{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OFBBFEOSCCRWG7ANWFAIIFNROU","short_pith_number":"pith:OFBBFEOS","schema_version":"1.0","canonical_sha256":"71421291d210a3637c0db1408415b1753d4cad70f2c5433ce8713d54134640a8","source":{"kind":"arxiv","id":"2110.07210","version":2},"attestation_state":"computed","paper":{"title":"Improve Cross-lingual Voice Cloning Using Low-quality Code-switched Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haitong Zhang, Yue Lin","submitted_at":"2021-10-14T08:16:06Z","abstract_excerpt":"Recently, sequence-to-sequence (seq-to-seq) models have been successfully applied in text-to-speech (TTS) to synthesize speech for single-language text. To synthesize speech for multiple languages usually requires multi-lingual speech from the target speaker. However, it is both laborious and expensive to collect high-quality multi-lingual TTS data for the target speakers. In this paper, we proposed to use low-quality code-switched found data from the non-target speakers to achieve cross-lingual voice cloning for the target speakers. Experiments show that our proposed method can generate high-"},"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":"2110.07210","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-14T08:16:06Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"3d94cde3724060b16b9be07cdb8077d3391a9f5e2db00e811e22f18f304ef53e","abstract_canon_sha256":"db5243e5af7b6ef4da45a770ad5b51b7a6a1150b882b27f7eecfbc1cc38a8b39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:16:49.388837Z","signature_b64":"LHNOEUdI5vyJ2LV55CjpVATe2pOT2jjCa27vQGCHIMC50UaXvfd/dL+0IS0jgp2vxJPPTVCehMZ559P0K9LuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71421291d210a3637c0db1408415b1753d4cad70f2c5433ce8713d54134640a8","last_reissued_at":"2026-07-05T05:16:49.388307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:16:49.388307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improve Cross-lingual Voice Cloning Using Low-quality Code-switched Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haitong Zhang, Yue Lin","submitted_at":"2021-10-14T08:16:06Z","abstract_excerpt":"Recently, sequence-to-sequence (seq-to-seq) models have been successfully applied in text-to-speech (TTS) to synthesize speech for single-language text. To synthesize speech for multiple languages usually requires multi-lingual speech from the target speaker. However, it is both laborious and expensive to collect high-quality multi-lingual TTS data for the target speakers. In this paper, we proposed to use low-quality code-switched found data from the non-target speakers to achieve cross-lingual voice cloning for the target speakers. Experiments show that our proposed method can generate high-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07210","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.07210/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":"2110.07210","created_at":"2026-07-05T05:16:49.388379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07210v2","created_at":"2026-07-05T05:16:49.388379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07210","created_at":"2026-07-05T05:16:49.388379+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFBBFEOSCCRW","created_at":"2026-07-05T05:16:49.388379+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFBBFEOSCCRWG7AN","created_at":"2026-07-05T05:16:49.388379+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFBBFEOS","created_at":"2026-07-05T05:16:49.388379+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/OFBBFEOSCCRWG7ANWFAIIFNROU","json":"https://pith.science/pith/OFBBFEOSCCRWG7ANWFAIIFNROU.json","graph_json":"https://pith.science/api/pith-number/OFBBFEOSCCRWG7ANWFAIIFNROU/graph.json","events_json":"https://pith.science/api/pith-number/OFBBFEOSCCRWG7ANWFAIIFNROU/events.json","paper":"https://pith.science/paper/OFBBFEOS"},"agent_actions":{"view_html":"https://pith.science/pith/OFBBFEOSCCRWG7ANWFAIIFNROU","download_json":"https://pith.science/pith/OFBBFEOSCCRWG7ANWFAIIFNROU.json","view_paper":"https://pith.science/paper/OFBBFEOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07210&json=true","fetch_graph":"https://pith.science/api/pith-number/OFBBFEOSCCRWG7ANWFAIIFNROU/graph.json","fetch_events":"https://pith.science/api/pith-number/OFBBFEOSCCRWG7ANWFAIIFNROU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFBBFEOSCCRWG7ANWFAIIFNROU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFBBFEOSCCRWG7ANWFAIIFNROU/action/storage_attestation","attest_author":"https://pith.science/pith/OFBBFEOSCCRWG7ANWFAIIFNROU/action/author_attestation","sign_citation":"https://pith.science/pith/OFBBFEOSCCRWG7ANWFAIIFNROU/action/citation_signature","submit_replication":"https://pith.science/pith/OFBBFEOSCCRWG7ANWFAIIFNROU/action/replication_record"}},"created_at":"2026-07-05T05:16:49.388379+00:00","updated_at":"2026-07-05T05:16:49.388379+00:00"}