{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T23WEJKBUETQEENBT4QJBXHEBJ","short_pith_number":"pith:T23WEJKB","schema_version":"1.0","canonical_sha256":"9eb7622541a1270211a19f2090dce40a5c88b8e3f4e5b5cd0cae206d39ed1dc6","source":{"kind":"arxiv","id":"2010.12653","version":1},"attestation_state":"computed","paper":{"title":"SpeakerNet: 1D Depth-wise Separable Convolutional Network for Text-Independent Speaker Recognition and Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Jason Li, Nithin Rao Koluguri, Vitaly Lavrukhin","submitted_at":"2020-10-23T20:34:54Z","abstract_excerpt":"We propose SpeakerNet - a new neural architecture for speaker recognition and speaker verification tasks. It is composed of residual blocks with 1D depth-wise separable convolutions, batch-normalization, and ReLU layers. This architecture uses x-vector based statistics pooling layer to map variable-length utterances to a fixed-length embedding (q-vector). SpeakerNet-M is a simple lightweight model with just 5M parameters. It doesn't use voice activity detection (VAD) and achieves close to state-of-the-art performance scoring an Equal Error Rate (EER) of 2.10% on the VoxCeleb1 cleaned and 2.29%"},"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":"2010.12653","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-23T20:34:54Z","cross_cats_sorted":[],"title_canon_sha256":"b44d3d8d98ee24f33f8b88a5714f4ba26903fb323c0ab07da9dd00d5380b2c15","abstract_canon_sha256":"0c0122d8fe2fcf4a28f68b342ee609739aa6b5fd7d45293f5922d17cd3efdf18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:46.921078Z","signature_b64":"Ck5Rj2ey/UeyyqaDS6H60hcBLHUl9R/P6+kTAcGjBomZT4sSyiHDQFhsQx4jVGtEIMBkFaheSHjIqrr8LjJACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9eb7622541a1270211a19f2090dce40a5c88b8e3f4e5b5cd0cae206d39ed1dc6","last_reissued_at":"2026-07-05T01:45:46.920685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:46.920685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeakerNet: 1D Depth-wise Separable Convolutional Network for Text-Independent Speaker Recognition and Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Jason Li, Nithin Rao Koluguri, Vitaly Lavrukhin","submitted_at":"2020-10-23T20:34:54Z","abstract_excerpt":"We propose SpeakerNet - a new neural architecture for speaker recognition and speaker verification tasks. It is composed of residual blocks with 1D depth-wise separable convolutions, batch-normalization, and ReLU layers. This architecture uses x-vector based statistics pooling layer to map variable-length utterances to a fixed-length embedding (q-vector). SpeakerNet-M is a simple lightweight model with just 5M parameters. It doesn't use voice activity detection (VAD) and achieves close to state-of-the-art performance scoring an Equal Error Rate (EER) of 2.10% on the VoxCeleb1 cleaned and 2.29%"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12653","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/2010.12653/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":"2010.12653","created_at":"2026-07-05T01:45:46.920747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.12653v1","created_at":"2026-07-05T01:45:46.920747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12653","created_at":"2026-07-05T01:45:46.920747+00:00"},{"alias_kind":"pith_short_12","alias_value":"T23WEJKBUETQ","created_at":"2026-07-05T01:45:46.920747+00:00"},{"alias_kind":"pith_short_16","alias_value":"T23WEJKBUETQEENB","created_at":"2026-07-05T01:45:46.920747+00:00"},{"alias_kind":"pith_short_8","alias_value":"T23WEJKB","created_at":"2026-07-05T01:45:46.920747+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00675","citing_title":"Speaker-Conditioned Phrase Break Prediction for Text-to-Speech with Phoneme-Level Pre-trained Language Model","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T23WEJKBUETQEENBT4QJBXHEBJ","json":"https://pith.science/pith/T23WEJKBUETQEENBT4QJBXHEBJ.json","graph_json":"https://pith.science/api/pith-number/T23WEJKBUETQEENBT4QJBXHEBJ/graph.json","events_json":"https://pith.science/api/pith-number/T23WEJKBUETQEENBT4QJBXHEBJ/events.json","paper":"https://pith.science/paper/T23WEJKB"},"agent_actions":{"view_html":"https://pith.science/pith/T23WEJKBUETQEENBT4QJBXHEBJ","download_json":"https://pith.science/pith/T23WEJKBUETQEENBT4QJBXHEBJ.json","view_paper":"https://pith.science/paper/T23WEJKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.12653&json=true","fetch_graph":"https://pith.science/api/pith-number/T23WEJKBUETQEENBT4QJBXHEBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/T23WEJKBUETQEENBT4QJBXHEBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T23WEJKBUETQEENBT4QJBXHEBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T23WEJKBUETQEENBT4QJBXHEBJ/action/storage_attestation","attest_author":"https://pith.science/pith/T23WEJKBUETQEENBT4QJBXHEBJ/action/author_attestation","sign_citation":"https://pith.science/pith/T23WEJKBUETQEENBT4QJBXHEBJ/action/citation_signature","submit_replication":"https://pith.science/pith/T23WEJKBUETQEENBT4QJBXHEBJ/action/replication_record"}},"created_at":"2026-07-05T01:45:46.920747+00:00","updated_at":"2026-07-05T01:45:46.920747+00:00"}