{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LF4562T5ODVFIKFIABY7BQWS22","short_pith_number":"pith:LF4562T5","schema_version":"1.0","canonical_sha256":"5979df6a7d70ea5428a80071f0c2d2d6b91dfe9ebf6f9227d8b47fa996631a8d","source":{"kind":"arxiv","id":"2203.15249","version":2},"attestation_state":"computed","paper":{"title":"MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haibin Wu, Helen Meng, Hung-yi Lee, Pengfei Hu, Shanshan Zhang, Yang Zhang, Zhiqiang Lv, Zhiyong Wu","submitted_at":"2022-03-29T05:48:24Z","abstract_excerpt":"In this paper, we present Multi-scale Feature Aggregation Conformer (MFA-Conformer), an easy-to-implement, simple but effective backbone for automatic speaker verification based on the Convolution-augmented Transformer (Conformer). The architecture of the MFA-Conformer is inspired by recent stateof-the-art models in speech recognition and speaker verification. Firstly, we introduce a convolution subsampling layer to decrease the computational cost of the model. Secondly, we adopt Conformer blocks which combine Transformers and convolution neural networks (CNNs) to capture global and local feat"},"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":"2203.15249","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-29T05:48:24Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d921fb040d7c8e05a5b8dd7bb1a49e9ae05c7054a96a8c5c85e167d25fd0d20d","abstract_canon_sha256":"556641c1602934066235d8cebf4a00eee59a06dd5209df59b6cf183b61d073d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:10.189463Z","signature_b64":"NcOSpkNmbk9NkBjnh3nnJ27JB+Q9JbZ64+s7RGbciVIHuv/Kn+FKAAIu1qfC3ZQO6ipV5Hgw3SF3Pkae/CGSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5979df6a7d70ea5428a80071f0c2d2d6b91dfe9ebf6f9227d8b47fa996631a8d","last_reissued_at":"2026-07-05T05:15:10.188975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:10.188975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haibin Wu, Helen Meng, Hung-yi Lee, Pengfei Hu, Shanshan Zhang, Yang Zhang, Zhiqiang Lv, Zhiyong Wu","submitted_at":"2022-03-29T05:48:24Z","abstract_excerpt":"In this paper, we present Multi-scale Feature Aggregation Conformer (MFA-Conformer), an easy-to-implement, simple but effective backbone for automatic speaker verification based on the Convolution-augmented Transformer (Conformer). The architecture of the MFA-Conformer is inspired by recent stateof-the-art models in speech recognition and speaker verification. Firstly, we introduce a convolution subsampling layer to decrease the computational cost of the model. Secondly, we adopt Conformer blocks which combine Transformers and convolution neural networks (CNNs) to capture global and local feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15249","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/2203.15249/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":"2203.15249","created_at":"2026-07-05T05:15:10.189032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.15249v2","created_at":"2026-07-05T05:15:10.189032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15249","created_at":"2026-07-05T05:15:10.189032+00:00"},{"alias_kind":"pith_short_12","alias_value":"LF4562T5ODVF","created_at":"2026-07-05T05:15:10.189032+00:00"},{"alias_kind":"pith_short_16","alias_value":"LF4562T5ODVFIKFI","created_at":"2026-07-05T05:15:10.189032+00:00"},{"alias_kind":"pith_short_8","alias_value":"LF4562T5","created_at":"2026-07-05T05:15:10.189032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21305","citing_title":"LISE : Listenable Interpretable Speaker Embeddings","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LF4562T5ODVFIKFIABY7BQWS22","json":"https://pith.science/pith/LF4562T5ODVFIKFIABY7BQWS22.json","graph_json":"https://pith.science/api/pith-number/LF4562T5ODVFIKFIABY7BQWS22/graph.json","events_json":"https://pith.science/api/pith-number/LF4562T5ODVFIKFIABY7BQWS22/events.json","paper":"https://pith.science/paper/LF4562T5"},"agent_actions":{"view_html":"https://pith.science/pith/LF4562T5ODVFIKFIABY7BQWS22","download_json":"https://pith.science/pith/LF4562T5ODVFIKFIABY7BQWS22.json","view_paper":"https://pith.science/paper/LF4562T5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.15249&json=true","fetch_graph":"https://pith.science/api/pith-number/LF4562T5ODVFIKFIABY7BQWS22/graph.json","fetch_events":"https://pith.science/api/pith-number/LF4562T5ODVFIKFIABY7BQWS22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LF4562T5ODVFIKFIABY7BQWS22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LF4562T5ODVFIKFIABY7BQWS22/action/storage_attestation","attest_author":"https://pith.science/pith/LF4562T5ODVFIKFIABY7BQWS22/action/author_attestation","sign_citation":"https://pith.science/pith/LF4562T5ODVFIKFIABY7BQWS22/action/citation_signature","submit_replication":"https://pith.science/pith/LF4562T5ODVFIKFIABY7BQWS22/action/replication_record"}},"created_at":"2026-07-05T05:15:10.189032+00:00","updated_at":"2026-07-05T05:15:10.189032+00:00"}