{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:C2XPGXALBG6FEQPDAU4HN3SP4B","short_pith_number":"pith:C2XPGXAL","schema_version":"1.0","canonical_sha256":"16aef35c0b09bc5241e3053876ee4fe070616c92c70a1adc6af13857f4a42791","source":{"kind":"arxiv","id":"2110.04692","version":1},"attestation_state":"computed","paper":{"title":"Poformer: A simple pooling transformer for speaker verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Miao Zhao, Min Liu, Minqiang Xu, Yiwei Ding, Yufeng Ma, Yu Zheng","submitted_at":"2021-10-10T03:12:07Z","abstract_excerpt":"Most recent speaker verification systems are based on extracting speaker embeddings using a deep neural network. The pooling layer in the network aims to aggregate frame-level features extracted by the backbone. In this paper, we propose a new transformer based pooling structure called PoFormer to enhance the ability of the pooling layer to capture information along the whole time axis. Different from previous works that apply attention mechanism in a simple way or implement the multi-head mechanism in serial instead of in parallel, PoFormer follows the initial transformer structure with some "},"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":"2110.04692","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-10T03:12:07Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0f5152d4514a08963a2be302ff1de6264d4eeafab49199628bba4875698ae071","abstract_canon_sha256":"bc1e9fb84ade40fc484077a9d868e8132da4c96b51ab2c6463866ab8df815633"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:20.231471Z","signature_b64":"w22MzujUJnonFTuHhfhzfyKXGEL1gzj2mIO3zToEKUaCAJe5P//j8VUt17I5eBkydMAROtLWT4v71S6PcpILBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16aef35c0b09bc5241e3053876ee4fe070616c92c70a1adc6af13857f4a42791","last_reissued_at":"2026-07-05T03:21:20.230947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:20.230947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Poformer: A simple pooling transformer for speaker verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Miao Zhao, Min Liu, Minqiang Xu, Yiwei Ding, Yufeng Ma, Yu Zheng","submitted_at":"2021-10-10T03:12:07Z","abstract_excerpt":"Most recent speaker verification systems are based on extracting speaker embeddings using a deep neural network. The pooling layer in the network aims to aggregate frame-level features extracted by the backbone. In this paper, we propose a new transformer based pooling structure called PoFormer to enhance the ability of the pooling layer to capture information along the whole time axis. Different from previous works that apply attention mechanism in a simple way or implement the multi-head mechanism in serial instead of in parallel, PoFormer follows the initial transformer structure with some "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04692","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/2110.04692/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":"2110.04692","created_at":"2026-07-05T03:21:20.231003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.04692v1","created_at":"2026-07-05T03:21:20.231003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04692","created_at":"2026-07-05T03:21:20.231003+00:00"},{"alias_kind":"pith_short_12","alias_value":"C2XPGXALBG6F","created_at":"2026-07-05T03:21:20.231003+00:00"},{"alias_kind":"pith_short_16","alias_value":"C2XPGXALBG6FEQPD","created_at":"2026-07-05T03:21:20.231003+00:00"},{"alias_kind":"pith_short_8","alias_value":"C2XPGXAL","created_at":"2026-07-05T03:21:20.231003+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/C2XPGXALBG6FEQPDAU4HN3SP4B","json":"https://pith.science/pith/C2XPGXALBG6FEQPDAU4HN3SP4B.json","graph_json":"https://pith.science/api/pith-number/C2XPGXALBG6FEQPDAU4HN3SP4B/graph.json","events_json":"https://pith.science/api/pith-number/C2XPGXALBG6FEQPDAU4HN3SP4B/events.json","paper":"https://pith.science/paper/C2XPGXAL"},"agent_actions":{"view_html":"https://pith.science/pith/C2XPGXALBG6FEQPDAU4HN3SP4B","download_json":"https://pith.science/pith/C2XPGXALBG6FEQPDAU4HN3SP4B.json","view_paper":"https://pith.science/paper/C2XPGXAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.04692&json=true","fetch_graph":"https://pith.science/api/pith-number/C2XPGXALBG6FEQPDAU4HN3SP4B/graph.json","fetch_events":"https://pith.science/api/pith-number/C2XPGXALBG6FEQPDAU4HN3SP4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C2XPGXALBG6FEQPDAU4HN3SP4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C2XPGXALBG6FEQPDAU4HN3SP4B/action/storage_attestation","attest_author":"https://pith.science/pith/C2XPGXALBG6FEQPDAU4HN3SP4B/action/author_attestation","sign_citation":"https://pith.science/pith/C2XPGXALBG6FEQPDAU4HN3SP4B/action/citation_signature","submit_replication":"https://pith.science/pith/C2XPGXALBG6FEQPDAU4HN3SP4B/action/replication_record"}},"created_at":"2026-07-05T03:21:20.231003+00:00","updated_at":"2026-07-05T03:21:20.231003+00:00"}