{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AULTLT4AKHMKEFJSM4Y4RTXEIB","short_pith_number":"pith:AULTLT4A","schema_version":"1.0","canonical_sha256":"051735cf8051d8a215326731c8cee44071648dac80c9844b8779b70823ae0688","source":{"kind":"arxiv","id":"2012.07460","version":4},"attestation_state":"computed","paper":{"title":"Bayesian Learning for Deep Neural Network Adaptation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Lan Wang, Tan Lee, Xunying Liu, Xurong Xie","submitted_at":"2020-12-14T12:30:41Z","abstract_excerpt":"A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that is often attributable to speaker differences. Speaker adaptation techniques play a vital role to reduce the mismatch. Model-based speaker adaptation approaches often require sufficient amounts of target speaker data to ensure robustness. When the amount of speaker level data is limited, speaker adaptation is prone to overfitting and poor generalization. To address the issue, this paper proposes a full Bayesian learning based DNN speaker adaptation framework to model speaker-dependent ("},"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":"2012.07460","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2020-12-14T12:30:41Z","cross_cats_sorted":["eess.AS","stat.ML"],"title_canon_sha256":"8448d246f879c1cc68de9db9e6d9871210d891569c5515b45b7fc8897a963a00","abstract_canon_sha256":"b07406c38ebb97a22490a7ebd049eeb40e067fb86f9a1060c223482e3beaabfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:37.765261Z","signature_b64":"SEmEbilskmQEfIxONjrwCPb8LITGGmOiZQ7dDWN24fll4ZRqYjDXa/SSJ4lDh7Ewpu3dF1Gkh8ws/Ih+mN38BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"051735cf8051d8a215326731c8cee44071648dac80c9844b8779b70823ae0688","last_reissued_at":"2026-07-05T08:31:37.764863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:37.764863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Learning for Deep Neural Network Adaptation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Lan Wang, Tan Lee, Xunying Liu, Xurong Xie","submitted_at":"2020-12-14T12:30:41Z","abstract_excerpt":"A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that is often attributable to speaker differences. Speaker adaptation techniques play a vital role to reduce the mismatch. Model-based speaker adaptation approaches often require sufficient amounts of target speaker data to ensure robustness. When the amount of speaker level data is limited, speaker adaptation is prone to overfitting and poor generalization. To address the issue, this paper proposes a full Bayesian learning based DNN speaker adaptation framework to model speaker-dependent ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07460","kind":"arxiv","version":4},"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/2012.07460/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":"2012.07460","created_at":"2026-07-05T08:31:37.764913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.07460v4","created_at":"2026-07-05T08:31:37.764913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07460","created_at":"2026-07-05T08:31:37.764913+00:00"},{"alias_kind":"pith_short_12","alias_value":"AULTLT4AKHMK","created_at":"2026-07-05T08:31:37.764913+00:00"},{"alias_kind":"pith_short_16","alias_value":"AULTLT4AKHMKEFJS","created_at":"2026-07-05T08:31:37.764913+00:00"},{"alias_kind":"pith_short_8","alias_value":"AULTLT4A","created_at":"2026-07-05T08:31:37.764913+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/AULTLT4AKHMKEFJSM4Y4RTXEIB","json":"https://pith.science/pith/AULTLT4AKHMKEFJSM4Y4RTXEIB.json","graph_json":"https://pith.science/api/pith-number/AULTLT4AKHMKEFJSM4Y4RTXEIB/graph.json","events_json":"https://pith.science/api/pith-number/AULTLT4AKHMKEFJSM4Y4RTXEIB/events.json","paper":"https://pith.science/paper/AULTLT4A"},"agent_actions":{"view_html":"https://pith.science/pith/AULTLT4AKHMKEFJSM4Y4RTXEIB","download_json":"https://pith.science/pith/AULTLT4AKHMKEFJSM4Y4RTXEIB.json","view_paper":"https://pith.science/paper/AULTLT4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.07460&json=true","fetch_graph":"https://pith.science/api/pith-number/AULTLT4AKHMKEFJSM4Y4RTXEIB/graph.json","fetch_events":"https://pith.science/api/pith-number/AULTLT4AKHMKEFJSM4Y4RTXEIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AULTLT4AKHMKEFJSM4Y4RTXEIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AULTLT4AKHMKEFJSM4Y4RTXEIB/action/storage_attestation","attest_author":"https://pith.science/pith/AULTLT4AKHMKEFJSM4Y4RTXEIB/action/author_attestation","sign_citation":"https://pith.science/pith/AULTLT4AKHMKEFJSM4Y4RTXEIB/action/citation_signature","submit_replication":"https://pith.science/pith/AULTLT4AKHMKEFJSM4Y4RTXEIB/action/replication_record"}},"created_at":"2026-07-05T08:31:37.764913+00:00","updated_at":"2026-07-05T08:31:37.764913+00:00"}