{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AJIVCMBYOSXYTLG6J6TXGXMGNF","short_pith_number":"pith:AJIVCMBY","schema_version":"1.0","canonical_sha256":"025151303874af89acde4fa7735d86694c0123f88c445aa5e1adf4a8c9c5283a","source":{"kind":"arxiv","id":"2010.12951","version":3},"attestation_state":"computed","paper":{"title":"Y-Vector: Multiscale Waveform Encoder for Speaker Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Fei Jiang, Ge Zhu, Zhiyao Duan","submitted_at":"2020-10-24T18:44:00Z","abstract_excerpt":"State-of-the-art text-independent speaker verification systems typically use cepstral features or filter bank energies as speech features. Recent studies attempted to extract speaker embeddings directly from raw waveforms and have shown competitive results. In this paper, we propose a novel multi-scale waveform encoder that uses three convolution branches with different time scales to compute speech features from the waveform. These features are then processed by squeeze-and-excitation blocks, a multi-level feature aggregator, and a time delayed neural network (TDNN) to compute speaker embeddi"},"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":"2010.12951","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-24T18:44:00Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"4149458807bbb38747914d395834454c5063ab720da5d5eaaeb66002b72f03af","abstract_canon_sha256":"4ca9e3ce85cf2fffa2840b58c448bac5ea6f533a134e7dad21829eab8ed0569f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:40.184097Z","signature_b64":"yrQ0jPzulNWJ6MKkp9DW9FoGeRYww6aJKfot3CleYZCw6i5R57CokErnyP31mkc715fK/WHZblLlvmDa1woJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"025151303874af89acde4fa7735d86694c0123f88c445aa5e1adf4a8c9c5283a","last_reissued_at":"2026-07-05T02:47:40.183535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:40.183535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Y-Vector: Multiscale Waveform Encoder for Speaker Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Fei Jiang, Ge Zhu, Zhiyao Duan","submitted_at":"2020-10-24T18:44:00Z","abstract_excerpt":"State-of-the-art text-independent speaker verification systems typically use cepstral features or filter bank energies as speech features. Recent studies attempted to extract speaker embeddings directly from raw waveforms and have shown competitive results. In this paper, we propose a novel multi-scale waveform encoder that uses three convolution branches with different time scales to compute speech features from the waveform. These features are then processed by squeeze-and-excitation blocks, a multi-level feature aggregator, and a time delayed neural network (TDNN) to compute speaker embeddi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12951","kind":"arxiv","version":3},"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/2010.12951/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":"2010.12951","created_at":"2026-07-05T02:47:40.183615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.12951v3","created_at":"2026-07-05T02:47:40.183615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12951","created_at":"2026-07-05T02:47:40.183615+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJIVCMBYOSXY","created_at":"2026-07-05T02:47:40.183615+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJIVCMBYOSXYTLG6","created_at":"2026-07-05T02:47:40.183615+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJIVCMBY","created_at":"2026-07-05T02:47:40.183615+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/AJIVCMBYOSXYTLG6J6TXGXMGNF","json":"https://pith.science/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF.json","graph_json":"https://pith.science/api/pith-number/AJIVCMBYOSXYTLG6J6TXGXMGNF/graph.json","events_json":"https://pith.science/api/pith-number/AJIVCMBYOSXYTLG6J6TXGXMGNF/events.json","paper":"https://pith.science/paper/AJIVCMBY"},"agent_actions":{"view_html":"https://pith.science/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF","download_json":"https://pith.science/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF.json","view_paper":"https://pith.science/paper/AJIVCMBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.12951&json=true","fetch_graph":"https://pith.science/api/pith-number/AJIVCMBYOSXYTLG6J6TXGXMGNF/graph.json","fetch_events":"https://pith.science/api/pith-number/AJIVCMBYOSXYTLG6J6TXGXMGNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF/action/storage_attestation","attest_author":"https://pith.science/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF/action/author_attestation","sign_citation":"https://pith.science/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF/action/citation_signature","submit_replication":"https://pith.science/pith/AJIVCMBYOSXYTLG6J6TXGXMGNF/action/replication_record"}},"created_at":"2026-07-05T02:47:40.183615+00:00","updated_at":"2026-07-05T02:47:40.183615+00:00"}