{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HTQRKYGKMXBGJFKLQTPVFAPCLT","short_pith_number":"pith:HTQRKYGK","schema_version":"1.0","canonical_sha256":"3ce11560ca65c264954b84df5281e25cf53d2a50d90e2bdc25dd3356b17e2eac","source":{"kind":"arxiv","id":"2107.13969","version":1},"attestation_state":"computed","paper":{"title":"Significance of Speaker Embeddings and Temporal Context for Depression Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CY","authors_text":"Rudolf Uher, Sageev Oore, Sebastian Rodriguez, Sheri Rempel, Sri Harsha Dumpala","submitted_at":"2021-07-24T05:14:48Z","abstract_excerpt":"Depression detection from speech has attracted a lot of attention in recent years. However, the significance of speaker-specific information in depression detection has not yet been explored. In this work, we analyze the significance of speaker embeddings for the task of depression detection from speech. Experimental results show that the speaker embeddings provide important cues to achieve state-of-the-art performance in depression detection. We also show that combining conventional OpenSMILE and COVAREP features, which carry complementary information, with speaker embeddings further improves"},"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":"2107.13969","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2021-07-24T05:14:48Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"c7e6199d6e107c8ac003a0373569ac511f13291b08df6830def41d68485c73d6","abstract_canon_sha256":"1c3b8a2827252e5a2879b73cb740864e8f37a020b755d73a8c3bba5e8b21000d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:01:42.495789Z","signature_b64":"Ycs8+KJB2GgvGCowxhTFky0yRujL4Xe9mNHeKP5dYgiGEiGRENUIUNfE2vgvMTInYQd3HhuZZNLiFInB0kG8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ce11560ca65c264954b84df5281e25cf53d2a50d90e2bdc25dd3356b17e2eac","last_reissued_at":"2026-07-05T03:01:42.495386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:01:42.495386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Significance of Speaker Embeddings and Temporal Context for Depression Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CY","authors_text":"Rudolf Uher, Sageev Oore, Sebastian Rodriguez, Sheri Rempel, Sri Harsha Dumpala","submitted_at":"2021-07-24T05:14:48Z","abstract_excerpt":"Depression detection from speech has attracted a lot of attention in recent years. However, the significance of speaker-specific information in depression detection has not yet been explored. In this work, we analyze the significance of speaker embeddings for the task of depression detection from speech. Experimental results show that the speaker embeddings provide important cues to achieve state-of-the-art performance in depression detection. We also show that combining conventional OpenSMILE and COVAREP features, which carry complementary information, with speaker embeddings further improves"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.13969","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/2107.13969/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":"2107.13969","created_at":"2026-07-05T03:01:42.495446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.13969v1","created_at":"2026-07-05T03:01:42.495446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.13969","created_at":"2026-07-05T03:01:42.495446+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTQRKYGKMXBG","created_at":"2026-07-05T03:01:42.495446+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTQRKYGKMXBGJFKL","created_at":"2026-07-05T03:01:42.495446+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTQRKYGK","created_at":"2026-07-05T03:01:42.495446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31730","citing_title":"A Fair and Transparent Framework for Speech-Based Depression Detection: Balancing Interpretability and Performance","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HTQRKYGKMXBGJFKLQTPVFAPCLT","json":"https://pith.science/pith/HTQRKYGKMXBGJFKLQTPVFAPCLT.json","graph_json":"https://pith.science/api/pith-number/HTQRKYGKMXBGJFKLQTPVFAPCLT/graph.json","events_json":"https://pith.science/api/pith-number/HTQRKYGKMXBGJFKLQTPVFAPCLT/events.json","paper":"https://pith.science/paper/HTQRKYGK"},"agent_actions":{"view_html":"https://pith.science/pith/HTQRKYGKMXBGJFKLQTPVFAPCLT","download_json":"https://pith.science/pith/HTQRKYGKMXBGJFKLQTPVFAPCLT.json","view_paper":"https://pith.science/paper/HTQRKYGK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.13969&json=true","fetch_graph":"https://pith.science/api/pith-number/HTQRKYGKMXBGJFKLQTPVFAPCLT/graph.json","fetch_events":"https://pith.science/api/pith-number/HTQRKYGKMXBGJFKLQTPVFAPCLT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTQRKYGKMXBGJFKLQTPVFAPCLT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTQRKYGKMXBGJFKLQTPVFAPCLT/action/storage_attestation","attest_author":"https://pith.science/pith/HTQRKYGKMXBGJFKLQTPVFAPCLT/action/author_attestation","sign_citation":"https://pith.science/pith/HTQRKYGKMXBGJFKLQTPVFAPCLT/action/citation_signature","submit_replication":"https://pith.science/pith/HTQRKYGKMXBGJFKLQTPVFAPCLT/action/replication_record"}},"created_at":"2026-07-05T03:01:42.495446+00:00","updated_at":"2026-07-05T03:01:42.495446+00:00"}