{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MZ2AJ24NOBUMMDZNYSMXZ4JOVM","short_pith_number":"pith:MZ2AJ24N","schema_version":"1.0","canonical_sha256":"667404eb8d7068c60f2dc4997cf12eab27bc4bbe6b61920e97648ee4fb58584f","source":{"kind":"arxiv","id":"1804.00047","version":2},"attestation_state":"computed","paper":{"title":"Conditional End-to-End Audio Transforms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Albert Haque, Michelle Guo, Prateek Verma","submitted_at":"2018-03-30T20:17:31Z","abstract_excerpt":"We present an end-to-end method for transforming audio from one style to another. For the case of speech, by conditioning on speaker identities, we can train a single model to transform words spoken by multiple people into multiple target voices. For the case of music, we can specify musical instruments and achieve the same result. Architecturally, our method is a fully-differentiable sequence-to-sequence model based on convolutional and hierarchical recurrent neural networks. It is designed to capture long-term acoustic dependencies, requires minimal post-processing, and produces realistic au"},"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":"1804.00047","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-03-30T20:17:31Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"d0e04d4939e4364ec342c644c3e022c609afae061640fda07dac0beb44a893af","abstract_canon_sha256":"1ba2aa11eaf2c3264a6a6683e1c99638d792d72ad23517e571eae3b9ce3936d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:00.042183Z","signature_b64":"Xdd48SR/W0fUwqfeeJ/9tvzTi4h1mfIhS2GVou9X23OdHLrx8Axp6a6HaklHON0cuMJxlDcyEe5fq6NWwkztAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"667404eb8d7068c60f2dc4997cf12eab27bc4bbe6b61920e97648ee4fb58584f","last_reissued_at":"2026-05-18T00:14:00.041289Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:00.041289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional End-to-End Audio Transforms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Albert Haque, Michelle Guo, Prateek Verma","submitted_at":"2018-03-30T20:17:31Z","abstract_excerpt":"We present an end-to-end method for transforming audio from one style to another. For the case of speech, by conditioning on speaker identities, we can train a single model to transform words spoken by multiple people into multiple target voices. For the case of music, we can specify musical instruments and achieve the same result. Architecturally, our method is a fully-differentiable sequence-to-sequence model based on convolutional and hierarchical recurrent neural networks. It is designed to capture long-term acoustic dependencies, requires minimal post-processing, and produces realistic au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00047","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":""},"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":"1804.00047","created_at":"2026-05-18T00:14:00.041453+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.00047v2","created_at":"2026-05-18T00:14:00.041453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00047","created_at":"2026-05-18T00:14:00.041453+00:00"},{"alias_kind":"pith_short_12","alias_value":"MZ2AJ24NOBUM","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"MZ2AJ24NOBUMMDZN","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"MZ2AJ24N","created_at":"2026-05-18T12:32:40.477152+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/MZ2AJ24NOBUMMDZNYSMXZ4JOVM","json":"https://pith.science/pith/MZ2AJ24NOBUMMDZNYSMXZ4JOVM.json","graph_json":"https://pith.science/api/pith-number/MZ2AJ24NOBUMMDZNYSMXZ4JOVM/graph.json","events_json":"https://pith.science/api/pith-number/MZ2AJ24NOBUMMDZNYSMXZ4JOVM/events.json","paper":"https://pith.science/paper/MZ2AJ24N"},"agent_actions":{"view_html":"https://pith.science/pith/MZ2AJ24NOBUMMDZNYSMXZ4JOVM","download_json":"https://pith.science/pith/MZ2AJ24NOBUMMDZNYSMXZ4JOVM.json","view_paper":"https://pith.science/paper/MZ2AJ24N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.00047&json=true","fetch_graph":"https://pith.science/api/pith-number/MZ2AJ24NOBUMMDZNYSMXZ4JOVM/graph.json","fetch_events":"https://pith.science/api/pith-number/MZ2AJ24NOBUMMDZNYSMXZ4JOVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MZ2AJ24NOBUMMDZNYSMXZ4JOVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MZ2AJ24NOBUMMDZNYSMXZ4JOVM/action/storage_attestation","attest_author":"https://pith.science/pith/MZ2AJ24NOBUMMDZNYSMXZ4JOVM/action/author_attestation","sign_citation":"https://pith.science/pith/MZ2AJ24NOBUMMDZNYSMXZ4JOVM/action/citation_signature","submit_replication":"https://pith.science/pith/MZ2AJ24NOBUMMDZNYSMXZ4JOVM/action/replication_record"}},"created_at":"2026-05-18T00:14:00.041453+00:00","updated_at":"2026-05-18T00:14:00.041453+00:00"}