{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UY3JYJCHI2JVSFVOWP7N3HINCS","short_pith_number":"pith:UY3JYJCH","schema_version":"1.0","canonical_sha256":"a6369c244746935916aeb3fedd9d0d14881838b52d00b512118ba0e43a726fd2","source":{"kind":"arxiv","id":"2106.13514","version":1},"attestation_state":"computed","paper":{"title":"Phoneme-aware and Channel-wise Attentive Learning for Text DependentSpeaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Lin Li, Qingyang Hong, Yan Liu, Zheng Li","submitted_at":"2021-06-25T09:11:18Z","abstract_excerpt":"This paper proposes a multi-task learning network with phoneme-aware and channel-wise attentive learning strategies for text-dependent Speaker Verification (SV). In the proposed structure, the frame-level multi-task learning along with the segment-level adversarial learning is adopted for speaker embedding extraction. The phoneme-aware attentive pooling is exploited on frame-level features in the main network for speaker classifier, with the corresponding posterior probability for the phoneme distribution in the auxiliary subnet. Further, the introduction of Squeeze and Excitation (SE-block) p"},"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":"2106.13514","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-06-25T09:11:18Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"aea862785ed9084856b4a387546af747a21bf923902d6f1db7b491e7554410e2","abstract_canon_sha256":"6d7c0c81b6e4829a579b8934a4f92921904fe155cd8c6a408a40a7e8f88de557"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:20.319526Z","signature_b64":"98exYu3LCyJbrFGF/g9jDtMmfwX1zxYG6Fw1AuIj0cVKwUpKWyv+a9u/gVAA24vvG/JKd3a4oHoZZmpD+sMmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6369c244746935916aeb3fedd9d0d14881838b52d00b512118ba0e43a726fd2","last_reissued_at":"2026-07-05T02:52:20.319158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:20.319158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phoneme-aware and Channel-wise Attentive Learning for Text DependentSpeaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Lin Li, Qingyang Hong, Yan Liu, Zheng Li","submitted_at":"2021-06-25T09:11:18Z","abstract_excerpt":"This paper proposes a multi-task learning network with phoneme-aware and channel-wise attentive learning strategies for text-dependent Speaker Verification (SV). In the proposed structure, the frame-level multi-task learning along with the segment-level adversarial learning is adopted for speaker embedding extraction. The phoneme-aware attentive pooling is exploited on frame-level features in the main network for speaker classifier, with the corresponding posterior probability for the phoneme distribution in the auxiliary subnet. Further, the introduction of Squeeze and Excitation (SE-block) p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13514","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/2106.13514/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":"2106.13514","created_at":"2026-07-05T02:52:20.319214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13514v1","created_at":"2026-07-05T02:52:20.319214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13514","created_at":"2026-07-05T02:52:20.319214+00:00"},{"alias_kind":"pith_short_12","alias_value":"UY3JYJCHI2JV","created_at":"2026-07-05T02:52:20.319214+00:00"},{"alias_kind":"pith_short_16","alias_value":"UY3JYJCHI2JVSFVO","created_at":"2026-07-05T02:52:20.319214+00:00"},{"alias_kind":"pith_short_8","alias_value":"UY3JYJCH","created_at":"2026-07-05T02:52:20.319214+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16276","citing_title":"The SVASR System for Text-dependent Speaker Verification (TdSV) AAIC Challenge 2024","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UY3JYJCHI2JVSFVOWP7N3HINCS","json":"https://pith.science/pith/UY3JYJCHI2JVSFVOWP7N3HINCS.json","graph_json":"https://pith.science/api/pith-number/UY3JYJCHI2JVSFVOWP7N3HINCS/graph.json","events_json":"https://pith.science/api/pith-number/UY3JYJCHI2JVSFVOWP7N3HINCS/events.json","paper":"https://pith.science/paper/UY3JYJCH"},"agent_actions":{"view_html":"https://pith.science/pith/UY3JYJCHI2JVSFVOWP7N3HINCS","download_json":"https://pith.science/pith/UY3JYJCHI2JVSFVOWP7N3HINCS.json","view_paper":"https://pith.science/paper/UY3JYJCH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13514&json=true","fetch_graph":"https://pith.science/api/pith-number/UY3JYJCHI2JVSFVOWP7N3HINCS/graph.json","fetch_events":"https://pith.science/api/pith-number/UY3JYJCHI2JVSFVOWP7N3HINCS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UY3JYJCHI2JVSFVOWP7N3HINCS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UY3JYJCHI2JVSFVOWP7N3HINCS/action/storage_attestation","attest_author":"https://pith.science/pith/UY3JYJCHI2JVSFVOWP7N3HINCS/action/author_attestation","sign_citation":"https://pith.science/pith/UY3JYJCHI2JVSFVOWP7N3HINCS/action/citation_signature","submit_replication":"https://pith.science/pith/UY3JYJCHI2JVSFVOWP7N3HINCS/action/replication_record"}},"created_at":"2026-07-05T02:52:20.319214+00:00","updated_at":"2026-07-05T02:52:20.319214+00:00"}