{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7OSWBU3ANFVBC3E2ZFYG26VVQL","short_pith_number":"pith:7OSWBU3A","schema_version":"1.0","canonical_sha256":"fba560d360696a116c9ac9706d7ab582ef8dbbb93a24629ba09a829edc0b5947","source":{"kind":"arxiv","id":"2204.01677","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Speech Representations Preserve Speech Characteristics while Anonymizing Voices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abner Hernandez, Andreas Maier, Juan Camilo V\\'asquez-Correa, Juan Rafael Orozco-Arroyave, Paula Andrea P\\'erez-Toro, Seung Hee Yang","submitted_at":"2022-04-04T17:48:01Z","abstract_excerpt":"Collecting speech data is an important step in training speech recognition systems and other speech-based machine learning models. However, the issue of privacy protection is an increasing concern that must be addressed. The current study investigates the use of voice conversion as a method for anonymizing voices. In particular, we train several voice conversion models using self-supervised speech representations including Wav2Vec2.0, Hubert and UniSpeech. Converted voices retain a low word error rate within 1% of the original voice. Equal error rate increases from 1.52% to 46.24% on the Libri"},"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":"2204.01677","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-04T17:48:01Z","cross_cats_sorted":[],"title_canon_sha256":"e856b6ba89f3de4b1e9503046744ac0b128115daafa8affcf55a1c1163497494","abstract_canon_sha256":"d66dc5e85c42dea277e65060188b8e2c9ba2b84e12cb4f97a683e25ef5000c20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:21.548402Z","signature_b64":"JzG4fNvEiVVM9N5xSTTw2ME4MjEgprc8+ECoX86bJvcnWR0VBKk4mwbKjprUQ5sclee3VMDDAXZwQCr7+n82Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fba560d360696a116c9ac9706d7ab582ef8dbbb93a24629ba09a829edc0b5947","last_reissued_at":"2026-07-05T04:11:21.547996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:21.547996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Speech Representations Preserve Speech Characteristics while Anonymizing Voices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abner Hernandez, Andreas Maier, Juan Camilo V\\'asquez-Correa, Juan Rafael Orozco-Arroyave, Paula Andrea P\\'erez-Toro, Seung Hee Yang","submitted_at":"2022-04-04T17:48:01Z","abstract_excerpt":"Collecting speech data is an important step in training speech recognition systems and other speech-based machine learning models. However, the issue of privacy protection is an increasing concern that must be addressed. The current study investigates the use of voice conversion as a method for anonymizing voices. In particular, we train several voice conversion models using self-supervised speech representations including Wav2Vec2.0, Hubert and UniSpeech. Converted voices retain a low word error rate within 1% of the original voice. Equal error rate increases from 1.52% to 46.24% on the Libri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.01677","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/2204.01677/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":"2204.01677","created_at":"2026-07-05T04:11:21.548054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.01677v1","created_at":"2026-07-05T04:11:21.548054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.01677","created_at":"2026-07-05T04:11:21.548054+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OSWBU3ANFVB","created_at":"2026-07-05T04:11:21.548054+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OSWBU3ANFVBC3E2","created_at":"2026-07-05T04:11:21.548054+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OSWBU3A","created_at":"2026-07-05T04:11:21.548054+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06356","citing_title":"Use Cases for Voice Anonymization","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7OSWBU3ANFVBC3E2ZFYG26VVQL","json":"https://pith.science/pith/7OSWBU3ANFVBC3E2ZFYG26VVQL.json","graph_json":"https://pith.science/api/pith-number/7OSWBU3ANFVBC3E2ZFYG26VVQL/graph.json","events_json":"https://pith.science/api/pith-number/7OSWBU3ANFVBC3E2ZFYG26VVQL/events.json","paper":"https://pith.science/paper/7OSWBU3A"},"agent_actions":{"view_html":"https://pith.science/pith/7OSWBU3ANFVBC3E2ZFYG26VVQL","download_json":"https://pith.science/pith/7OSWBU3ANFVBC3E2ZFYG26VVQL.json","view_paper":"https://pith.science/paper/7OSWBU3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.01677&json=true","fetch_graph":"https://pith.science/api/pith-number/7OSWBU3ANFVBC3E2ZFYG26VVQL/graph.json","fetch_events":"https://pith.science/api/pith-number/7OSWBU3ANFVBC3E2ZFYG26VVQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OSWBU3ANFVBC3E2ZFYG26VVQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OSWBU3ANFVBC3E2ZFYG26VVQL/action/storage_attestation","attest_author":"https://pith.science/pith/7OSWBU3ANFVBC3E2ZFYG26VVQL/action/author_attestation","sign_citation":"https://pith.science/pith/7OSWBU3ANFVBC3E2ZFYG26VVQL/action/citation_signature","submit_replication":"https://pith.science/pith/7OSWBU3ANFVBC3E2ZFYG26VVQL/action/replication_record"}},"created_at":"2026-07-05T04:11:21.548054+00:00","updated_at":"2026-07-05T04:11:21.548054+00:00"}