{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H4EONSHR5QQ7TGGENUUEUJRGPE","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":"ec21ba89fcf7b2638c1bffa3d733208b21ac28f2875905ea39a92afc2a0b703d","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-04-24T10:15:58Z","title_canon_sha256":"3532f434bc80c53c222af782f3a0e46826f51363017391560e85450698c3cdb2"},"schema_version":"1.0","source":{"id":"2304.11976","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.11976","created_at":"2026-07-05T07:24:49Z"},{"alias_kind":"arxiv_version","alias_value":"2304.11976v1","created_at":"2026-07-05T07:24:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11976","created_at":"2026-07-05T07:24:49Z"},{"alias_kind":"pith_short_12","alias_value":"H4EONSHR5QQ7","created_at":"2026-07-05T07:24:49Z"},{"alias_kind":"pith_short_16","alias_value":"H4EONSHR5QQ7TGGE","created_at":"2026-07-05T07:24:49Z"},{"alias_kind":"pith_short_8","alias_value":"H4EONSHR","created_at":"2026-07-05T07:24:49Z"}],"graph_snapshots":[{"event_id":"sha256:9d70e5bb86c69c1fc70c7d72f736cf47e51f7e9579eace3beb922ea1b0041c48","target":"graph","created_at":"2026-07-05T07:24:49Z","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/2304.11976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a zero-shot text-to-speech (TTS) conditioned by a self-supervised speech-representation model acquired through self-supervised learning (SSL). Conventional methods with embedding vectors from x-vector or global style tokens still have a gap in reproducing the speaker characteristics of unseen speakers. A novel point of the proposed method is the direct use of the SSL model to obtain embedding vectors from speech representations trained with a large amount of data. We also introduce the separate conditioning of acoustic features and a phoneme duration predictor to obtain the","authors_text":"Hiroki Kanagawa, Kenichi Fujita, Takafumi Moriya, Takanori Ashihara, Yusuke Ijima","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-04-24T10:15:58Z","title":"Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11976","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:df7f425c25b2adc6e81434be25f0e5e4f73eb1f7e0debdb537173a520be070fb","target":"record","created_at":"2026-07-05T07:24:49Z","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":"ec21ba89fcf7b2638c1bffa3d733208b21ac28f2875905ea39a92afc2a0b703d","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-04-24T10:15:58Z","title_canon_sha256":"3532f434bc80c53c222af782f3a0e46826f51363017391560e85450698c3cdb2"},"schema_version":"1.0","source":{"id":"2304.11976","kind":"arxiv","version":1}},"canonical_sha256":"3f08e6c8f1ec21f998c46d284a262679165e12c7e32ed03fea42f13c2b588c2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f08e6c8f1ec21f998c46d284a262679165e12c7e32ed03fea42f13c2b588c2c","first_computed_at":"2026-07-05T07:24:49.705934Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:49.705934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zv+32Ut/MvzoxyNM//C9Og17eQa2sTmo0I+66xpda1kC1Y7YVTanePXmhl1eD4asL4CraeKzMGPY1AxDyf61BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:49.706440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.11976","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df7f425c25b2adc6e81434be25f0e5e4f73eb1f7e0debdb537173a520be070fb","sha256:9d70e5bb86c69c1fc70c7d72f736cf47e51f7e9579eace3beb922ea1b0041c48"],"state_sha256":"7949cbe74809e6286bed554c53fe443ad770e4673741205aba1a9a356c80e9b0"}