{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JSYWFTDB5HOSIH4NKCKL3LG5DU","short_pith_number":"pith:JSYWFTDB","schema_version":"1.0","canonical_sha256":"4cb162cc61e9dd241f8d5094bdacdd1d1723501f44979b85fc4f69fd4b75650e","source":{"kind":"arxiv","id":"2406.04791","version":3},"attestation_state":"computed","paper":{"title":"Speaker-Smoothed kNN Speaker Adaptation for End-to-End ASR","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Daimeng Wei, Hao Yang, Hengchao Shang, Jiaxin Guo, Shaojun Li, Xianghui He, Yuanchang Luo, Zhanglin Wu, Zhiqiang Rao, Zongyao Li","submitted_at":"2024-06-07T09:38:38Z","abstract_excerpt":"Despite recent improvements in End-to-End Automatic Speech Recognition (E2E ASR) systems, the performance can degrade due to vocal characteristic mismatches between training and testing data, particularly with limited target speaker adaptation data. We propose a novel speaker adaptation approach Speaker-Smoothed kNN that leverages k-Nearest Neighbors (kNN) retrieval techniques to improve model output by finding correctly pronounced tokens from its pre-built datastore during the decoding phase. Moreover, we utilize x-vector to dynamically adjust kNN interpolation parameters for data sparsity is"},"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":"2406.04791","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-07T09:38:38Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0e7153b907c0b043e998e8b37bd8f98061f905685337cc4f33b1f4a4af7fae3d","abstract_canon_sha256":"87e664e4d548372c7dadcdf3d440ce60ea2582a2e03144b02aef233d66e7c84d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:00.411051Z","signature_b64":"j08e0g5yEomEb7lML/sNjzgnMkAUT/oXj57m+SOVgn+iqIX6VXwyQFFaMfoDvoV5rn3ZXrCWYmmINyLUWdacAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cb162cc61e9dd241f8d5094bdacdd1d1723501f44979b85fc4f69fd4b75650e","last_reissued_at":"2026-07-05T08:39:00.410517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:00.410517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaker-Smoothed kNN Speaker Adaptation for End-to-End ASR","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Daimeng Wei, Hao Yang, Hengchao Shang, Jiaxin Guo, Shaojun Li, Xianghui He, Yuanchang Luo, Zhanglin Wu, Zhiqiang Rao, Zongyao Li","submitted_at":"2024-06-07T09:38:38Z","abstract_excerpt":"Despite recent improvements in End-to-End Automatic Speech Recognition (E2E ASR) systems, the performance can degrade due to vocal characteristic mismatches between training and testing data, particularly with limited target speaker adaptation data. We propose a novel speaker adaptation approach Speaker-Smoothed kNN that leverages k-Nearest Neighbors (kNN) retrieval techniques to improve model output by finding correctly pronounced tokens from its pre-built datastore during the decoding phase. Moreover, we utilize x-vector to dynamically adjust kNN interpolation parameters for data sparsity is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04791","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/2406.04791/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":"2406.04791","created_at":"2026-07-05T08:39:00.410576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04791v3","created_at":"2026-07-05T08:39:00.410576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04791","created_at":"2026-07-05T08:39:00.410576+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSYWFTDB5HOS","created_at":"2026-07-05T08:39:00.410576+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSYWFTDB5HOSIH4N","created_at":"2026-07-05T08:39:00.410576+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSYWFTDB","created_at":"2026-07-05T08:39:00.410576+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/JSYWFTDB5HOSIH4NKCKL3LG5DU","json":"https://pith.science/pith/JSYWFTDB5HOSIH4NKCKL3LG5DU.json","graph_json":"https://pith.science/api/pith-number/JSYWFTDB5HOSIH4NKCKL3LG5DU/graph.json","events_json":"https://pith.science/api/pith-number/JSYWFTDB5HOSIH4NKCKL3LG5DU/events.json","paper":"https://pith.science/paper/JSYWFTDB"},"agent_actions":{"view_html":"https://pith.science/pith/JSYWFTDB5HOSIH4NKCKL3LG5DU","download_json":"https://pith.science/pith/JSYWFTDB5HOSIH4NKCKL3LG5DU.json","view_paper":"https://pith.science/paper/JSYWFTDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04791&json=true","fetch_graph":"https://pith.science/api/pith-number/JSYWFTDB5HOSIH4NKCKL3LG5DU/graph.json","fetch_events":"https://pith.science/api/pith-number/JSYWFTDB5HOSIH4NKCKL3LG5DU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSYWFTDB5HOSIH4NKCKL3LG5DU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSYWFTDB5HOSIH4NKCKL3LG5DU/action/storage_attestation","attest_author":"https://pith.science/pith/JSYWFTDB5HOSIH4NKCKL3LG5DU/action/author_attestation","sign_citation":"https://pith.science/pith/JSYWFTDB5HOSIH4NKCKL3LG5DU/action/citation_signature","submit_replication":"https://pith.science/pith/JSYWFTDB5HOSIH4NKCKL3LG5DU/action/replication_record"}},"created_at":"2026-07-05T08:39:00.410576+00:00","updated_at":"2026-07-05T08:39:00.410576+00:00"}