{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6XVPADXGZQAPIHKDNPIYSHFEFV","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":"b336a5184a4fef180d0853d6c010aad0e6f7f1a360f9934d0d36903bb45115ac","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-10-12T07:40:15Z","title_canon_sha256":"dffad2fe974f9bb57af69dd8d93420e5cded94f021e35bfe951ca23b6f465de6"},"schema_version":"1.0","source":{"id":"2210.05979","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05979","created_at":"2026-07-05T05:18:07Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05979v2","created_at":"2026-07-05T05:18:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05979","created_at":"2026-07-05T05:18:07Z"},{"alias_kind":"pith_short_12","alias_value":"6XVPADXGZQAP","created_at":"2026-07-05T05:18:07Z"},{"alias_kind":"pith_short_16","alias_value":"6XVPADXGZQAPIHKD","created_at":"2026-07-05T05:18:07Z"},{"alias_kind":"pith_short_8","alias_value":"6XVPADXG","created_at":"2026-07-05T05:18:07Z"}],"graph_snapshots":[{"event_id":"sha256:8e1049489032032cb7d51e53e7b249fb50ba4fe99db8dca493e1f7b6067ef27a","target":"graph","created_at":"2026-07-05T05:18:07Z","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/2210.05979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Byoung Jin Choi, Minchan Kim, Myeonghun Jeong, Nam Soo Kim, Sung Hwan Mun","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-10-12T07:40:15Z","title":"Adversarial Speaker-Consistency Learning Using Untranscribed Speech Data for Zero-Shot Multi-Speaker Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05979","kind":"arxiv","version":2},"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:a000b5488dfa69997c54a5b6ac0e7719b1e8f3e8fa407bd975fa24fc6dc2d025","target":"record","created_at":"2026-07-05T05:18:07Z","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":"b336a5184a4fef180d0853d6c010aad0e6f7f1a360f9934d0d36903bb45115ac","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-10-12T07:40:15Z","title_canon_sha256":"dffad2fe974f9bb57af69dd8d93420e5cded94f021e35bfe951ca23b6f465de6"},"schema_version":"1.0","source":{"id":"2210.05979","kind":"arxiv","version":2}},"canonical_sha256":"f5eaf00ee6cc00f41d436bd1891ca42d4d0cf6d0387401d4745388971dedadab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5eaf00ee6cc00f41d436bd1891ca42d4d0cf6d0387401d4745388971dedadab","first_computed_at":"2026-07-05T05:18:07.685060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:18:07.685060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cCErJIxqJodRFempoq3cAgizTTeAzwOuZnSmQQ1DrgP5rSd9gsAoiBDoq0BZWuk0L8c6rlyr4eRQV/y3IN2BAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:18:07.685542Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05979","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a000b5488dfa69997c54a5b6ac0e7719b1e8f3e8fa407bd975fa24fc6dc2d025","sha256:8e1049489032032cb7d51e53e7b249fb50ba4fe99db8dca493e1f7b6067ef27a"],"state_sha256":"58e938c54538bbc972318b825cc98e53499f2cd0895793afffcabf7aa5736e7e"}