{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:C2DOXUKC2PNOC2AHKPVOSMLHFZ","short_pith_number":"pith:C2DOXUKC","schema_version":"1.0","canonical_sha256":"1686ebd142d3dae1680753eae931672e6b6f8aa9ae804f7cdc271a0e37d82060","source":{"kind":"arxiv","id":"2105.07367","version":1},"attestation_state":"computed","paper":{"title":"X-Vectors with Multi-Scale Aggregation for Speaker Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Divya Neelagiri, Myungjong Kim, Vijendra Raj Apsingekar","submitted_at":"2021-05-16T06:23:36Z","abstract_excerpt":"Speaker diarization is the process of labeling different speakers in a speech signal. Deep speaker embeddings are generally extracted from short speech segments and clustered to determine the segments belong to same speaker identity. The x-vector, which embeds segment-level speaker characteristics by statistically pooling frame-level representations, is one of the most widely used deep speaker embeddings in speaker diarization. Multi-scale aggregation, which employs multi-scale representations from different layers, has recently successfully been used in short duration speaker verification. In"},"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":"2105.07367","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-05-16T06:23:36Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0bac33db5f94e735698703618f9f0e35801da883ac93bd51e02cdc0e4f3d3591","abstract_canon_sha256":"3775fb2f93882456e24898e2edcec1cb8df3dbd9f5707d551aa62fdd68f91ab1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:40.269031Z","signature_b64":"LRYcsNhDNE7yViSCdzG/hN9yrEK8kmV4oDl1k29ZH4RNCbJD2b9SP7nbwK/+piDPpEVrp/T9qWNnG5+LIW6KBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1686ebd142d3dae1680753eae931672e6b6f8aa9ae804f7cdc271a0e37d82060","last_reissued_at":"2026-07-05T02:40:40.268615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:40.268615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X-Vectors with Multi-Scale Aggregation for Speaker Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Divya Neelagiri, Myungjong Kim, Vijendra Raj Apsingekar","submitted_at":"2021-05-16T06:23:36Z","abstract_excerpt":"Speaker diarization is the process of labeling different speakers in a speech signal. Deep speaker embeddings are generally extracted from short speech segments and clustered to determine the segments belong to same speaker identity. The x-vector, which embeds segment-level speaker characteristics by statistically pooling frame-level representations, is one of the most widely used deep speaker embeddings in speaker diarization. Multi-scale aggregation, which employs multi-scale representations from different layers, has recently successfully been used in short duration speaker verification. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.07367","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/2105.07367/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":"2105.07367","created_at":"2026-07-05T02:40:40.268680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.07367v1","created_at":"2026-07-05T02:40:40.268680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.07367","created_at":"2026-07-05T02:40:40.268680+00:00"},{"alias_kind":"pith_short_12","alias_value":"C2DOXUKC2PNO","created_at":"2026-07-05T02:40:40.268680+00:00"},{"alias_kind":"pith_short_16","alias_value":"C2DOXUKC2PNOC2AH","created_at":"2026-07-05T02:40:40.268680+00:00"},{"alias_kind":"pith_short_8","alias_value":"C2DOXUKC","created_at":"2026-07-05T02:40:40.268680+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/C2DOXUKC2PNOC2AHKPVOSMLHFZ","json":"https://pith.science/pith/C2DOXUKC2PNOC2AHKPVOSMLHFZ.json","graph_json":"https://pith.science/api/pith-number/C2DOXUKC2PNOC2AHKPVOSMLHFZ/graph.json","events_json":"https://pith.science/api/pith-number/C2DOXUKC2PNOC2AHKPVOSMLHFZ/events.json","paper":"https://pith.science/paper/C2DOXUKC"},"agent_actions":{"view_html":"https://pith.science/pith/C2DOXUKC2PNOC2AHKPVOSMLHFZ","download_json":"https://pith.science/pith/C2DOXUKC2PNOC2AHKPVOSMLHFZ.json","view_paper":"https://pith.science/paper/C2DOXUKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.07367&json=true","fetch_graph":"https://pith.science/api/pith-number/C2DOXUKC2PNOC2AHKPVOSMLHFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/C2DOXUKC2PNOC2AHKPVOSMLHFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C2DOXUKC2PNOC2AHKPVOSMLHFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C2DOXUKC2PNOC2AHKPVOSMLHFZ/action/storage_attestation","attest_author":"https://pith.science/pith/C2DOXUKC2PNOC2AHKPVOSMLHFZ/action/author_attestation","sign_citation":"https://pith.science/pith/C2DOXUKC2PNOC2AHKPVOSMLHFZ/action/citation_signature","submit_replication":"https://pith.science/pith/C2DOXUKC2PNOC2AHKPVOSMLHFZ/action/replication_record"}},"created_at":"2026-07-05T02:40:40.268680+00:00","updated_at":"2026-07-05T02:40:40.268680+00:00"}