{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6XVPADXGZQAPIHKDNPIYSHFEFV","short_pith_number":"pith:6XVPADXG","schema_version":"1.0","canonical_sha256":"f5eaf00ee6cc00f41d436bd1891ca42d4d0cf6d0387401d4745388971dedadab","source":{"kind":"arxiv","id":"2210.05979","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Speaker-Consistency Learning Using Untranscribed Speech Data for Zero-Shot Multi-Speaker Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Byoung Jin Choi, Minchan Kim, Myeonghun Jeong, Nam Soo Kim, Sung Hwan Mun","submitted_at":"2022-10-12T07:40:15Z","abstract_excerpt":"Several recently proposed text-to-speech (TTS) models achieved to generate the speech samples with the human-level quality in the single-speaker and multi-speaker TTS scenarios with a set of pre-defined speakers. However, synthesizing a new speaker's voice with a single reference audio, commonly known as zero-shot multi-speaker text-to-speech (ZSM-TTS), is still a very challenging task. The main challenge of ZSM-TTS is the speaker domain shift problem upon the speech generation of a new speaker. To mitigate this problem, we propose adversarial speaker-consistency learning (ASCL). The proposed "},"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":"2210.05979","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-10-12T07:40:15Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"dffad2fe974f9bb57af69dd8d93420e5cded94f021e35bfe951ca23b6f465de6","abstract_canon_sha256":"b336a5184a4fef180d0853d6c010aad0e6f7f1a360f9934d0d36903bb45115ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:07.685542Z","signature_b64":"cCErJIxqJodRFempoq3cAgizTTeAzwOuZnSmQQ1DrgP5rSd9gsAoiBDoq0BZWuk0L8c6rlyr4eRQV/y3IN2BAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5eaf00ee6cc00f41d436bd1891ca42d4d0cf6d0387401d4745388971dedadab","last_reissued_at":"2026-07-05T05:18:07.685060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:07.685060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Speaker-Consistency Learning Using Untranscribed Speech Data for Zero-Shot Multi-Speaker Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Byoung Jin Choi, Minchan Kim, Myeonghun Jeong, Nam Soo Kim, Sung Hwan Mun","submitted_at":"2022-10-12T07:40:15Z","abstract_excerpt":"Several recently proposed text-to-speech (TTS) models achieved to generate the speech samples with the human-level quality in the single-speaker and multi-speaker TTS scenarios with a set of pre-defined speakers. However, synthesizing a new speaker's voice with a single reference audio, commonly known as zero-shot multi-speaker text-to-speech (ZSM-TTS), is still a very challenging task. The main challenge of ZSM-TTS is the speaker domain shift problem upon the speech generation of a new speaker. To mitigate this problem, we propose adversarial speaker-consistency learning (ASCL). The proposed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05979","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/2210.05979/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":"2210.05979","created_at":"2026-07-05T05:18:07.685120+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05979v2","created_at":"2026-07-05T05:18:07.685120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05979","created_at":"2026-07-05T05:18:07.685120+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XVPADXGZQAP","created_at":"2026-07-05T05:18:07.685120+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XVPADXGZQAPIHKD","created_at":"2026-07-05T05:18:07.685120+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XVPADXG","created_at":"2026-07-05T05:18:07.685120+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/6XVPADXGZQAPIHKDNPIYSHFEFV","json":"https://pith.science/pith/6XVPADXGZQAPIHKDNPIYSHFEFV.json","graph_json":"https://pith.science/api/pith-number/6XVPADXGZQAPIHKDNPIYSHFEFV/graph.json","events_json":"https://pith.science/api/pith-number/6XVPADXGZQAPIHKDNPIYSHFEFV/events.json","paper":"https://pith.science/paper/6XVPADXG"},"agent_actions":{"view_html":"https://pith.science/pith/6XVPADXGZQAPIHKDNPIYSHFEFV","download_json":"https://pith.science/pith/6XVPADXGZQAPIHKDNPIYSHFEFV.json","view_paper":"https://pith.science/paper/6XVPADXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05979&json=true","fetch_graph":"https://pith.science/api/pith-number/6XVPADXGZQAPIHKDNPIYSHFEFV/graph.json","fetch_events":"https://pith.science/api/pith-number/6XVPADXGZQAPIHKDNPIYSHFEFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XVPADXGZQAPIHKDNPIYSHFEFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XVPADXGZQAPIHKDNPIYSHFEFV/action/storage_attestation","attest_author":"https://pith.science/pith/6XVPADXGZQAPIHKDNPIYSHFEFV/action/author_attestation","sign_citation":"https://pith.science/pith/6XVPADXGZQAPIHKDNPIYSHFEFV/action/citation_signature","submit_replication":"https://pith.science/pith/6XVPADXGZQAPIHKDNPIYSHFEFV/action/replication_record"}},"created_at":"2026-07-05T05:18:07.685120+00:00","updated_at":"2026-07-05T05:18:07.685120+00:00"}