{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:K2FXZZUQHOZYK27RXJOXFF4I5U","short_pith_number":"pith:K2FXZZUQ","schema_version":"1.0","canonical_sha256":"568b7ce6903bb3856bf1ba5d729788ed3e15f88ee962066b4b8dd805897a193d","source":{"kind":"arxiv","id":"2201.08124","version":1},"attestation_state":"computed","paper":{"title":"Cross-Lingual Text-to-Speech Using Multi-Task Learning and Speaker Classifier Joint Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"J. Yang, Lei He","submitted_at":"2022-01-20T12:02:58Z","abstract_excerpt":"In cross-lingual speech synthesis, the speech in various languages can be synthesized for a monoglot speaker. Normally, only the data of monoglot speakers are available for model training, thus the speaker similarity is relatively low between the synthesized cross-lingual speech and the native language recordings. Based on the multilingual transformer text-to-speech model, this paper studies a multi-task learning framework to improve the cross-lingual speaker similarity. To further improve the speaker similarity, joint training with a speaker classifier is proposed. Here, a scheme similar to p"},"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":"2201.08124","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-01-20T12:02:58Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"8117c5a0ad974259a35cf23a18874f8d7c0d530df5ab799698992d38dac235ef","abstract_canon_sha256":"28bda4b5a7ced02cc7f2791dbc1d533e2f377ef312a5775431a03557898b6656"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:08.951454Z","signature_b64":"B3kQGF6SMjc/X4uGnVeUya1KmCHz4EYKCKCnqEou9iZ9Um6aVUvNKwCItrpcFs6wOlnnqjh+yWRIBKSbWQCwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"568b7ce6903bb3856bf1ba5d729788ed3e15f88ee962066b4b8dd805897a193d","last_reissued_at":"2026-07-05T03:50:08.950966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:08.950966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Lingual Text-to-Speech Using Multi-Task Learning and Speaker Classifier Joint Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"J. Yang, Lei He","submitted_at":"2022-01-20T12:02:58Z","abstract_excerpt":"In cross-lingual speech synthesis, the speech in various languages can be synthesized for a monoglot speaker. Normally, only the data of monoglot speakers are available for model training, thus the speaker similarity is relatively low between the synthesized cross-lingual speech and the native language recordings. Based on the multilingual transformer text-to-speech model, this paper studies a multi-task learning framework to improve the cross-lingual speaker similarity. To further improve the speaker similarity, joint training with a speaker classifier is proposed. Here, a scheme similar to p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08124","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/2201.08124/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":"2201.08124","created_at":"2026-07-05T03:50:08.951041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.08124v1","created_at":"2026-07-05T03:50:08.951041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08124","created_at":"2026-07-05T03:50:08.951041+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2FXZZUQHOZY","created_at":"2026-07-05T03:50:08.951041+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2FXZZUQHOZYK27R","created_at":"2026-07-05T03:50:08.951041+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2FXZZUQ","created_at":"2026-07-05T03:50:08.951041+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.04639","citing_title":"Language translation, and change of accent for speech-to-speech task using diffusion model","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K2FXZZUQHOZYK27RXJOXFF4I5U","json":"https://pith.science/pith/K2FXZZUQHOZYK27RXJOXFF4I5U.json","graph_json":"https://pith.science/api/pith-number/K2FXZZUQHOZYK27RXJOXFF4I5U/graph.json","events_json":"https://pith.science/api/pith-number/K2FXZZUQHOZYK27RXJOXFF4I5U/events.json","paper":"https://pith.science/paper/K2FXZZUQ"},"agent_actions":{"view_html":"https://pith.science/pith/K2FXZZUQHOZYK27RXJOXFF4I5U","download_json":"https://pith.science/pith/K2FXZZUQHOZYK27RXJOXFF4I5U.json","view_paper":"https://pith.science/paper/K2FXZZUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.08124&json=true","fetch_graph":"https://pith.science/api/pith-number/K2FXZZUQHOZYK27RXJOXFF4I5U/graph.json","fetch_events":"https://pith.science/api/pith-number/K2FXZZUQHOZYK27RXJOXFF4I5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2FXZZUQHOZYK27RXJOXFF4I5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2FXZZUQHOZYK27RXJOXFF4I5U/action/storage_attestation","attest_author":"https://pith.science/pith/K2FXZZUQHOZYK27RXJOXFF4I5U/action/author_attestation","sign_citation":"https://pith.science/pith/K2FXZZUQHOZYK27RXJOXFF4I5U/action/citation_signature","submit_replication":"https://pith.science/pith/K2FXZZUQHOZYK27RXJOXFF4I5U/action/replication_record"}},"created_at":"2026-07-05T03:50:08.951041+00:00","updated_at":"2026-07-05T03:50:08.951041+00:00"}