{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:H2QRJVZJ7NNVS3DTHD5IUBD27V","short_pith_number":"pith:H2QRJVZJ","schema_version":"1.0","canonical_sha256":"3ea114d729fb5b596c7338fa8a047afd4e50625b2d20ccf3df60a45992bf0a19","source":{"kind":"arxiv","id":"2104.05557","version":2},"attestation_state":"computed","paper":{"title":"SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","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","submitted_at":"2021-04-02T22:31:45Z","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"},"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":"2104.05557","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-04-02T22:31:45Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"3109ce1d81a3397f94272af1053598d494f24ab04c6656883839d112e6b74b1c","abstract_canon_sha256":"9ec12cef183b0f8644493bae73ad0389c781ce9c14e7d4063e35cac91db0ce42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:54.621969Z","signature_b64":"/g4oFFCtE+L9rHlsV8nu0ssQ77TOprrKx2o0iyOgA+7UL7zDZujlEIoLcjLxM9Q0d3Q12z61mJgO1KfJvVSRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ea114d729fb5b596c7338fa8a047afd4e50625b2d20ccf3df60a45992bf0a19","last_reissued_at":"2026-07-05T02:49:54.621491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:54.621491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","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","submitted_at":"2021-04-02T22:31:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05557","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/2104.05557/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":"2104.05557","created_at":"2026-07-05T02:49:54.621547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.05557v2","created_at":"2026-07-05T02:49:54.621547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05557","created_at":"2026-07-05T02:49:54.621547+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2QRJVZJ7NNV","created_at":"2026-07-05T02:49:54.621547+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2QRJVZJ7NNVS3DT","created_at":"2026-07-05T02:49:54.621547+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2QRJVZJ","created_at":"2026-07-05T02:49:54.621547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14988","citing_title":"DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H2QRJVZJ7NNVS3DTHD5IUBD27V","json":"https://pith.science/pith/H2QRJVZJ7NNVS3DTHD5IUBD27V.json","graph_json":"https://pith.science/api/pith-number/H2QRJVZJ7NNVS3DTHD5IUBD27V/graph.json","events_json":"https://pith.science/api/pith-number/H2QRJVZJ7NNVS3DTHD5IUBD27V/events.json","paper":"https://pith.science/paper/H2QRJVZJ"},"agent_actions":{"view_html":"https://pith.science/pith/H2QRJVZJ7NNVS3DTHD5IUBD27V","download_json":"https://pith.science/pith/H2QRJVZJ7NNVS3DTHD5IUBD27V.json","view_paper":"https://pith.science/paper/H2QRJVZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.05557&json=true","fetch_graph":"https://pith.science/api/pith-number/H2QRJVZJ7NNVS3DTHD5IUBD27V/graph.json","fetch_events":"https://pith.science/api/pith-number/H2QRJVZJ7NNVS3DTHD5IUBD27V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2QRJVZJ7NNVS3DTHD5IUBD27V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2QRJVZJ7NNVS3DTHD5IUBD27V/action/storage_attestation","attest_author":"https://pith.science/pith/H2QRJVZJ7NNVS3DTHD5IUBD27V/action/author_attestation","sign_citation":"https://pith.science/pith/H2QRJVZJ7NNVS3DTHD5IUBD27V/action/citation_signature","submit_replication":"https://pith.science/pith/H2QRJVZJ7NNVS3DTHD5IUBD27V/action/replication_record"}},"created_at":"2026-07-05T02:49:54.621547+00:00","updated_at":"2026-07-05T02:49:54.621547+00:00"}