{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JBPTQKV5EMKVMCXWHDO7RA74MC","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":"d958274563c579a482ef15e9235c197bb4173cfda3e510044f6882dae3dee13c","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-02-22T07:43:30Z","title_canon_sha256":"e51e6f431ac48ed470b1623ec9344a3cdcbf4dc668a357fb2fde0773dae847a2"},"schema_version":"1.0","source":{"id":"2202.10712","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.10712","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"arxiv_version","alias_value":"2202.10712v1","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.10712","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"pith_short_12","alias_value":"JBPTQKV5EMKV","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"pith_short_16","alias_value":"JBPTQKV5EMKVMCXW","created_at":"2026-07-05T03:59:07Z"},{"alias_kind":"pith_short_8","alias_value":"JBPTQKV5","created_at":"2026-07-05T03:59:07Z"}],"graph_snapshots":[{"event_id":"sha256:bbae82a448eceac1fb8322a97fce6601e0db2dece45c44e59f174213a8d5a647","target":"graph","created_at":"2026-07-05T03:59:07Z","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/2202.10712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-speaker text-to-speech (TTS) using a few adaption data is a challenge in practical applications. To address that, we propose a zero-shot multi-speaker TTS, named nnSpeech, that could synthesis a new speaker voice without fine-tuning and using only one adaption utterance. Compared with using a speaker representation module to extract the characteristics of new speakers, our method bases on a speaker-guided conditional variational autoencoder and can generate a variable Z, which contains both speaker characteristics and content information. The latent variable Z distribution is approximate","authors_text":"Botao Zhao, Jianzong Wang, Jing Xiao, Ning Cheng, Xulong Zhang","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-02-22T07:43:30Z","title":"nnSpeech: Speaker-Guided Conditional Variational Autoencoder for Zero-shot Multi-speaker Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.10712","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":"sha256:5b2400123d4624ad73c1e2f675cd86f53c938e47b45440cb6526a83a837672cf","target":"record","created_at":"2026-07-05T03:59:07Z","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":"d958274563c579a482ef15e9235c197bb4173cfda3e510044f6882dae3dee13c","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-02-22T07:43:30Z","title_canon_sha256":"e51e6f431ac48ed470b1623ec9344a3cdcbf4dc668a357fb2fde0773dae847a2"},"schema_version":"1.0","source":{"id":"2202.10712","kind":"arxiv","version":1}},"canonical_sha256":"485f382abd2315560af638ddf883fc608bf60d073dcb47db14beeabc10cdbe16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"485f382abd2315560af638ddf883fc608bf60d073dcb47db14beeabc10cdbe16","first_computed_at":"2026-07-05T03:59:07.614802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:59:07.614802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NH5dpTOkIwFk51LPKm/OnRsH2vCwg8/fZEmIuOzaTfrKIEt7Sm4i4Lz9/qT0hd1MbhbH21BouS0cIdqfhgEJAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:59:07.615371Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.10712","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b2400123d4624ad73c1e2f675cd86f53c938e47b45440cb6526a83a837672cf","sha256:bbae82a448eceac1fb8322a97fce6601e0db2dece45c44e59f174213a8d5a647"],"state_sha256":"781039f2258ddc1f0141d90797467e50cb26f341172be86cc7a0442999ee8cfc"}