{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OPYZ647DL4KU5S6F3GYTR3TYWA","short_pith_number":"pith:OPYZ647D","schema_version":"1.0","canonical_sha256":"73f19f73e35f154ecbc5d9b138ee78b02da03b005c03961c1470f3b304ba6531","source":{"kind":"arxiv","id":"2306.11309","version":1},"attestation_state":"computed","paper":{"title":"Multi-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Haoran Wei, Xuefei Wang, Yanhua Long, Yijie Li","submitted_at":"2023-06-20T06:08:09Z","abstract_excerpt":"Low-resource accented speech recognition is one of the important challenges faced by current ASR technology in practical applications. In this study, we propose a Conformer-based architecture, called Aformer, to leverage both the acoustic information from large non-accented and limited accented training data. Specifically, a general encoder and an accent encoder are designed in the Aformer to extract complementary acoustic information. Moreover, we propose to train the Aformer in a multi-pass manner, and investigate three cross-information fusion methods to effectively combine the information "},"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":"2306.11309","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-20T06:08:09Z","cross_cats_sorted":["cs.CL","eess.AS","eess.SP"],"title_canon_sha256":"09a4b00d92483c0ccfdbc5bfbfb9551367d74d00530205d1898ad5de6b47026e","abstract_canon_sha256":"735e15ef007384317a26dc2a6e4c932b62e111adade4ae0ebf703d402acdebee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:22:18.091644Z","signature_b64":"w1d2SKhoJASsD2xSuVNTRLOBfbmSzEPRKlm/TnrogFASo/+zCqY1KrzjSKtEDDEhDbU3MIuhAmbGtgAwoGnLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73f19f73e35f154ecbc5d9b138ee78b02da03b005c03961c1470f3b304ba6531","last_reissued_at":"2026-07-05T06:22:18.091244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:22:18.091244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Haoran Wei, Xuefei Wang, Yanhua Long, Yijie Li","submitted_at":"2023-06-20T06:08:09Z","abstract_excerpt":"Low-resource accented speech recognition is one of the important challenges faced by current ASR technology in practical applications. In this study, we propose a Conformer-based architecture, called Aformer, to leverage both the acoustic information from large non-accented and limited accented training data. Specifically, a general encoder and an accent encoder are designed in the Aformer to extract complementary acoustic information. Moreover, we propose to train the Aformer in a multi-pass manner, and investigate three cross-information fusion methods to effectively combine the information "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11309","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/2306.11309/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":"2306.11309","created_at":"2026-07-05T06:22:18.091302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11309v1","created_at":"2026-07-05T06:22:18.091302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11309","created_at":"2026-07-05T06:22:18.091302+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPYZ647DL4KU","created_at":"2026-07-05T06:22:18.091302+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPYZ647DL4KU5S6F","created_at":"2026-07-05T06:22:18.091302+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPYZ647D","created_at":"2026-07-05T06:22:18.091302+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/OPYZ647DL4KU5S6F3GYTR3TYWA","json":"https://pith.science/pith/OPYZ647DL4KU5S6F3GYTR3TYWA.json","graph_json":"https://pith.science/api/pith-number/OPYZ647DL4KU5S6F3GYTR3TYWA/graph.json","events_json":"https://pith.science/api/pith-number/OPYZ647DL4KU5S6F3GYTR3TYWA/events.json","paper":"https://pith.science/paper/OPYZ647D"},"agent_actions":{"view_html":"https://pith.science/pith/OPYZ647DL4KU5S6F3GYTR3TYWA","download_json":"https://pith.science/pith/OPYZ647DL4KU5S6F3GYTR3TYWA.json","view_paper":"https://pith.science/paper/OPYZ647D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11309&json=true","fetch_graph":"https://pith.science/api/pith-number/OPYZ647DL4KU5S6F3GYTR3TYWA/graph.json","fetch_events":"https://pith.science/api/pith-number/OPYZ647DL4KU5S6F3GYTR3TYWA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPYZ647DL4KU5S6F3GYTR3TYWA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPYZ647DL4KU5S6F3GYTR3TYWA/action/storage_attestation","attest_author":"https://pith.science/pith/OPYZ647DL4KU5S6F3GYTR3TYWA/action/author_attestation","sign_citation":"https://pith.science/pith/OPYZ647DL4KU5S6F3GYTR3TYWA/action/citation_signature","submit_replication":"https://pith.science/pith/OPYZ647DL4KU5S6F3GYTR3TYWA/action/replication_record"}},"created_at":"2026-07-05T06:22:18.091302+00:00","updated_at":"2026-07-05T06:22:18.091302+00:00"}