{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WCJAGKPZ64B7NGWZUXRRPSE4GZ","short_pith_number":"pith:WCJAGKPZ","schema_version":"1.0","canonical_sha256":"b0920329f9f703f69ad9a5e317c89c3646433b6e07e296c38d109d61bd2e5b7c","source":{"kind":"arxiv","id":"1806.04558","version":4},"attestation_state":"computed","paper":{"title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Fei Ren, Ignacio Lopez Moreno, Jonathan Shen, Patrick Nguyen, Quan Wang, Ron J. Weiss, Ruoming Pang, Ye Jia, Yonghui Wu, Yu Zhang, Zhifeng Chen","submitted_at":"2018-06-12T14:29:22Z","abstract_excerpt":"We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently trained components: (1) a speaker encoder network, trained on a speaker verification task using an independent dataset of noisy speech from thousands of speakers without transcripts, to generate a fixed-dimensional embedding vector from seconds of reference speech from a target speaker; (2) a sequence-to-sequence synthesis network based on Tacotron 2, which g"},"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":"1806.04558","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-12T14:29:22Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"9e4cac955ad37a1225a5cfc2f4ab03b493659187839ce76b5c09eea060ff3137","abstract_canon_sha256":"38b5228479e80a2ee2e666b1ffb9bd1295a1d40aa847004e072562ba989bc8fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:02.884173Z","signature_b64":"cXr/UrCO5mYJXMcH5efZ77j7qqMDRSF493SCYcwcPOAjDgtgTWiY6oHzKMpiA3He0JfoW0yenkTlBPiGUBmRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0920329f9f703f69ad9a5e317c89c3646433b6e07e296c38d109d61bd2e5b7c","last_reissued_at":"2026-05-17T23:57:02.883524Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:02.883524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Fei Ren, Ignacio Lopez Moreno, Jonathan Shen, Patrick Nguyen, Quan Wang, Ron J. Weiss, Ruoming Pang, Ye Jia, Yonghui Wu, Yu Zhang, Zhifeng Chen","submitted_at":"2018-06-12T14:29:22Z","abstract_excerpt":"We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently trained components: (1) a speaker encoder network, trained on a speaker verification task using an independent dataset of noisy speech from thousands of speakers without transcripts, to generate a fixed-dimensional embedding vector from seconds of reference speech from a target speaker; (2) a sequence-to-sequence synthesis network based on Tacotron 2, which g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04558","kind":"arxiv","version":4},"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":"1806.04558","created_at":"2026-05-17T23:57:02.883630+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.04558v4","created_at":"2026-05-17T23:57:02.883630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04558","created_at":"2026-05-17T23:57:02.883630+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCJAGKPZ64B7","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCJAGKPZ64B7NGWZ","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCJAGKPZ","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.07769","citing_title":"Hierarchical Sequence to Sequence Voice Conversion with Limited Data","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ","json":"https://pith.science/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ.json","graph_json":"https://pith.science/api/pith-number/WCJAGKPZ64B7NGWZUXRRPSE4GZ/graph.json","events_json":"https://pith.science/api/pith-number/WCJAGKPZ64B7NGWZUXRRPSE4GZ/events.json","paper":"https://pith.science/paper/WCJAGKPZ"},"agent_actions":{"view_html":"https://pith.science/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ","download_json":"https://pith.science/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ.json","view_paper":"https://pith.science/paper/WCJAGKPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.04558&json=true","fetch_graph":"https://pith.science/api/pith-number/WCJAGKPZ64B7NGWZUXRRPSE4GZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WCJAGKPZ64B7NGWZUXRRPSE4GZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ/action/storage_attestation","attest_author":"https://pith.science/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ/action/author_attestation","sign_citation":"https://pith.science/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ/action/citation_signature","submit_replication":"https://pith.science/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ/action/replication_record"}},"created_at":"2026-05-17T23:57:02.883630+00:00","updated_at":"2026-05-17T23:57:02.883630+00:00"}