{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:THJJBDIQ53VLVLRLZK5ZFSH2UF","short_pith_number":"pith:THJJBDIQ","schema_version":"1.0","canonical_sha256":"99d2908d10eeeabaae2bcabb92c8faa14e52e30fd438db9ba1d7f1e10390bf56","source":{"kind":"arxiv","id":"2004.03194","version":4},"attestation_state":"computed","paper":{"title":"Improving Multi-Scale Aggregation Using Feature Pyramid Module for Robust Speaker Verification of Variable-Duration Utterances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Hoirin Kim, Myunghun Jung, Seong Min Kye, Yeunju Choi, Youngmoon Jung","submitted_at":"2020-04-07T08:35:05Z","abstract_excerpt":"Currently, the most widely used approach for speaker verification is the deep speaker embedding learning. In this approach, we obtain a speaker embedding vector by pooling single-scale features that are extracted from the last layer of a speaker feature extractor. Multi-scale aggregation (MSA), which utilizes multi-scale features from different layers of the feature extractor, has recently been introduced and shows superior performance for variable-duration utterances. To increase the robustness dealing with utterances of arbitrary duration, this paper improves the MSA by using a feature pyram"},"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":"2004.03194","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-04-07T08:35:05Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"e3a2f84658c517753d8eee78aa8f802621f6a174af4b9dc5649cef12dcda3dc4","abstract_canon_sha256":"db9ed4fe9c83da7d20306084e11c2415c287a2c5f576b07ae99ccaac39ab3623"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:36.450350Z","signature_b64":"+z6vEwPz563UbIwOVitmmJ6hDq21BK+N5iXjZxwGtZVdDoNH/RDUBqycERFifIZFm2NLVzPkuDv4x7pgmrEZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99d2908d10eeeabaae2bcabb92c8faa14e52e30fd438db9ba1d7f1e10390bf56","last_reissued_at":"2026-07-05T01:49:36.449909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:36.449909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Multi-Scale Aggregation Using Feature Pyramid Module for Robust Speaker Verification of Variable-Duration Utterances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Hoirin Kim, Myunghun Jung, Seong Min Kye, Yeunju Choi, Youngmoon Jung","submitted_at":"2020-04-07T08:35:05Z","abstract_excerpt":"Currently, the most widely used approach for speaker verification is the deep speaker embedding learning. In this approach, we obtain a speaker embedding vector by pooling single-scale features that are extracted from the last layer of a speaker feature extractor. Multi-scale aggregation (MSA), which utilizes multi-scale features from different layers of the feature extractor, has recently been introduced and shows superior performance for variable-duration utterances. To increase the robustness dealing with utterances of arbitrary duration, this paper improves the MSA by using a feature pyram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03194","kind":"arxiv","version":4},"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/2004.03194/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":"2004.03194","created_at":"2026-07-05T01:49:36.449963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.03194v4","created_at":"2026-07-05T01:49:36.449963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03194","created_at":"2026-07-05T01:49:36.449963+00:00"},{"alias_kind":"pith_short_12","alias_value":"THJJBDIQ53VL","created_at":"2026-07-05T01:49:36.449963+00:00"},{"alias_kind":"pith_short_16","alias_value":"THJJBDIQ53VLVLRL","created_at":"2026-07-05T01:49:36.449963+00:00"},{"alias_kind":"pith_short_8","alias_value":"THJJBDIQ","created_at":"2026-07-05T01:49:36.449963+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/THJJBDIQ53VLVLRLZK5ZFSH2UF","json":"https://pith.science/pith/THJJBDIQ53VLVLRLZK5ZFSH2UF.json","graph_json":"https://pith.science/api/pith-number/THJJBDIQ53VLVLRLZK5ZFSH2UF/graph.json","events_json":"https://pith.science/api/pith-number/THJJBDIQ53VLVLRLZK5ZFSH2UF/events.json","paper":"https://pith.science/paper/THJJBDIQ"},"agent_actions":{"view_html":"https://pith.science/pith/THJJBDIQ53VLVLRLZK5ZFSH2UF","download_json":"https://pith.science/pith/THJJBDIQ53VLVLRLZK5ZFSH2UF.json","view_paper":"https://pith.science/paper/THJJBDIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.03194&json=true","fetch_graph":"https://pith.science/api/pith-number/THJJBDIQ53VLVLRLZK5ZFSH2UF/graph.json","fetch_events":"https://pith.science/api/pith-number/THJJBDIQ53VLVLRLZK5ZFSH2UF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/THJJBDIQ53VLVLRLZK5ZFSH2UF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/THJJBDIQ53VLVLRLZK5ZFSH2UF/action/storage_attestation","attest_author":"https://pith.science/pith/THJJBDIQ53VLVLRLZK5ZFSH2UF/action/author_attestation","sign_citation":"https://pith.science/pith/THJJBDIQ53VLVLRLZK5ZFSH2UF/action/citation_signature","submit_replication":"https://pith.science/pith/THJJBDIQ53VLVLRLZK5ZFSH2UF/action/replication_record"}},"created_at":"2026-07-05T01:49:36.449963+00:00","updated_at":"2026-07-05T01:49:36.449963+00:00"}