{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VOR3S37BGUMEBAZIFXF6CUAN6T","short_pith_number":"pith:VOR3S37B","schema_version":"1.0","canonical_sha256":"aba3b96fe135184083282dcbe1500df4fda4af10621d4745808766b5ef182136","source":{"kind":"arxiv","id":"2606.05739","version":1},"attestation_state":"computed","paper":{"title":"Do speech foundation models perceive speaker similarity as humans do?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hayato Yagi, Minoru Kishi, Shinnosuke Takamichi, Yuki Saito","submitted_at":"2026-06-04T06:04:18Z","abstract_excerpt":"This study presents a comparative analysis between the speaker embeddings of speech foundation models and human subjective perception of speaker similarity. Human listeners have the ability to judge speaker similarity on a continuous scale discerning how similar two voices are. In contrast, speech foundation models embed speaker characteristics into numerical representation. However, a question remains: does the numerical distance between speaker embeddings in these models truly align with the similarity perceived by humans? To address this, we conduct a comprehensive investigation using more "},"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":"2606.05739","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T06:04:18Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"228c2b04bc50208fec33ab35076fa51b010ea590ca7812b77b6648d318d358bf","abstract_canon_sha256":"bf5183829dde14d9353846332737c7d322b03e5b0e56e0facf52b81180f92468"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:01.276891Z","signature_b64":"BHfhXzU0O+5yCc80anOmdfD4UQTllDUalE6BpdrG61IEcrerYQs6lqj9bALo/ttmVV17FyVwxHU+HPLvXoEtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aba3b96fe135184083282dcbe1500df4fda4af10621d4745808766b5ef182136","last_reissued_at":"2026-06-05T01:15:01.276370Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:01.276370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do speech foundation models perceive speaker similarity as humans do?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hayato Yagi, Minoru Kishi, Shinnosuke Takamichi, Yuki Saito","submitted_at":"2026-06-04T06:04:18Z","abstract_excerpt":"This study presents a comparative analysis between the speaker embeddings of speech foundation models and human subjective perception of speaker similarity. Human listeners have the ability to judge speaker similarity on a continuous scale discerning how similar two voices are. In contrast, speech foundation models embed speaker characteristics into numerical representation. However, a question remains: does the numerical distance between speaker embeddings in these models truly align with the similarity perceived by humans? To address this, we conduct a comprehensive investigation using more "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05739","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/2606.05739/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":"2606.05739","created_at":"2026-06-05T01:15:01.276447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05739v1","created_at":"2026-06-05T01:15:01.276447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05739","created_at":"2026-06-05T01:15:01.276447+00:00"},{"alias_kind":"pith_short_12","alias_value":"VOR3S37BGUME","created_at":"2026-06-05T01:15:01.276447+00:00"},{"alias_kind":"pith_short_16","alias_value":"VOR3S37BGUMEBAZI","created_at":"2026-06-05T01:15:01.276447+00:00"},{"alias_kind":"pith_short_8","alias_value":"VOR3S37B","created_at":"2026-06-05T01:15:01.276447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.05739","citing_title":"Do speech foundation models perceive speaker similarity as humans do?","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VOR3S37BGUMEBAZIFXF6CUAN6T","json":"https://pith.science/pith/VOR3S37BGUMEBAZIFXF6CUAN6T.json","graph_json":"https://pith.science/api/pith-number/VOR3S37BGUMEBAZIFXF6CUAN6T/graph.json","events_json":"https://pith.science/api/pith-number/VOR3S37BGUMEBAZIFXF6CUAN6T/events.json","paper":"https://pith.science/paper/VOR3S37B"},"agent_actions":{"view_html":"https://pith.science/pith/VOR3S37BGUMEBAZIFXF6CUAN6T","download_json":"https://pith.science/pith/VOR3S37BGUMEBAZIFXF6CUAN6T.json","view_paper":"https://pith.science/paper/VOR3S37B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05739&json=true","fetch_graph":"https://pith.science/api/pith-number/VOR3S37BGUMEBAZIFXF6CUAN6T/graph.json","fetch_events":"https://pith.science/api/pith-number/VOR3S37BGUMEBAZIFXF6CUAN6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VOR3S37BGUMEBAZIFXF6CUAN6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VOR3S37BGUMEBAZIFXF6CUAN6T/action/storage_attestation","attest_author":"https://pith.science/pith/VOR3S37BGUMEBAZIFXF6CUAN6T/action/author_attestation","sign_citation":"https://pith.science/pith/VOR3S37BGUMEBAZIFXF6CUAN6T/action/citation_signature","submit_replication":"https://pith.science/pith/VOR3S37BGUMEBAZIFXF6CUAN6T/action/replication_record"}},"created_at":"2026-06-05T01:15:01.276447+00:00","updated_at":"2026-06-05T01:15:01.276447+00:00"}