{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JZGJRCYQ3ZFIJ3BMVTSYLCFQBC","short_pith_number":"pith:JZGJRCYQ","schema_version":"1.0","canonical_sha256":"4e4c988b10de4a84ec2cace58588b008bc94c81af30dea50e8ee420a7db55897","source":{"kind":"arxiv","id":"2103.11326","version":2},"attestation_state":"computed","paper":{"title":"A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Junich Yamagishi, Xin Wang","submitted_at":"2021-03-21T07:39:20Z","abstract_excerpt":"A great deal of recent research effort on speech spoofing countermeasures has been invested into back-end neural networks and training criteria. We contribute to this effort with a comparative perspective in this study. Our comparison of countermeasure models on the ASVspoof 2019 logical access task takes into account recently proposed margin-based training criteria, widely used front ends, and common strategies to deal with varied-length input trials. We also measured intra-model differences through multiple training-evaluation rounds with random initialization. Our statistical analysis demon"},"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":"2103.11326","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2021-03-21T07:39:20Z","cross_cats_sorted":[],"title_canon_sha256":"082682db09818fc1af9a5a4aa9bff3037f3df1d1cc4675c0cbba239135e7b882","abstract_canon_sha256":"aca73cb62590cd6f9a1aef43578b302f4e43a0fe11573cbe92d41c3c8b1a4db9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:36.611056Z","signature_b64":"/tLxNBwkUK2o5N5uYmxWjmewwkK08SKQ2HeePnMBJ4IMI1R9NSrBY/tQp5Bj6KT+6lckL9hXwqRcsD3Qo5AjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e4c988b10de4a84ec2cace58588b008bc94c81af30dea50e8ee420a7db55897","last_reissued_at":"2026-07-05T02:48:36.610615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:36.610615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Junich Yamagishi, Xin Wang","submitted_at":"2021-03-21T07:39:20Z","abstract_excerpt":"A great deal of recent research effort on speech spoofing countermeasures has been invested into back-end neural networks and training criteria. We contribute to this effort with a comparative perspective in this study. Our comparison of countermeasure models on the ASVspoof 2019 logical access task takes into account recently proposed margin-based training criteria, widely used front ends, and common strategies to deal with varied-length input trials. We also measured intra-model differences through multiple training-evaluation rounds with random initialization. Our statistical analysis demon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11326","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/2103.11326/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":"2103.11326","created_at":"2026-07-05T02:48:36.610671+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.11326v2","created_at":"2026-07-05T02:48:36.610671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11326","created_at":"2026-07-05T02:48:36.610671+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZGJRCYQ3ZFI","created_at":"2026-07-05T02:48:36.610671+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZGJRCYQ3ZFIJ3BM","created_at":"2026-07-05T02:48:36.610671+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZGJRCYQ","created_at":"2026-07-05T02:48:36.610671+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10246","citing_title":"Linguistically Augmented Audio Speech Data (LinguAS)","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07232","citing_title":"Towards multi-modal forgery representation learning for AI-generated video detection and localization","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JZGJRCYQ3ZFIJ3BMVTSYLCFQBC","json":"https://pith.science/pith/JZGJRCYQ3ZFIJ3BMVTSYLCFQBC.json","graph_json":"https://pith.science/api/pith-number/JZGJRCYQ3ZFIJ3BMVTSYLCFQBC/graph.json","events_json":"https://pith.science/api/pith-number/JZGJRCYQ3ZFIJ3BMVTSYLCFQBC/events.json","paper":"https://pith.science/paper/JZGJRCYQ"},"agent_actions":{"view_html":"https://pith.science/pith/JZGJRCYQ3ZFIJ3BMVTSYLCFQBC","download_json":"https://pith.science/pith/JZGJRCYQ3ZFIJ3BMVTSYLCFQBC.json","view_paper":"https://pith.science/paper/JZGJRCYQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.11326&json=true","fetch_graph":"https://pith.science/api/pith-number/JZGJRCYQ3ZFIJ3BMVTSYLCFQBC/graph.json","fetch_events":"https://pith.science/api/pith-number/JZGJRCYQ3ZFIJ3BMVTSYLCFQBC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZGJRCYQ3ZFIJ3BMVTSYLCFQBC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZGJRCYQ3ZFIJ3BMVTSYLCFQBC/action/storage_attestation","attest_author":"https://pith.science/pith/JZGJRCYQ3ZFIJ3BMVTSYLCFQBC/action/author_attestation","sign_citation":"https://pith.science/pith/JZGJRCYQ3ZFIJ3BMVTSYLCFQBC/action/citation_signature","submit_replication":"https://pith.science/pith/JZGJRCYQ3ZFIJ3BMVTSYLCFQBC/action/replication_record"}},"created_at":"2026-07-05T02:48:36.610671+00:00","updated_at":"2026-07-05T02:48:36.610671+00:00"}