{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:M4Q6RYNGC53GSZGMSMFUYB3EA5","short_pith_number":"pith:M4Q6RYNG","schema_version":"1.0","canonical_sha256":"6721e8e1a617766964cc930b4c0764076eab63c1225e06968cc3fa3a3c8b3003","source":{"kind":"arxiv","id":"2110.14513","version":2},"attestation_state":"computed","paper":{"title":"Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hoon Heo, Hyeong-Seok Choi, Jie Hwan Lee, Juheon Lee, Kyogu Lee, Wansoo Kim","submitted_at":"2021-10-27T15:25:26Z","abstract_excerpt":"We present a neural analysis and synthesis (NANSY) framework that can manipulate voice, pitch, and speed of an arbitrary speech signal. Most of the previous works have focused on using information bottleneck to disentangle analysis features for controllable synthesis, which usually results in poor reconstruction quality. We address this issue by proposing a novel training strategy based on information perturbation. The idea is to perturb information in the original input signal (e.g., formant, pitch, and frequency response), thereby letting synthesis networks selectively take essential attribu"},"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":"2110.14513","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-27T15:25:26Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"1f587047d27951d4e8c4ceb08a3f9a1e6c24d6d5832d54cb662b654a9175dab3","abstract_canon_sha256":"f84fe2dbf650373ebe9347e4d99e9352c71fc047ece0556b830fc602525b3ffd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:45.697208Z","signature_b64":"QB1rTRwxV/2ExAlf+dz5ke5SS6aNC8GLie7ZL3G1MUFw3wgOQYmhIFeF5vg1VVVRZd+e34ui2llVpkr9DaruCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6721e8e1a617766964cc930b4c0764076eab63c1225e06968cc3fa3a3c8b3003","last_reissued_at":"2026-07-05T03:26:45.696730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:45.696730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hoon Heo, Hyeong-Seok Choi, Jie Hwan Lee, Juheon Lee, Kyogu Lee, Wansoo Kim","submitted_at":"2021-10-27T15:25:26Z","abstract_excerpt":"We present a neural analysis and synthesis (NANSY) framework that can manipulate voice, pitch, and speed of an arbitrary speech signal. Most of the previous works have focused on using information bottleneck to disentangle analysis features for controllable synthesis, which usually results in poor reconstruction quality. We address this issue by proposing a novel training strategy based on information perturbation. The idea is to perturb information in the original input signal (e.g., formant, pitch, and frequency response), thereby letting synthesis networks selectively take essential attribu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14513","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/2110.14513/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":"2110.14513","created_at":"2026-07-05T03:26:45.696782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.14513v2","created_at":"2026-07-05T03:26:45.696782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14513","created_at":"2026-07-05T03:26:45.696782+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4Q6RYNGC53G","created_at":"2026-07-05T03:26:45.696782+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4Q6RYNGC53GSZGM","created_at":"2026-07-05T03:26:45.696782+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4Q6RYNG","created_at":"2026-07-05T03:26:45.696782+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/M4Q6RYNGC53GSZGMSMFUYB3EA5","json":"https://pith.science/pith/M4Q6RYNGC53GSZGMSMFUYB3EA5.json","graph_json":"https://pith.science/api/pith-number/M4Q6RYNGC53GSZGMSMFUYB3EA5/graph.json","events_json":"https://pith.science/api/pith-number/M4Q6RYNGC53GSZGMSMFUYB3EA5/events.json","paper":"https://pith.science/paper/M4Q6RYNG"},"agent_actions":{"view_html":"https://pith.science/pith/M4Q6RYNGC53GSZGMSMFUYB3EA5","download_json":"https://pith.science/pith/M4Q6RYNGC53GSZGMSMFUYB3EA5.json","view_paper":"https://pith.science/paper/M4Q6RYNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.14513&json=true","fetch_graph":"https://pith.science/api/pith-number/M4Q6RYNGC53GSZGMSMFUYB3EA5/graph.json","fetch_events":"https://pith.science/api/pith-number/M4Q6RYNGC53GSZGMSMFUYB3EA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4Q6RYNGC53GSZGMSMFUYB3EA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4Q6RYNGC53GSZGMSMFUYB3EA5/action/storage_attestation","attest_author":"https://pith.science/pith/M4Q6RYNGC53GSZGMSMFUYB3EA5/action/author_attestation","sign_citation":"https://pith.science/pith/M4Q6RYNGC53GSZGMSMFUYB3EA5/action/citation_signature","submit_replication":"https://pith.science/pith/M4Q6RYNGC53GSZGMSMFUYB3EA5/action/replication_record"}},"created_at":"2026-07-05T03:26:45.696782+00:00","updated_at":"2026-07-05T03:26:45.696782+00:00"}