{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EDPWGU4XMHIWFSEII3GECBL4ED","short_pith_number":"pith:EDPWGU4X","schema_version":"1.0","canonical_sha256":"20df63539761d162c88846cc41057c20ef39b7862e47666bdf66c1742928bfa9","source":{"kind":"arxiv","id":"2202.01252","version":2},"attestation_state":"computed","paper":{"title":"Speaker Normalization for Self-supervised Speech Emotion Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Edmilson Morais, Hagai Aronowitz, Itai Gat, Ron Hoory, Weizhong Zhu","submitted_at":"2022-02-02T19:30:47Z","abstract_excerpt":"Large speech emotion recognition datasets are hard to obtain, and small datasets may contain biases. Deep-net-based classifiers, in turn, are prone to exploit those biases and find shortcuts such as speaker characteristics. These shortcuts usually harm a model's ability to generalize. To address this challenge, we propose a gradient-based adversary learning framework that learns a speech emotion recognition task while normalizing speaker characteristics from the feature representation. We demonstrate the efficacy of our method on both speaker-independent and speaker-dependent settings and obta"},"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":"2202.01252","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-02T19:30:47Z","cross_cats_sorted":[],"title_canon_sha256":"2f870a7f2bcea251c34d3ca71f79e05ab2d9a3ac5565406d97113a2c463433da","abstract_canon_sha256":"4d15b4778d06c64bd0bbb0ba3fbdf6d9a010e45c43f14df16771549a293c2471"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:31.548949Z","signature_b64":"LUdVUWS5Hrd6RbzrXRXtsvxETY51WatpmVoeXzNEmBDNK6h5MM9CK1PbDyKTnZxOP0k4p4HwCeyUf/y1w++EBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20df63539761d162c88846cc41057c20ef39b7862e47666bdf66c1742928bfa9","last_reissued_at":"2026-07-05T05:13:31.548410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:31.548410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaker Normalization for Self-supervised Speech Emotion Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Edmilson Morais, Hagai Aronowitz, Itai Gat, Ron Hoory, Weizhong Zhu","submitted_at":"2022-02-02T19:30:47Z","abstract_excerpt":"Large speech emotion recognition datasets are hard to obtain, and small datasets may contain biases. Deep-net-based classifiers, in turn, are prone to exploit those biases and find shortcuts such as speaker characteristics. These shortcuts usually harm a model's ability to generalize. To address this challenge, we propose a gradient-based adversary learning framework that learns a speech emotion recognition task while normalizing speaker characteristics from the feature representation. We demonstrate the efficacy of our method on both speaker-independent and speaker-dependent settings and obta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.01252","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/2202.01252/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":"2202.01252","created_at":"2026-07-05T05:13:31.548469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.01252v2","created_at":"2026-07-05T05:13:31.548469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.01252","created_at":"2026-07-05T05:13:31.548469+00:00"},{"alias_kind":"pith_short_12","alias_value":"EDPWGU4XMHIW","created_at":"2026-07-05T05:13:31.548469+00:00"},{"alias_kind":"pith_short_16","alias_value":"EDPWGU4XMHIWFSEI","created_at":"2026-07-05T05:13:31.548469+00:00"},{"alias_kind":"pith_short_8","alias_value":"EDPWGU4X","created_at":"2026-07-05T05:13:31.548469+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/EDPWGU4XMHIWFSEII3GECBL4ED","json":"https://pith.science/pith/EDPWGU4XMHIWFSEII3GECBL4ED.json","graph_json":"https://pith.science/api/pith-number/EDPWGU4XMHIWFSEII3GECBL4ED/graph.json","events_json":"https://pith.science/api/pith-number/EDPWGU4XMHIWFSEII3GECBL4ED/events.json","paper":"https://pith.science/paper/EDPWGU4X"},"agent_actions":{"view_html":"https://pith.science/pith/EDPWGU4XMHIWFSEII3GECBL4ED","download_json":"https://pith.science/pith/EDPWGU4XMHIWFSEII3GECBL4ED.json","view_paper":"https://pith.science/paper/EDPWGU4X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.01252&json=true","fetch_graph":"https://pith.science/api/pith-number/EDPWGU4XMHIWFSEII3GECBL4ED/graph.json","fetch_events":"https://pith.science/api/pith-number/EDPWGU4XMHIWFSEII3GECBL4ED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EDPWGU4XMHIWFSEII3GECBL4ED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EDPWGU4XMHIWFSEII3GECBL4ED/action/storage_attestation","attest_author":"https://pith.science/pith/EDPWGU4XMHIWFSEII3GECBL4ED/action/author_attestation","sign_citation":"https://pith.science/pith/EDPWGU4XMHIWFSEII3GECBL4ED/action/citation_signature","submit_replication":"https://pith.science/pith/EDPWGU4XMHIWFSEII3GECBL4ED/action/replication_record"}},"created_at":"2026-07-05T05:13:31.548469+00:00","updated_at":"2026-07-05T05:13:31.548469+00:00"}