{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QLKNSZ5VR44ZUSRFKGMA5UKYJN","short_pith_number":"pith:QLKNSZ5V","schema_version":"1.0","canonical_sha256":"82d4d967b58f399a4a2551980ed1584b5c799d5bac0d245a3e182533342baedd","source":{"kind":"arxiv","id":"2311.00489","version":2},"attestation_state":"computed","paper":{"title":"Deep Neural Networks for Automatic Speaker Recognition Do Not Learn Supra-Segmental Temporal Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Daniel Neururer, Thilo Stadelmann, Volker Dellwo","submitted_at":"2023-11-01T12:45:31Z","abstract_excerpt":"While deep neural networks have shown impressive results in automatic speaker recognition and related tasks, it is dissatisfactory how little is understood about what exactly is responsible for these results. Part of the success has been attributed in prior work to their capability to model supra-segmental temporal information (SST), i.e., learn rhythmic-prosodic characteristics of speech in addition to spectral features. In this paper, we (i) present and apply a novel test to quantify to what extent the performance of state-of-the-art neural networks for speaker recognition can be explained b"},"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":"2311.00489","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-11-01T12:45:31Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"62917402815da46865da6902870e59d97d0b741dd60ddd3f17ca848fe2dce6c7","abstract_canon_sha256":"ced6897b586c5e7399e23202f4b9acd662acc277f0e6c7685dfefe5879241f78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:40.520675Z","signature_b64":"lqcBht5eAao4YF0FaoA/WMRrIHRcYm4Av7nKD0cEuxa0Bz/mKZr5ObEtgIE2KMpEVY89P8GdxTG9DzEItvUcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82d4d967b58f399a4a2551980ed1584b5c799d5bac0d245a3e182533342baedd","last_reissued_at":"2026-07-05T08:41:40.520133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:40.520133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Neural Networks for Automatic Speaker Recognition Do Not Learn Supra-Segmental Temporal Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Daniel Neururer, Thilo Stadelmann, Volker Dellwo","submitted_at":"2023-11-01T12:45:31Z","abstract_excerpt":"While deep neural networks have shown impressive results in automatic speaker recognition and related tasks, it is dissatisfactory how little is understood about what exactly is responsible for these results. Part of the success has been attributed in prior work to their capability to model supra-segmental temporal information (SST), i.e., learn rhythmic-prosodic characteristics of speech in addition to spectral features. In this paper, we (i) present and apply a novel test to quantify to what extent the performance of state-of-the-art neural networks for speaker recognition can be explained b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00489","kind":"arxiv","version":2},"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/2311.00489/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":"2311.00489","created_at":"2026-07-05T08:41:40.520191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00489v2","created_at":"2026-07-05T08:41:40.520191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00489","created_at":"2026-07-05T08:41:40.520191+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLKNSZ5VR44Z","created_at":"2026-07-05T08:41:40.520191+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLKNSZ5VR44ZUSRF","created_at":"2026-07-05T08:41:40.520191+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLKNSZ5V","created_at":"2026-07-05T08:41:40.520191+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/QLKNSZ5VR44ZUSRFKGMA5UKYJN","json":"https://pith.science/pith/QLKNSZ5VR44ZUSRFKGMA5UKYJN.json","graph_json":"https://pith.science/api/pith-number/QLKNSZ5VR44ZUSRFKGMA5UKYJN/graph.json","events_json":"https://pith.science/api/pith-number/QLKNSZ5VR44ZUSRFKGMA5UKYJN/events.json","paper":"https://pith.science/paper/QLKNSZ5V"},"agent_actions":{"view_html":"https://pith.science/pith/QLKNSZ5VR44ZUSRFKGMA5UKYJN","download_json":"https://pith.science/pith/QLKNSZ5VR44ZUSRFKGMA5UKYJN.json","view_paper":"https://pith.science/paper/QLKNSZ5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00489&json=true","fetch_graph":"https://pith.science/api/pith-number/QLKNSZ5VR44ZUSRFKGMA5UKYJN/graph.json","fetch_events":"https://pith.science/api/pith-number/QLKNSZ5VR44ZUSRFKGMA5UKYJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLKNSZ5VR44ZUSRFKGMA5UKYJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLKNSZ5VR44ZUSRFKGMA5UKYJN/action/storage_attestation","attest_author":"https://pith.science/pith/QLKNSZ5VR44ZUSRFKGMA5UKYJN/action/author_attestation","sign_citation":"https://pith.science/pith/QLKNSZ5VR44ZUSRFKGMA5UKYJN/action/citation_signature","submit_replication":"https://pith.science/pith/QLKNSZ5VR44ZUSRFKGMA5UKYJN/action/replication_record"}},"created_at":"2026-07-05T08:41:40.520191+00:00","updated_at":"2026-07-05T08:41:40.520191+00:00"}