{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VX2DJC33BBBFELH6W37N5BAXME","short_pith_number":"pith:VX2DJC33","schema_version":"1.0","canonical_sha256":"adf4348b7b0842522cfeb6fede84176119511b3393d50ae57d03d9dd2cefe42e","source":{"kind":"arxiv","id":"2306.01100","version":1},"attestation_state":"computed","paper":{"title":"ALO-VC: Any-to-any Low-latency One-shot Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bohan Wang, Damien Ronssin, Milos Cernak","submitted_at":"2023-06-01T19:23:38Z","abstract_excerpt":"This paper presents ALO-VC, a non-parallel low-latency one-shot phonetic posteriorgrams (PPGs) based voice conversion method. ALO-VC enables any-to-any voice conversion using only one utterance from the target speaker, with only 47.5 ms future look-ahead. The proposed hybrid signal processing and machine learning pipeline combines a pre-trained speaker encoder, a pitch predictor to predict the converted speech's prosody, and positional encoding to convey the phoneme's location information. We introduce two system versions: ALO-VC-R, which uses a pre-trained d-vector speaker encoder, and ALO-VC"},"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":"2306.01100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-01T19:23:38Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"8a931b3842eceb2c38a6d0d02f35b4c9957647f559c85d38751ad75a8533e970","abstract_canon_sha256":"91aceb971584cbc06b496e5ce87106a55f3ce5716a964913c374a5d6d36ebf10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:37.959932Z","signature_b64":"DQ/79dMD4WcgeefJ5bK5FZASUr9CxyCCd9XkgejPz3RDpmnqzp2mZAAI8y/10vwMlH+vPgurr2c3ebD6ZaX0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adf4348b7b0842522cfeb6fede84176119511b3393d50ae57d03d9dd2cefe42e","last_reissued_at":"2026-07-05T06:16:37.959490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:37.959490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALO-VC: Any-to-any Low-latency One-shot Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bohan Wang, Damien Ronssin, Milos Cernak","submitted_at":"2023-06-01T19:23:38Z","abstract_excerpt":"This paper presents ALO-VC, a non-parallel low-latency one-shot phonetic posteriorgrams (PPGs) based voice conversion method. ALO-VC enables any-to-any voice conversion using only one utterance from the target speaker, with only 47.5 ms future look-ahead. The proposed hybrid signal processing and machine learning pipeline combines a pre-trained speaker encoder, a pitch predictor to predict the converted speech's prosody, and positional encoding to convey the phoneme's location information. We introduce two system versions: ALO-VC-R, which uses a pre-trained d-vector speaker encoder, and ALO-VC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01100","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/2306.01100/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":"2306.01100","created_at":"2026-07-05T06:16:37.959551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01100v1","created_at":"2026-07-05T06:16:37.959551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01100","created_at":"2026-07-05T06:16:37.959551+00:00"},{"alias_kind":"pith_short_12","alias_value":"VX2DJC33BBBF","created_at":"2026-07-05T06:16:37.959551+00:00"},{"alias_kind":"pith_short_16","alias_value":"VX2DJC33BBBFELH6","created_at":"2026-07-05T06:16:37.959551+00:00"},{"alias_kind":"pith_short_8","alias_value":"VX2DJC33","created_at":"2026-07-05T06:16:37.959551+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/VX2DJC33BBBFELH6W37N5BAXME","json":"https://pith.science/pith/VX2DJC33BBBFELH6W37N5BAXME.json","graph_json":"https://pith.science/api/pith-number/VX2DJC33BBBFELH6W37N5BAXME/graph.json","events_json":"https://pith.science/api/pith-number/VX2DJC33BBBFELH6W37N5BAXME/events.json","paper":"https://pith.science/paper/VX2DJC33"},"agent_actions":{"view_html":"https://pith.science/pith/VX2DJC33BBBFELH6W37N5BAXME","download_json":"https://pith.science/pith/VX2DJC33BBBFELH6W37N5BAXME.json","view_paper":"https://pith.science/paper/VX2DJC33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01100&json=true","fetch_graph":"https://pith.science/api/pith-number/VX2DJC33BBBFELH6W37N5BAXME/graph.json","fetch_events":"https://pith.science/api/pith-number/VX2DJC33BBBFELH6W37N5BAXME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VX2DJC33BBBFELH6W37N5BAXME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VX2DJC33BBBFELH6W37N5BAXME/action/storage_attestation","attest_author":"https://pith.science/pith/VX2DJC33BBBFELH6W37N5BAXME/action/author_attestation","sign_citation":"https://pith.science/pith/VX2DJC33BBBFELH6W37N5BAXME/action/citation_signature","submit_replication":"https://pith.science/pith/VX2DJC33BBBFELH6W37N5BAXME/action/replication_record"}},"created_at":"2026-07-05T06:16:37.959551+00:00","updated_at":"2026-07-05T06:16:37.959551+00:00"}