{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZCUHWWAF7VU6RWCLSLPDC7YZVJ","short_pith_number":"pith:ZCUHWWAF","schema_version":"1.0","canonical_sha256":"c8a87b5805fd69e8d84b92de317f19aa4ef0429c7d9403895358653c07d83104","source":{"kind":"arxiv","id":"2606.10317","version":1},"attestation_state":"computed","paper":{"title":"SSL-GMMVC: Interpretable Voice Conversion via Locally Linear GMM Transforms in Self-Supervised Representation Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daisuke Saito, Hiroshi Nishijima, Nobuaki Minematsu, Tomoya Tanabu","submitted_at":"2026-06-09T02:14:11Z","abstract_excerpt":"We introduce SSL-GMMVC, an interpretable voice conversion method in self-supervised speech space. The method models paired source-target features with a Gaussian mixture model and performs conversion as a posterior-weighted sum of affine transforms. This yields locally linear transformations that adapt to heterogeneous feature-space structure while remaining analytically tractable. Through objective and subjective evaluations, we show that SSL-GMMVC improves speaker similarity with comparable intelligibility and naturalness, and that even a constrained covariance variant surpasses a deep learn"},"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":"2606.10317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-09T02:14:11Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"8318f4a8011a5bab52f58af97e535a2073c26eda0c1bc17659d8290ce44e255a","abstract_canon_sha256":"dc151c9ae469af2fddd3c225fe4e9849a98d3b285f483ffb5de43a17b66b72b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:11.520694Z","signature_b64":"SVKv8f4Wm3XjXDpzu+GvzrrwzwGsHHEvn3Id3f+7ATJge/B3Ajukv/HrPg1834NpFhDhCHMN1NU4aGjAwyrVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8a87b5805fd69e8d84b92de317f19aa4ef0429c7d9403895358653c07d83104","last_reissued_at":"2026-06-10T01:10:11.519856Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:11.519856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SSL-GMMVC: Interpretable Voice Conversion via Locally Linear GMM Transforms in Self-Supervised Representation Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daisuke Saito, Hiroshi Nishijima, Nobuaki Minematsu, Tomoya Tanabu","submitted_at":"2026-06-09T02:14:11Z","abstract_excerpt":"We introduce SSL-GMMVC, an interpretable voice conversion method in self-supervised speech space. The method models paired source-target features with a Gaussian mixture model and performs conversion as a posterior-weighted sum of affine transforms. This yields locally linear transformations that adapt to heterogeneous feature-space structure while remaining analytically tractable. Through objective and subjective evaluations, we show that SSL-GMMVC improves speaker similarity with comparable intelligibility and naturalness, and that even a constrained covariance variant surpasses a deep learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10317","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/2606.10317/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":"2606.10317","created_at":"2026-06-10T01:10:11.519987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10317v1","created_at":"2026-06-10T01:10:11.519987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10317","created_at":"2026-06-10T01:10:11.519987+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZCUHWWAF7VU6","created_at":"2026-06-10T01:10:11.519987+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZCUHWWAF7VU6RWCL","created_at":"2026-06-10T01:10:11.519987+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZCUHWWAF","created_at":"2026-06-10T01:10:11.519987+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/ZCUHWWAF7VU6RWCLSLPDC7YZVJ","json":"https://pith.science/pith/ZCUHWWAF7VU6RWCLSLPDC7YZVJ.json","graph_json":"https://pith.science/api/pith-number/ZCUHWWAF7VU6RWCLSLPDC7YZVJ/graph.json","events_json":"https://pith.science/api/pith-number/ZCUHWWAF7VU6RWCLSLPDC7YZVJ/events.json","paper":"https://pith.science/paper/ZCUHWWAF"},"agent_actions":{"view_html":"https://pith.science/pith/ZCUHWWAF7VU6RWCLSLPDC7YZVJ","download_json":"https://pith.science/pith/ZCUHWWAF7VU6RWCLSLPDC7YZVJ.json","view_paper":"https://pith.science/paper/ZCUHWWAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10317&json=true","fetch_graph":"https://pith.science/api/pith-number/ZCUHWWAF7VU6RWCLSLPDC7YZVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZCUHWWAF7VU6RWCLSLPDC7YZVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZCUHWWAF7VU6RWCLSLPDC7YZVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZCUHWWAF7VU6RWCLSLPDC7YZVJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZCUHWWAF7VU6RWCLSLPDC7YZVJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZCUHWWAF7VU6RWCLSLPDC7YZVJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZCUHWWAF7VU6RWCLSLPDC7YZVJ/action/replication_record"}},"created_at":"2026-06-10T01:10:11.519987+00:00","updated_at":"2026-06-10T01:10:11.519987+00:00"}