectively constructed by transferring knowledge from a high-resource (source) language. Since the model trained on source language cannot be directly applied to targe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06508","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1904.06508","created_at":"2026-05-17T23:41:42.387940+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.06508v2","created_at":"2026-05-17T23:41:42.387940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06508","created_at":"2026-05-17T23:41:42.387940+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HMTTLLSKHZ3","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HMTTLLSKHZ32DX7","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HMTTLLS","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6HMTTLLSKHZ32DX7IJBWYGREID","json":"https://pith.science/pith/6HMTTLLSKHZ32DX7IJBWYGREID.json","graph_json":"https://pith.science/api/pith-number/6HMTTLLSKHZ32DX7IJBWYGREID/graph.json","events_json":"https://pith.science/api/pith-number/6HMTTLLSKHZ32DX7IJBWYGREID/events.json","paper":"https://pith.science/paper/6HMTTLLS"},"agent_actions":{"view_html":"https://pith.science/pith/6HMTTLLSKHZ32DX7IJBWYGREID","download_json":"https://pith.science/pith/6HMTTLLSKHZ32DX7IJBWYGREID.json","view_paper":"https://pith.science/paper/6HMTTLLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.06508&json=true","fetch_graph":"https://pith.science/api/pith-number/6HMTTLLSKHZ32DX7IJBWYGREID/graph.json","fetch_events":"https://pith.science/api/pith-number/6HMTTLLSKHZ32DX7IJBWYGREID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HMTTLLSKHZ32DX7IJBWYGREID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HMTTLLSKHZ32DX7IJBWYGREID/action/storage_attestation","attest_author":"https://pith.science/pith/6HMTTLLSKHZ32DX7IJBWYGREID/action/author_attestation","sign_citation":"https://pith.science/pith/6HMTTLLSKHZ32DX7IJBWYGREID/action/citation_signature","submit_replication":"https://pith.science/pith/6HMTTLLSKHZ32DX7IJBWYGREID/action/replication_record"}},"created_at":"2026-05-17T23:41:42.387940+00:00","updated_at":"2026-05-17T23:41:42.387940+00:00"}