{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2006:RWCN2OAVRTUJOCXSPKBVIQ55JQ","short_pith_number":"pith:RWCN2OAV","schema_version":"1.0","canonical_sha256":"8d84dd38158ce8970af27a835443bd4c0ea54b301e42c13c5ecf8e5518fb0972","source":{"kind":"arxiv","id":"cs/0612138","version":1},"attestation_state":"computed","paper":{"title":"Accommodating Sample Size Effect on Similarity Measures in Speaker Clustering","license":"","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.SD","authors_text":"Alexander Haubold, John R. Kender","submitted_at":"2006-12-28T06:39:55Z","abstract_excerpt":"We investigate the symmetric Kullback-Leibler (KL2) distance in speaker clustering and its unreported effects for differently-sized feature matrices. Speaker data is represented as Mel Frequency Cepstral Coefficient (MFCC) vectors, and features are compared using the KL2 metric to form clusters of speech segments for each speaker. We make two observations with respect to clustering based on KL2: 1.) The accuracy of clustering is strongly dependent on the absolute lengths of the speech segments and their extracted feature vectors. 2.) The accuracy of the similarity measure strongly degrades wit"},"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":"cs/0612138","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.SD","submitted_at":"2006-12-28T06:39:55Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"0b645c0d6d75fdc0af62464c436fce44ce332526b1ed4aaa9e4152de3d728c05","abstract_canon_sha256":"039d5eb9d435c65c4771590850c1f37278b790a6b93a923ce9053cc8a190e979"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T14:58:16.485623Z","signature_b64":"6sa+SJMxzTTIJ7iYcMxE5iPMk80OWX3V0VJGfDUjsj6PiPg2ufhmVeNpWS6l7Kt0RryT7pGZKGzUd25/xRmWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d84dd38158ce8970af27a835443bd4c0ea54b301e42c13c5ecf8e5518fb0972","last_reissued_at":"2026-07-04T14:58:16.485222Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T14:58:16.485222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accommodating Sample Size Effect on Similarity Measures in Speaker Clustering","license":"","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.SD","authors_text":"Alexander Haubold, John R. Kender","submitted_at":"2006-12-28T06:39:55Z","abstract_excerpt":"We investigate the symmetric Kullback-Leibler (KL2) distance in speaker clustering and its unreported effects for differently-sized feature matrices. Speaker data is represented as Mel Frequency Cepstral Coefficient (MFCC) vectors, and features are compared using the KL2 metric to form clusters of speech segments for each speaker. We make two observations with respect to clustering based on KL2: 1.) The accuracy of clustering is strongly dependent on the absolute lengths of the speech segments and their extracted feature vectors. 2.) The accuracy of the similarity measure strongly degrades wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0612138","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/cs/0612138/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":"cs/0612138","created_at":"2026-07-04T14:58:16.485277+00:00"},{"alias_kind":"arxiv_version","alias_value":"cs/0612138v1","created_at":"2026-07-04T14:58:16.485277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0612138","created_at":"2026-07-04T14:58:16.485277+00:00"},{"alias_kind":"pith_short_12","alias_value":"RWCN2OAVRTUJ","created_at":"2026-07-04T14:58:16.485277+00:00"},{"alias_kind":"pith_short_16","alias_value":"RWCN2OAVRTUJOCXS","created_at":"2026-07-04T14:58:16.485277+00:00"},{"alias_kind":"pith_short_8","alias_value":"RWCN2OAV","created_at":"2026-07-04T14:58:16.485277+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/RWCN2OAVRTUJOCXSPKBVIQ55JQ","json":"https://pith.science/pith/RWCN2OAVRTUJOCXSPKBVIQ55JQ.json","graph_json":"https://pith.science/api/pith-number/RWCN2OAVRTUJOCXSPKBVIQ55JQ/graph.json","events_json":"https://pith.science/api/pith-number/RWCN2OAVRTUJOCXSPKBVIQ55JQ/events.json","paper":"https://pith.science/paper/RWCN2OAV"},"agent_actions":{"view_html":"https://pith.science/pith/RWCN2OAVRTUJOCXSPKBVIQ55JQ","download_json":"https://pith.science/pith/RWCN2OAVRTUJOCXSPKBVIQ55JQ.json","view_paper":"https://pith.science/paper/RWCN2OAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cs/0612138&json=true","fetch_graph":"https://pith.science/api/pith-number/RWCN2OAVRTUJOCXSPKBVIQ55JQ/graph.json","fetch_events":"https://pith.science/api/pith-number/RWCN2OAVRTUJOCXSPKBVIQ55JQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RWCN2OAVRTUJOCXSPKBVIQ55JQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RWCN2OAVRTUJOCXSPKBVIQ55JQ/action/storage_attestation","attest_author":"https://pith.science/pith/RWCN2OAVRTUJOCXSPKBVIQ55JQ/action/author_attestation","sign_citation":"https://pith.science/pith/RWCN2OAVRTUJOCXSPKBVIQ55JQ/action/citation_signature","submit_replication":"https://pith.science/pith/RWCN2OAVRTUJOCXSPKBVIQ55JQ/action/replication_record"}},"created_at":"2026-07-04T14:58:16.485277+00:00","updated_at":"2026-07-04T14:58:16.485277+00:00"}