{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:K2FXZZUQHOZYK27RXJOXFF4I5U","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"28bda4b5a7ced02cc7f2791dbc1d533e2f377ef312a5775431a03557898b6656","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-01-20T12:02:58Z","title_canon_sha256":"8117c5a0ad974259a35cf23a18874f8d7c0d530df5ab799698992d38dac235ef"},"schema_version":"1.0","source":{"id":"2201.08124","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.08124","created_at":"2026-07-05T03:50:08Z"},{"alias_kind":"arxiv_version","alias_value":"2201.08124v1","created_at":"2026-07-05T03:50:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08124","created_at":"2026-07-05T03:50:08Z"},{"alias_kind":"pith_short_12","alias_value":"K2FXZZUQHOZY","created_at":"2026-07-05T03:50:08Z"},{"alias_kind":"pith_short_16","alias_value":"K2FXZZUQHOZYK27R","created_at":"2026-07-05T03:50:08Z"},{"alias_kind":"pith_short_8","alias_value":"K2FXZZUQ","created_at":"2026-07-05T03:50:08Z"}],"graph_snapshots":[{"event_id":"sha256:3e5393350a8b12ee6e6f4d3b041f37a4e905a15cb025ebfc55377c84e0dcfbc1","target":"graph","created_at":"2026-07-05T03:50:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2201.08124/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"J. Yang, Lei He","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-01-20T12:02:58Z","title":"Cross-Lingual Text-to-Speech Using Multi-Task Learning and Speaker Classifier Joint Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08124","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:57a7c6e7a532cd874defdb56e6dca1e60851b63221b2613752f89012973d2179","target":"record","created_at":"2026-07-05T03:50:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"28bda4b5a7ced02cc7f2791dbc1d533e2f377ef312a5775431a03557898b6656","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-01-20T12:02:58Z","title_canon_sha256":"8117c5a0ad974259a35cf23a18874f8d7c0d530df5ab799698992d38dac235ef"},"schema_version":"1.0","source":{"id":"2201.08124","kind":"arxiv","version":1}},"canonical_sha256":"568b7ce6903bb3856bf1ba5d729788ed3e15f88ee962066b4b8dd805897a193d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"568b7ce6903bb3856bf1ba5d729788ed3e15f88ee962066b4b8dd805897a193d","first_computed_at":"2026-07-05T03:50:08.950966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:50:08.950966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B3kQGF6SMjc/X4uGnVeUya1KmCHz4EYKCKCnqEou9iZ9Um6aVUvNKwCItrpcFs6wOlnnqjh+yWRIBKSbWQCwCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:50:08.951454Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.08124","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57a7c6e7a532cd874defdb56e6dca1e60851b63221b2613752f89012973d2179","sha256:3e5393350a8b12ee6e6f4d3b041f37a4e905a15cb025ebfc55377c84e0dcfbc1"],"state_sha256":"2593054895af9dc6c74bac088bfb26eef3f99c860f6ff4fb1618b54910c73f51"}