{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WJGWSSTA4T4WRS7CW4IC6GTTBD","short_pith_number":"pith:WJGWSSTA","schema_version":"1.0","canonical_sha256":"b24d694a60e4f968cbe2b7102f1a7308dcba7fa4d840e72207bf42f545b2b867","source":{"kind":"arxiv","id":"1904.02373","version":1},"attestation_state":"computed","paper":{"title":"Multi-reference Tacotron by Intercross Training for Style Disentangling,Transfer and Control in Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changbin Chen, Yanyao Bian, Yongguo Kang, Zhenglin Pan","submitted_at":"2019-04-04T06:37:19Z","abstract_excerpt":"Speech style control and transfer techniques aim to enrich the diversity and expressiveness of synthesized speech. Existing approaches model all speech styles into one representation, lacking the ability to control a specific speech feature independently. To address this issue, we introduce a novel multi-reference structure to Tacotron and propose intercross training approach, which together ensure that each sub-encoder of the multi-reference encoder independently disentangles and controls a specific style. Experimental results show that our model is able to control and transfer desired speech"},"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":"1904.02373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-04T06:37:19Z","cross_cats_sorted":[],"title_canon_sha256":"758b935c2bb099686e8f979073bfa7ffc6200883ab3fdc265705fc418c10e9b8","abstract_canon_sha256":"a61ad611d64e4cd8da5b96a9b1c5ee89efc805359a5a70e5d654316a8714e11e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:23.874775Z","signature_b64":"wGwtk1rVIaXBzPGCWKCcRZVjiN8j1eXGKn++C/gkgq69aBhlYTMRoU+JhGMmqzAdUAJnIiNGctuaH1cPlvB9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b24d694a60e4f968cbe2b7102f1a7308dcba7fa4d840e72207bf42f545b2b867","last_reissued_at":"2026-05-17T23:49:23.874378Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:23.874378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-reference Tacotron by Intercross Training for Style Disentangling,Transfer and Control in Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changbin Chen, Yanyao Bian, Yongguo Kang, Zhenglin Pan","submitted_at":"2019-04-04T06:37:19Z","abstract_excerpt":"Speech style control and transfer techniques aim to enrich the diversity and expressiveness of synthesized speech. Existing approaches model all speech styles into one representation, lacking the ability to control a specific speech feature independently. To address this issue, we introduce a novel multi-reference structure to Tacotron and propose intercross training approach, which together ensure that each sub-encoder of the multi-reference encoder independently disentangles and controls a specific style. Experimental results show that our model is able to control and transfer desired speech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02373","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":""},"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":"1904.02373","created_at":"2026-05-17T23:49:23.874451+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02373v1","created_at":"2026-05-17T23:49:23.874451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02373","created_at":"2026-05-17T23:49:23.874451+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJGWSSTA4T4W","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJGWSSTA4T4WRS7C","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJGWSSTA","created_at":"2026-05-18T12:33:30.264802+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/WJGWSSTA4T4WRS7CW4IC6GTTBD","json":"https://pith.science/pith/WJGWSSTA4T4WRS7CW4IC6GTTBD.json","graph_json":"https://pith.science/api/pith-number/WJGWSSTA4T4WRS7CW4IC6GTTBD/graph.json","events_json":"https://pith.science/api/pith-number/WJGWSSTA4T4WRS7CW4IC6GTTBD/events.json","paper":"https://pith.science/paper/WJGWSSTA"},"agent_actions":{"view_html":"https://pith.science/pith/WJGWSSTA4T4WRS7CW4IC6GTTBD","download_json":"https://pith.science/pith/WJGWSSTA4T4WRS7CW4IC6GTTBD.json","view_paper":"https://pith.science/paper/WJGWSSTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02373&json=true","fetch_graph":"https://pith.science/api/pith-number/WJGWSSTA4T4WRS7CW4IC6GTTBD/graph.json","fetch_events":"https://pith.science/api/pith-number/WJGWSSTA4T4WRS7CW4IC6GTTBD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJGWSSTA4T4WRS7CW4IC6GTTBD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJGWSSTA4T4WRS7CW4IC6GTTBD/action/storage_attestation","attest_author":"https://pith.science/pith/WJGWSSTA4T4WRS7CW4IC6GTTBD/action/author_attestation","sign_citation":"https://pith.science/pith/WJGWSSTA4T4WRS7CW4IC6GTTBD/action/citation_signature","submit_replication":"https://pith.science/pith/WJGWSSTA4T4WRS7CW4IC6GTTBD/action/replication_record"}},"created_at":"2026-05-17T23:49:23.874451+00:00","updated_at":"2026-05-17T23:49:23.874451+00:00"}