{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TWTBL3GCR6PGDPXEU5YDMNY5S5","short_pith_number":"pith:TWTBL3GC","schema_version":"1.0","canonical_sha256":"9da615ecc28f9e61bee4a77036371d974e43ce839f2446f107962756f79f3269","source":{"kind":"arxiv","id":"2110.04410","version":1},"attestation_state":"computed","paper":{"title":"TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Nithin Rao Koluguri, Taejin Park","submitted_at":"2021-10-08T23:49:42Z","abstract_excerpt":"In this paper, we propose TitaNet, a novel neural network architecture for extracting speaker representations. We employ 1D depth-wise separable convolutions with Squeeze-and-Excitation (SE) layers with global context followed by channel attention based statistics pooling layer to map variable-length utterances to a fixed-length embedding (t-vector). TitaNet is a scalable architecture and achieves state-of-the-art performance on speaker verification task with an equal error rate (EER) of 0.68% on the VoxCeleb1 trial file and also on speaker diarization tasks with diarization error rate (DER) o"},"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":"2110.04410","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-08T23:49:42Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"12beeff5e6d3ed4c35171b0756565d62cabdeac4e2dbcb5b3ecfe79dd8095222","abstract_canon_sha256":"45b488a87278063126154b0979d104958e0ba2a0ce6eddeae3939b0a607896c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:16.531583Z","signature_b64":"pbDXvEK5Wfua+FwnRMoKBhj7+7vatP+L3ha1lmBzdkzJcNiaHWIDVGl3kTsGwE0WGzdznAxERmLcxnhckFZRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9da615ecc28f9e61bee4a77036371d974e43ce839f2446f107962756f79f3269","last_reissued_at":"2026-07-05T03:21:16.531140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:16.531140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Nithin Rao Koluguri, Taejin Park","submitted_at":"2021-10-08T23:49:42Z","abstract_excerpt":"In this paper, we propose TitaNet, a novel neural network architecture for extracting speaker representations. We employ 1D depth-wise separable convolutions with Squeeze-and-Excitation (SE) layers with global context followed by channel attention based statistics pooling layer to map variable-length utterances to a fixed-length embedding (t-vector). TitaNet is a scalable architecture and achieves state-of-the-art performance on speaker verification task with an equal error rate (EER) of 0.68% on the VoxCeleb1 trial file and also on speaker diarization tasks with diarization error rate (DER) o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04410","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/2110.04410/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":"2110.04410","created_at":"2026-07-05T03:21:16.531196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.04410v1","created_at":"2026-07-05T03:21:16.531196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04410","created_at":"2026-07-05T03:21:16.531196+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWTBL3GCR6PG","created_at":"2026-07-05T03:21:16.531196+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWTBL3GCR6PGDPXE","created_at":"2026-07-05T03:21:16.531196+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWTBL3GC","created_at":"2026-07-05T03:21:16.531196+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09908","citing_title":"Voice Biomarkers for Depression and Anxiety","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TWTBL3GCR6PGDPXEU5YDMNY5S5","json":"https://pith.science/pith/TWTBL3GCR6PGDPXEU5YDMNY5S5.json","graph_json":"https://pith.science/api/pith-number/TWTBL3GCR6PGDPXEU5YDMNY5S5/graph.json","events_json":"https://pith.science/api/pith-number/TWTBL3GCR6PGDPXEU5YDMNY5S5/events.json","paper":"https://pith.science/paper/TWTBL3GC"},"agent_actions":{"view_html":"https://pith.science/pith/TWTBL3GCR6PGDPXEU5YDMNY5S5","download_json":"https://pith.science/pith/TWTBL3GCR6PGDPXEU5YDMNY5S5.json","view_paper":"https://pith.science/paper/TWTBL3GC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.04410&json=true","fetch_graph":"https://pith.science/api/pith-number/TWTBL3GCR6PGDPXEU5YDMNY5S5/graph.json","fetch_events":"https://pith.science/api/pith-number/TWTBL3GCR6PGDPXEU5YDMNY5S5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWTBL3GCR6PGDPXEU5YDMNY5S5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWTBL3GCR6PGDPXEU5YDMNY5S5/action/storage_attestation","attest_author":"https://pith.science/pith/TWTBL3GCR6PGDPXEU5YDMNY5S5/action/author_attestation","sign_citation":"https://pith.science/pith/TWTBL3GCR6PGDPXEU5YDMNY5S5/action/citation_signature","submit_replication":"https://pith.science/pith/TWTBL3GCR6PGDPXEU5YDMNY5S5/action/replication_record"}},"created_at":"2026-07-05T03:21:16.531196+00:00","updated_at":"2026-07-05T03:21:16.531196+00:00"}