{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CL3NXEPSFXIEB3GEAONX7TBEK3","short_pith_number":"pith:CL3NXEPS","schema_version":"1.0","canonical_sha256":"12f6db91f22dd040ecc4039b7fcc2456dacafc820e4d5111eee65c8a4897f460","source":{"kind":"arxiv","id":"1806.02786","version":1},"attestation_state":"computed","paper":{"title":"Domain Adversarial Training for Accented Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ching-Feng Yeh, Lei Xie, Mari Ostendorf, Mei-Yuh Hwang, Sining Sun","submitted_at":"2018-06-07T17:02:54Z","abstract_excerpt":"In this paper, we propose a domain adversarial training (DAT) algorithm to alleviate the accented speech recognition problem. In order to reduce the mismatch between labeled source domain data (\"standard\" accent) and unlabeled target domain data (with heavy accents), we augment the learning objective for a Kaldi TDNN network with a domain adversarial training (DAT) objective to encourage the model to learn accent-invariant features. In experiments with three Mandarin accents, we show that DAT yields up to 7.45% relative character error rate reduction when we do not have transcriptions of the a"},"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":"1806.02786","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-07T17:02:54Z","cross_cats_sorted":[],"title_canon_sha256":"5060b0bab98b76e4ced0e5989cd50c960d5e39f87abad58ffcffb9ad43c4b42b","abstract_canon_sha256":"f74d74c454525760cadfa9f592494e7a9fcd5b0400cf656ac701ac3c2170507a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:55.670221Z","signature_b64":"VLVonYiHQI5zEXvOJm36NlsT39rkBl8F0mLcDj4Lpp+s9YzdMXWjAl4KSsbXRy5+xtYbjVLM3zLQC1yT+x2cCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12f6db91f22dd040ecc4039b7fcc2456dacafc820e4d5111eee65c8a4897f460","last_reissued_at":"2026-05-18T00:13:55.669499Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:55.669499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Adversarial Training for Accented Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ching-Feng Yeh, Lei Xie, Mari Ostendorf, Mei-Yuh Hwang, Sining Sun","submitted_at":"2018-06-07T17:02:54Z","abstract_excerpt":"In this paper, we propose a domain adversarial training (DAT) algorithm to alleviate the accented speech recognition problem. In order to reduce the mismatch between labeled source domain data (\"standard\" accent) and unlabeled target domain data (with heavy accents), we augment the learning objective for a Kaldi TDNN network with a domain adversarial training (DAT) objective to encourage the model to learn accent-invariant features. In experiments with three Mandarin accents, we show that DAT yields up to 7.45% relative character error rate reduction when we do not have transcriptions of the a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02786","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":""},"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":"1806.02786","created_at":"2026-05-18T00:13:55.669618+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.02786v1","created_at":"2026-05-18T00:13:55.669618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02786","created_at":"2026-05-18T00:13:55.669618+00:00"},{"alias_kind":"pith_short_12","alias_value":"CL3NXEPSFXIE","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CL3NXEPSFXIEB3GE","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CL3NXEPS","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27273","citing_title":"Few-Shot Accent Synthesis for ASR with LLM-Guided Phoneme Editing","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CL3NXEPSFXIEB3GEAONX7TBEK3","json":"https://pith.science/pith/CL3NXEPSFXIEB3GEAONX7TBEK3.json","graph_json":"https://pith.science/api/pith-number/CL3NXEPSFXIEB3GEAONX7TBEK3/graph.json","events_json":"https://pith.science/api/pith-number/CL3NXEPSFXIEB3GEAONX7TBEK3/events.json","paper":"https://pith.science/paper/CL3NXEPS"},"agent_actions":{"view_html":"https://pith.science/pith/CL3NXEPSFXIEB3GEAONX7TBEK3","download_json":"https://pith.science/pith/CL3NXEPSFXIEB3GEAONX7TBEK3.json","view_paper":"https://pith.science/paper/CL3NXEPS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.02786&json=true","fetch_graph":"https://pith.science/api/pith-number/CL3NXEPSFXIEB3GEAONX7TBEK3/graph.json","fetch_events":"https://pith.science/api/pith-number/CL3NXEPSFXIEB3GEAONX7TBEK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CL3NXEPSFXIEB3GEAONX7TBEK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CL3NXEPSFXIEB3GEAONX7TBEK3/action/storage_attestation","attest_author":"https://pith.science/pith/CL3NXEPSFXIEB3GEAONX7TBEK3/action/author_attestation","sign_citation":"https://pith.science/pith/CL3NXEPSFXIEB3GEAONX7TBEK3/action/citation_signature","submit_replication":"https://pith.science/pith/CL3NXEPSFXIEB3GEAONX7TBEK3/action/replication_record"}},"created_at":"2026-05-18T00:13:55.669618+00:00","updated_at":"2026-05-18T00:13:55.669618+00:00"}