{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IDL27OGIPIE7BXX3EK6BPNPM3T","short_pith_number":"pith:IDL27OGI","schema_version":"1.0","canonical_sha256":"40d7afb8c87a09f0defb22bc17b5ecdcdcd7364d840b1e866a2afc2de7b0578d","source":{"kind":"arxiv","id":"2309.01437","version":2},"attestation_state":"computed","paper":{"title":"SememeASR: Boosting Performance of End-to-End Speech Recognition against Domain and Long-Tailed Data Shift with Sememe Semantic Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Changhe Song, Helen Meng, Jiaxu Zhu, Zhiyong Wu","submitted_at":"2023-09-04T08:35:05Z","abstract_excerpt":"Recently, excellent progress has been made in speech recognition. However, pure data-driven approaches have struggled to solve the problem in domain-mismatch and long-tailed data. Considering that knowledge-driven approaches can help data-driven approaches alleviate their flaws, we introduce sememe-based semantic knowledge information to speech recognition (SememeASR). Sememe, according to the linguistic definition, is the minimum semantic unit in a language and is able to represent the implicit semantic information behind each word very well. Our experiments show that the introduction of seme"},"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":"2309.01437","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-04T08:35:05Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"068b4c903c2cbac886e8ff039bfce89226ae5ff722b01d1c86ef0aadd6f47d24","abstract_canon_sha256":"086c1628852791aa3a9d8ff597aafee2d8129fa3420432eccadff8ca62de2139"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:14.204446Z","signature_b64":"yjt6xHCwifYg//9W21xGAX9wFKLDMtovq32JWqjnfqpvQdNhKUmLh0ntdKDSQMGE8wj+ZDj0qoZ8tDL/4/AQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40d7afb8c87a09f0defb22bc17b5ecdcdcd7364d840b1e866a2afc2de7b0578d","last_reissued_at":"2026-07-05T06:58:14.203975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:14.203975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SememeASR: Boosting Performance of End-to-End Speech Recognition against Domain and Long-Tailed Data Shift with Sememe Semantic Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Changhe Song, Helen Meng, Jiaxu Zhu, Zhiyong Wu","submitted_at":"2023-09-04T08:35:05Z","abstract_excerpt":"Recently, excellent progress has been made in speech recognition. However, pure data-driven approaches have struggled to solve the problem in domain-mismatch and long-tailed data. Considering that knowledge-driven approaches can help data-driven approaches alleviate their flaws, we introduce sememe-based semantic knowledge information to speech recognition (SememeASR). Sememe, according to the linguistic definition, is the minimum semantic unit in a language and is able to represent the implicit semantic information behind each word very well. Our experiments show that the introduction of seme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01437","kind":"arxiv","version":2},"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/2309.01437/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":"2309.01437","created_at":"2026-07-05T06:58:14.204030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01437v2","created_at":"2026-07-05T06:58:14.204030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01437","created_at":"2026-07-05T06:58:14.204030+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDL27OGIPIE7","created_at":"2026-07-05T06:58:14.204030+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDL27OGIPIE7BXX3","created_at":"2026-07-05T06:58:14.204030+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDL27OGI","created_at":"2026-07-05T06:58:14.204030+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/IDL27OGIPIE7BXX3EK6BPNPM3T","json":"https://pith.science/pith/IDL27OGIPIE7BXX3EK6BPNPM3T.json","graph_json":"https://pith.science/api/pith-number/IDL27OGIPIE7BXX3EK6BPNPM3T/graph.json","events_json":"https://pith.science/api/pith-number/IDL27OGIPIE7BXX3EK6BPNPM3T/events.json","paper":"https://pith.science/paper/IDL27OGI"},"agent_actions":{"view_html":"https://pith.science/pith/IDL27OGIPIE7BXX3EK6BPNPM3T","download_json":"https://pith.science/pith/IDL27OGIPIE7BXX3EK6BPNPM3T.json","view_paper":"https://pith.science/paper/IDL27OGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01437&json=true","fetch_graph":"https://pith.science/api/pith-number/IDL27OGIPIE7BXX3EK6BPNPM3T/graph.json","fetch_events":"https://pith.science/api/pith-number/IDL27OGIPIE7BXX3EK6BPNPM3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDL27OGIPIE7BXX3EK6BPNPM3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDL27OGIPIE7BXX3EK6BPNPM3T/action/storage_attestation","attest_author":"https://pith.science/pith/IDL27OGIPIE7BXX3EK6BPNPM3T/action/author_attestation","sign_citation":"https://pith.science/pith/IDL27OGIPIE7BXX3EK6BPNPM3T/action/citation_signature","submit_replication":"https://pith.science/pith/IDL27OGIPIE7BXX3EK6BPNPM3T/action/replication_record"}},"created_at":"2026-07-05T06:58:14.204030+00:00","updated_at":"2026-07-05T06:58:14.204030+00:00"}