{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q342ITGAI75G55OGJNY7UUOWYF","short_pith_number":"pith:Q342ITGA","schema_version":"1.0","canonical_sha256":"86f9a44cc047fa6ef5c64b71fa51d6c173d7b63c43f9c1bb57191a1d8a74bb5a","source":{"kind":"arxiv","id":"2312.08494","version":1},"attestation_state":"computed","paper":{"title":"PerMod: Perceptually Grounded Voice Modification with Latent Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ajil Jalal, Gopala Krishna Anumanchipalli, Luna McNulty, Robin Netzorg","submitted_at":"2023-12-13T20:14:27Z","abstract_excerpt":"Perceptual modification of voice is an elusive goal. While non-experts can modify an image or sentence perceptually with available tools, it is not clear how to similarly modify speech along perceptual axes. Voice conversion does make it possible to convert one voice to another, but these modifications are handled by black box models, and the specifics of what perceptual qualities to modify and how to modify them are unclear. Towards allowing greater perceptual control over voice, we introduce PerMod, a conditional latent diffusion model that takes in an input voice and a perceptual qualities "},"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":"2312.08494","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-13T20:14:27Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"6fbe017c2d524fab3e60df3a0e782210594cb6f231c457d3691e1829195d85fb","abstract_canon_sha256":"a938e5b287c07692e1548c688b2ceac808782421924c999a6f4b5a858005c148"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:05.255897Z","signature_b64":"YyPO+ynFA7KeQn9xUSvo97niufJ2FS1ZvvzhhNRLgd4wxbtJfA1KRx0fK5PWncu9vwj73fLNMEDCMUPhqNvXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86f9a44cc047fa6ef5c64b71fa51d6c173d7b63c43f9c1bb57191a1d8a74bb5a","last_reissued_at":"2026-07-05T07:24:05.255481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:05.255481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PerMod: Perceptually Grounded Voice Modification with Latent Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ajil Jalal, Gopala Krishna Anumanchipalli, Luna McNulty, Robin Netzorg","submitted_at":"2023-12-13T20:14:27Z","abstract_excerpt":"Perceptual modification of voice is an elusive goal. While non-experts can modify an image or sentence perceptually with available tools, it is not clear how to similarly modify speech along perceptual axes. Voice conversion does make it possible to convert one voice to another, but these modifications are handled by black box models, and the specifics of what perceptual qualities to modify and how to modify them are unclear. Towards allowing greater perceptual control over voice, we introduce PerMod, a conditional latent diffusion model that takes in an input voice and a perceptual qualities "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08494","kind":"arxiv","version":1},"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/2312.08494/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":"2312.08494","created_at":"2026-07-05T07:24:05.255539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08494v1","created_at":"2026-07-05T07:24:05.255539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08494","created_at":"2026-07-05T07:24:05.255539+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q342ITGAI75G","created_at":"2026-07-05T07:24:05.255539+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q342ITGAI75G55OG","created_at":"2026-07-05T07:24:05.255539+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q342ITGA","created_at":"2026-07-05T07:24:05.255539+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/Q342ITGAI75G55OGJNY7UUOWYF","json":"https://pith.science/pith/Q342ITGAI75G55OGJNY7UUOWYF.json","graph_json":"https://pith.science/api/pith-number/Q342ITGAI75G55OGJNY7UUOWYF/graph.json","events_json":"https://pith.science/api/pith-number/Q342ITGAI75G55OGJNY7UUOWYF/events.json","paper":"https://pith.science/paper/Q342ITGA"},"agent_actions":{"view_html":"https://pith.science/pith/Q342ITGAI75G55OGJNY7UUOWYF","download_json":"https://pith.science/pith/Q342ITGAI75G55OGJNY7UUOWYF.json","view_paper":"https://pith.science/paper/Q342ITGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08494&json=true","fetch_graph":"https://pith.science/api/pith-number/Q342ITGAI75G55OGJNY7UUOWYF/graph.json","fetch_events":"https://pith.science/api/pith-number/Q342ITGAI75G55OGJNY7UUOWYF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q342ITGAI75G55OGJNY7UUOWYF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q342ITGAI75G55OGJNY7UUOWYF/action/storage_attestation","attest_author":"https://pith.science/pith/Q342ITGAI75G55OGJNY7UUOWYF/action/author_attestation","sign_citation":"https://pith.science/pith/Q342ITGAI75G55OGJNY7UUOWYF/action/citation_signature","submit_replication":"https://pith.science/pith/Q342ITGAI75G55OGJNY7UUOWYF/action/replication_record"}},"created_at":"2026-07-05T07:24:05.255539+00:00","updated_at":"2026-07-05T07:24:05.255539+00:00"}