{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:H2QRJVZJ7NNVS3DTHD5IUBD27V","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":"9ec12cef183b0f8644493bae73ad0389c781ce9c14e7d4063e35cac91db0ce42","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-04-02T22:31:45Z","title_canon_sha256":"3109ce1d81a3397f94272af1053598d494f24ab04c6656883839d112e6b74b1c"},"schema_version":"1.0","source":{"id":"2104.05557","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.05557","created_at":"2026-07-05T02:49:54Z"},{"alias_kind":"arxiv_version","alias_value":"2104.05557v2","created_at":"2026-07-05T02:49:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05557","created_at":"2026-07-05T02:49:54Z"},{"alias_kind":"pith_short_12","alias_value":"H2QRJVZJ7NNV","created_at":"2026-07-05T02:49:54Z"},{"alias_kind":"pith_short_16","alias_value":"H2QRJVZJ7NNVS3DT","created_at":"2026-07-05T02:49:54Z"},{"alias_kind":"pith_short_8","alias_value":"H2QRJVZJ","created_at":"2026-07-05T02:49:54Z"}],"graph_snapshots":[{"event_id":"sha256:0526c95888ee1454e8c15946349b8d95b2636ab6abbf9170ad09279856ea52bf","target":"graph","created_at":"2026-07-05T02:49:54Z","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/2104.05557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose SC-GlowTTS: an efficient zero-shot multi-speaker text-to-speech model that improves similarity for speakers unseen during training. We propose a speaker-conditional architecture that explores a flow-based decoder that works in a zero-shot scenario. As text encoders, we explore a dilated residual convolutional-based encoder, gated convolutional-based encoder, and transformer-based encoder. Additionally, we have shown that adjusting a GAN-based vocoder for the spectrograms predicted by the TTS model on the training dataset can significantly improve the similarity and sp","authors_text":"Anderson da Silva Soares, Arnaldo Candido Junior, Christopher Shulby, Edresson Casanova, Eren G\\\"olge, Frederico Santos de Oliveira, Moacir Antonelli Ponti, Nicolas Michael M\\\"uller, Sandra Maria Aluisio","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-04-02T22:31:45Z","title":"SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05557","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":"sha256:3e54714081b17cb1572a78a47cf7eac329633213a302ce34d0bb918fe2937827","target":"record","created_at":"2026-07-05T02:49:54Z","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":"9ec12cef183b0f8644493bae73ad0389c781ce9c14e7d4063e35cac91db0ce42","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-04-02T22:31:45Z","title_canon_sha256":"3109ce1d81a3397f94272af1053598d494f24ab04c6656883839d112e6b74b1c"},"schema_version":"1.0","source":{"id":"2104.05557","kind":"arxiv","version":2}},"canonical_sha256":"3ea114d729fb5b596c7338fa8a047afd4e50625b2d20ccf3df60a45992bf0a19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ea114d729fb5b596c7338fa8a047afd4e50625b2d20ccf3df60a45992bf0a19","first_computed_at":"2026-07-05T02:49:54.621491Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:54.621491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/g4oFFCtE+L9rHlsV8nu0ssQ77TOprrKx2o0iyOgA+7UL7zDZujlEIoLcjLxM9Q0d3Q12z61mJgO1KfJvVSRCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:54.621969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.05557","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e54714081b17cb1572a78a47cf7eac329633213a302ce34d0bb918fe2937827","sha256:0526c95888ee1454e8c15946349b8d95b2636ab6abbf9170ad09279856ea52bf"],"state_sha256":"998f5501bf5983f65b869c36886436f76ad0f975f21c10478340cf990fc595ae"}