{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:L6KURH27KINVIECRE6BC4D2LUF","short_pith_number":"pith:L6KURH27","schema_version":"1.0","canonical_sha256":"5f95489f5f521b54105127822e0f4ba1602cd86238e7ca32917858be349dc02c","source":{"kind":"arxiv","id":"2203.15277","version":2},"attestation_state":"computed","paper":{"title":"Decomposed Temporal Dynamic CNN: Efficient Time-Adaptive Network for Text-Independent Speaker Verification Explained with Speaker Activation Map","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hyeonuk Nam, Seong-Hu Kim, Yong-Hwa Park","submitted_at":"2022-03-29T06:46:53Z","abstract_excerpt":"To extract accurate speaker information for text-independent speaker verification, temporal dynamic CNNs (TDY-CNNs) adapting kernels to each time bin was proposed. However, model size of TDY-CNN is too large and the adaptive kernel's degree of freedom is limited. To address these limitations, we propose decomposed temporal dynamic CNNs (DTDY-CNNs) which forms time-adaptive kernel by combining static kernel with dynamic residual based on matrix decomposition. Proposed DTDY-ResNet-34(x0.50) using attentive statistical pooling without data augmentation shows EER of 0.96%, which is better than oth"},"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":"2203.15277","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-03-29T06:46:53Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"bb017539058c53f11bc149ff84ffadf30b0797b0cbf4a664425e14bcfb1ec6b5","abstract_canon_sha256":"034024aefacf2598fba8089f0b1b0f2e2408180b424207f8da1852bc191d806e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:54.889497Z","signature_b64":"tzUdJl2DCPMk4ORnUl/R0vF6FvGB1/YyYoYCjxAnEJEz3AIecKmJFTYIoqQcucQtMNbASk0SsSenURKOcKTDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f95489f5f521b54105127822e0f4ba1602cd86238e7ca32917858be349dc02c","last_reissued_at":"2026-07-05T05:10:54.889065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:54.889065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decomposed Temporal Dynamic CNN: Efficient Time-Adaptive Network for Text-Independent Speaker Verification Explained with Speaker Activation Map","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hyeonuk Nam, Seong-Hu Kim, Yong-Hwa Park","submitted_at":"2022-03-29T06:46:53Z","abstract_excerpt":"To extract accurate speaker information for text-independent speaker verification, temporal dynamic CNNs (TDY-CNNs) adapting kernels to each time bin was proposed. However, model size of TDY-CNN is too large and the adaptive kernel's degree of freedom is limited. To address these limitations, we propose decomposed temporal dynamic CNNs (DTDY-CNNs) which forms time-adaptive kernel by combining static kernel with dynamic residual based on matrix decomposition. Proposed DTDY-ResNet-34(x0.50) using attentive statistical pooling without data augmentation shows EER of 0.96%, which is better than oth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15277","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/2203.15277/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":"2203.15277","created_at":"2026-07-05T05:10:54.889129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.15277v2","created_at":"2026-07-05T05:10:54.889129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15277","created_at":"2026-07-05T05:10:54.889129+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6KURH27KINV","created_at":"2026-07-05T05:10:54.889129+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6KURH27KINVIECR","created_at":"2026-07-05T05:10:54.889129+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6KURH27","created_at":"2026-07-05T05:10:54.889129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12785","citing_title":"Frequency Dynamic Convolutions for Sound Event Detection","ref_index":102,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L6KURH27KINVIECRE6BC4D2LUF","json":"https://pith.science/pith/L6KURH27KINVIECRE6BC4D2LUF.json","graph_json":"https://pith.science/api/pith-number/L6KURH27KINVIECRE6BC4D2LUF/graph.json","events_json":"https://pith.science/api/pith-number/L6KURH27KINVIECRE6BC4D2LUF/events.json","paper":"https://pith.science/paper/L6KURH27"},"agent_actions":{"view_html":"https://pith.science/pith/L6KURH27KINVIECRE6BC4D2LUF","download_json":"https://pith.science/pith/L6KURH27KINVIECRE6BC4D2LUF.json","view_paper":"https://pith.science/paper/L6KURH27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.15277&json=true","fetch_graph":"https://pith.science/api/pith-number/L6KURH27KINVIECRE6BC4D2LUF/graph.json","fetch_events":"https://pith.science/api/pith-number/L6KURH27KINVIECRE6BC4D2LUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6KURH27KINVIECRE6BC4D2LUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6KURH27KINVIECRE6BC4D2LUF/action/storage_attestation","attest_author":"https://pith.science/pith/L6KURH27KINVIECRE6BC4D2LUF/action/author_attestation","sign_citation":"https://pith.science/pith/L6KURH27KINVIECRE6BC4D2LUF/action/citation_signature","submit_replication":"https://pith.science/pith/L6KURH27KINVIECRE6BC4D2LUF/action/replication_record"}},"created_at":"2026-07-05T05:10:54.889129+00:00","updated_at":"2026-07-05T05:10:54.889129+00:00"}