{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WSAOPOC5SPYM3QFHO2MBFFOA24","short_pith_number":"pith:WSAOPOC5","schema_version":"1.0","canonical_sha256":"b480e7b85d93f0cdc0a776981295c0d72142c9471d6940906e71052b05189a18","source":{"kind":"arxiv","id":"2305.12121","version":1},"attestation_state":"computed","paper":{"title":"ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Ma, Chongjia Ni, Chong Zhang, Dianwen Ng, Eng Siong Chng, Jia Qi Yip, Shengkui Zhao, Trung Hieu Nguyen, Tuan Truong, Yukun Ma","submitted_at":"2023-05-20T06:56:00Z","abstract_excerpt":"In this paper, we propose ACA-Net, a lightweight, global context-aware speaker embedding extractor for Speaker Verification (SV) that improves upon existing work by using Asymmetric Cross Attention (ACA) to replace temporal pooling. ACA is able to distill large, variable-length sequences into small, fixed-sized latents by attending a small query to large key and value matrices. In ACA-Net, we build a Multi-Layer Aggregation (MLA) block using ACA to generate fixed-sized identity vectors from variable-length inputs. Through global attention, ACA-Net acts as an efficient global feature extractor "},"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":"2305.12121","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-20T06:56:00Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"fa1c8ba8656f7b36e30854143cd48149c7f8bae81209c03656898ca77da8d773","abstract_canon_sha256":"311311268f73d4f4702770468587caa9b69400a70b8cd2661ec5884e26a359a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:06.648259Z","signature_b64":"1LELGM8Ilx9s0EqWvthBDSq6M/xYfI2nw3gg4afnPymKjnrpVAsFx/d00OYDY/WXZ3uFZDCeEgJO7aLxE9s5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b480e7b85d93f0cdc0a776981295c0d72142c9471d6940906e71052b05189a18","last_reissued_at":"2026-07-05T06:12:06.647805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:06.647805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Ma, Chongjia Ni, Chong Zhang, Dianwen Ng, Eng Siong Chng, Jia Qi Yip, Shengkui Zhao, Trung Hieu Nguyen, Tuan Truong, Yukun Ma","submitted_at":"2023-05-20T06:56:00Z","abstract_excerpt":"In this paper, we propose ACA-Net, a lightweight, global context-aware speaker embedding extractor for Speaker Verification (SV) that improves upon existing work by using Asymmetric Cross Attention (ACA) to replace temporal pooling. ACA is able to distill large, variable-length sequences into small, fixed-sized latents by attending a small query to large key and value matrices. In ACA-Net, we build a Multi-Layer Aggregation (MLA) block using ACA to generate fixed-sized identity vectors from variable-length inputs. Through global attention, ACA-Net acts as an efficient global feature extractor "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12121","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/2305.12121/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":"2305.12121","created_at":"2026-07-05T06:12:06.647865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12121v1","created_at":"2026-07-05T06:12:06.647865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12121","created_at":"2026-07-05T06:12:06.647865+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSAOPOC5SPYM","created_at":"2026-07-05T06:12:06.647865+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSAOPOC5SPYM3QFH","created_at":"2026-07-05T06:12:06.647865+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSAOPOC5","created_at":"2026-07-05T06:12:06.647865+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/WSAOPOC5SPYM3QFHO2MBFFOA24","json":"https://pith.science/pith/WSAOPOC5SPYM3QFHO2MBFFOA24.json","graph_json":"https://pith.science/api/pith-number/WSAOPOC5SPYM3QFHO2MBFFOA24/graph.json","events_json":"https://pith.science/api/pith-number/WSAOPOC5SPYM3QFHO2MBFFOA24/events.json","paper":"https://pith.science/paper/WSAOPOC5"},"agent_actions":{"view_html":"https://pith.science/pith/WSAOPOC5SPYM3QFHO2MBFFOA24","download_json":"https://pith.science/pith/WSAOPOC5SPYM3QFHO2MBFFOA24.json","view_paper":"https://pith.science/paper/WSAOPOC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12121&json=true","fetch_graph":"https://pith.science/api/pith-number/WSAOPOC5SPYM3QFHO2MBFFOA24/graph.json","fetch_events":"https://pith.science/api/pith-number/WSAOPOC5SPYM3QFHO2MBFFOA24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSAOPOC5SPYM3QFHO2MBFFOA24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSAOPOC5SPYM3QFHO2MBFFOA24/action/storage_attestation","attest_author":"https://pith.science/pith/WSAOPOC5SPYM3QFHO2MBFFOA24/action/author_attestation","sign_citation":"https://pith.science/pith/WSAOPOC5SPYM3QFHO2MBFFOA24/action/citation_signature","submit_replication":"https://pith.science/pith/WSAOPOC5SPYM3QFHO2MBFFOA24/action/replication_record"}},"created_at":"2026-07-05T06:12:06.647865+00:00","updated_at":"2026-07-05T06:12:06.647865+00:00"}