{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HZSWIQS7K7ZZG6LCEFJQFQGFMR","short_pith_number":"pith:HZSWIQS7","schema_version":"1.0","canonical_sha256":"3e6564425f57f3937962215302c0c5647eaeb69d04a6575952b99fb6cc5cfcf6","source":{"kind":"arxiv","id":"2001.04584","version":1},"attestation_state":"computed","paper":{"title":"An Improved Deep Neural Network for Modeling Speaker Characteristics at Different Temporal Scales","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Bin Gu, Wu Guo","submitted_at":"2020-01-14T02:02:47Z","abstract_excerpt":"This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution (MSCNN) is adopted in frame-level layers to capture complementary speaker information in different receptive fields. (2) A Baum-Welch statistics attention (BWSA) mechanism is applied in pooling-layer, which can integrate more useful long-term speaker characteristics in the temporal pooling layer. Experiments are carried out on the NIST SRE16 evaluation set."},"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":"2001.04584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-01-14T02:02:47Z","cross_cats_sorted":["cs.SD","eess.SP"],"title_canon_sha256":"452eba09d46cde6ccde9a66d390b4696f75151f3c76c956f43ca7f65ed2c1513","abstract_canon_sha256":"a1a0ff6c5ebbd2bf1056a045aa83161096de09068f1c9a9963a6000fc824056a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:33:27.173166Z","signature_b64":"OOFf0QcikNVsKCyKwGGBpSbzwynaCt4Cl9lQEVX5FaNlQK/aFp5eassjpnihUhyVg8VCOWp8CbxY7WsCQg/NDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e6564425f57f3937962215302c0c5647eaeb69d04a6575952b99fb6cc5cfcf6","last_reissued_at":"2026-07-05T00:33:27.172768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:33:27.172768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Improved Deep Neural Network for Modeling Speaker Characteristics at Different Temporal Scales","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Bin Gu, Wu Guo","submitted_at":"2020-01-14T02:02:47Z","abstract_excerpt":"This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution (MSCNN) is adopted in frame-level layers to capture complementary speaker information in different receptive fields. (2) A Baum-Welch statistics attention (BWSA) mechanism is applied in pooling-layer, which can integrate more useful long-term speaker characteristics in the temporal pooling layer. Experiments are carried out on the NIST SRE16 evaluation set."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.04584","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/2001.04584/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":"2001.04584","created_at":"2026-07-05T00:33:27.172815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.04584v1","created_at":"2026-07-05T00:33:27.172815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.04584","created_at":"2026-07-05T00:33:27.172815+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZSWIQS7K7ZZ","created_at":"2026-07-05T00:33:27.172815+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZSWIQS7K7ZZG6LC","created_at":"2026-07-05T00:33:27.172815+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZSWIQS7","created_at":"2026-07-05T00:33:27.172815+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/HZSWIQS7K7ZZG6LCEFJQFQGFMR","json":"https://pith.science/pith/HZSWIQS7K7ZZG6LCEFJQFQGFMR.json","graph_json":"https://pith.science/api/pith-number/HZSWIQS7K7ZZG6LCEFJQFQGFMR/graph.json","events_json":"https://pith.science/api/pith-number/HZSWIQS7K7ZZG6LCEFJQFQGFMR/events.json","paper":"https://pith.science/paper/HZSWIQS7"},"agent_actions":{"view_html":"https://pith.science/pith/HZSWIQS7K7ZZG6LCEFJQFQGFMR","download_json":"https://pith.science/pith/HZSWIQS7K7ZZG6LCEFJQFQGFMR.json","view_paper":"https://pith.science/paper/HZSWIQS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.04584&json=true","fetch_graph":"https://pith.science/api/pith-number/HZSWIQS7K7ZZG6LCEFJQFQGFMR/graph.json","fetch_events":"https://pith.science/api/pith-number/HZSWIQS7K7ZZG6LCEFJQFQGFMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZSWIQS7K7ZZG6LCEFJQFQGFMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZSWIQS7K7ZZG6LCEFJQFQGFMR/action/storage_attestation","attest_author":"https://pith.science/pith/HZSWIQS7K7ZZG6LCEFJQFQGFMR/action/author_attestation","sign_citation":"https://pith.science/pith/HZSWIQS7K7ZZG6LCEFJQFQGFMR/action/citation_signature","submit_replication":"https://pith.science/pith/HZSWIQS7K7ZZG6LCEFJQFQGFMR/action/replication_record"}},"created_at":"2026-07-05T00:33:27.172815+00:00","updated_at":"2026-07-05T00:33:27.172815+00:00"}