{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3KHL4XLP445APGEDNMN7MCFHSX","short_pith_number":"pith:3KHL4XLP","schema_version":"1.0","canonical_sha256":"da8ebe5d6fe73a0798836b1bf608a795d5f2498b5eab4611e9cf6207548fed3a","source":{"kind":"arxiv","id":"2203.16930","version":2},"attestation_state":"computed","paper":{"title":"WavThruVec: Latent speech representation as intermediate features for neural speech synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hubert Siuzdak, Nori Jacoby, Piotr Dura, Pol van Rijn","submitted_at":"2022-03-31T10:21:08Z","abstract_excerpt":"Recent advances in neural text-to-speech research have been dominated by two-stage pipelines utilizing low-level intermediate speech representation such as mel-spectrograms. However, such predetermined features are fundamentally limited, because they do not allow to exploit the full potential of a data-driven approach through learning hidden representations. For this reason, several end-to-end methods have been proposed. However, such models are harder to train and require a large number of high-quality recordings with transcriptions. Here, we propose WavThruVec - a two-stage architecture that"},"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":"2203.16930","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T10:21:08Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"36ff052bd15dc629b9cfd5565fdd264ccee208670f407cfac84bf6b451a4933e","abstract_canon_sha256":"6c5d17ba04e823e84f248e5f3d899416f6348c79848cf60ebdcd513d52175e25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:45.433836Z","signature_b64":"zk/5ke1bc5FUKEODvpMh9VtpPbkuxHxJ+AGzzEXm6E3s+AL4BiT+FqHVKdDmEt63dxatx+V8CyhmH+0cUesaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da8ebe5d6fe73a0798836b1bf608a795d5f2498b5eab4611e9cf6207548fed3a","last_reissued_at":"2026-07-05T05:17:45.433426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:45.433426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WavThruVec: Latent speech representation as intermediate features for neural speech synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hubert Siuzdak, Nori Jacoby, Piotr Dura, Pol van Rijn","submitted_at":"2022-03-31T10:21:08Z","abstract_excerpt":"Recent advances in neural text-to-speech research have been dominated by two-stage pipelines utilizing low-level intermediate speech representation such as mel-spectrograms. However, such predetermined features are fundamentally limited, because they do not allow to exploit the full potential of a data-driven approach through learning hidden representations. For this reason, several end-to-end methods have been proposed. However, such models are harder to train and require a large number of high-quality recordings with transcriptions. Here, we propose WavThruVec - a two-stage architecture that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16930","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/2203.16930/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":"2203.16930","created_at":"2026-07-05T05:17:45.433479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16930v2","created_at":"2026-07-05T05:17:45.433479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16930","created_at":"2026-07-05T05:17:45.433479+00:00"},{"alias_kind":"pith_short_12","alias_value":"3KHL4XLP445A","created_at":"2026-07-05T05:17:45.433479+00:00"},{"alias_kind":"pith_short_16","alias_value":"3KHL4XLP445APGED","created_at":"2026-07-05T05:17:45.433479+00:00"},{"alias_kind":"pith_short_8","alias_value":"3KHL4XLP","created_at":"2026-07-05T05:17:45.433479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3KHL4XLP445APGEDNMN7MCFHSX","json":"https://pith.science/pith/3KHL4XLP445APGEDNMN7MCFHSX.json","graph_json":"https://pith.science/api/pith-number/3KHL4XLP445APGEDNMN7MCFHSX/graph.json","events_json":"https://pith.science/api/pith-number/3KHL4XLP445APGEDNMN7MCFHSX/events.json","paper":"https://pith.science/paper/3KHL4XLP"},"agent_actions":{"view_html":"https://pith.science/pith/3KHL4XLP445APGEDNMN7MCFHSX","download_json":"https://pith.science/pith/3KHL4XLP445APGEDNMN7MCFHSX.json","view_paper":"https://pith.science/paper/3KHL4XLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16930&json=true","fetch_graph":"https://pith.science/api/pith-number/3KHL4XLP445APGEDNMN7MCFHSX/graph.json","fetch_events":"https://pith.science/api/pith-number/3KHL4XLP445APGEDNMN7MCFHSX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3KHL4XLP445APGEDNMN7MCFHSX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3KHL4XLP445APGEDNMN7MCFHSX/action/storage_attestation","attest_author":"https://pith.science/pith/3KHL4XLP445APGEDNMN7MCFHSX/action/author_attestation","sign_citation":"https://pith.science/pith/3KHL4XLP445APGEDNMN7MCFHSX/action/citation_signature","submit_replication":"https://pith.science/pith/3KHL4XLP445APGEDNMN7MCFHSX/action/replication_record"}},"created_at":"2026-07-05T05:17:45.433479+00:00","updated_at":"2026-07-05T05:17:45.433479+00:00"}