{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7TYTDPCEA3NIW2MH7L6NNPNLKH","short_pith_number":"pith:7TYTDPCE","schema_version":"1.0","canonical_sha256":"fcf131bc4406da8b6987fafcd6bdab51d2eb685e5be6ee7502b8ca8f8fdcc2a3","source":{"kind":"arxiv","id":"1909.11430","version":3},"attestation_state":"computed","paper":{"title":"Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Jin Huang, Meiyuan Fang, Qiao Cheng, Yaqian Han, Yitao Duan","submitted_at":"2019-09-25T12:13:43Z","abstract_excerpt":"In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel corpus composed of clean text and will perform poorly on text with recognition noise, a gap well known in speech translation community. In this paper, we propose a training architecture which aims at making a neural machine translation model more robust against speech recognition errors. Our approach addresses the encoder and the decoder simultaneously using "},"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":"1909.11430","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-25T12:13:43Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"41e76a9d9658aeb6e5dd266aa9c0df5854f84d9644abc577f81e200607daea6a","abstract_canon_sha256":"654ae862117d4eb519b22f57251481fd728d4e60443a1d90e433feb6fd51e25e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:09.498057Z","signature_b64":"w4QSGoH5unlLyk17HBjdzB4YwS3NQX2cIuiQMDFWb+Pu86xazsFTJTo2zmMHtjYV0hJGcuhGYkvbaM228vujAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcf131bc4406da8b6987fafcd6bdab51d2eb685e5be6ee7502b8ca8f8fdcc2a3","last_reissued_at":"2026-07-05T00:15:09.497618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:09.497618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Jin Huang, Meiyuan Fang, Qiao Cheng, Yaqian Han, Yitao Duan","submitted_at":"2019-09-25T12:13:43Z","abstract_excerpt":"In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel corpus composed of clean text and will perform poorly on text with recognition noise, a gap well known in speech translation community. In this paper, we propose a training architecture which aims at making a neural machine translation model more robust against speech recognition errors. Our approach addresses the encoder and the decoder simultaneously using "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11430","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/1909.11430/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":"1909.11430","created_at":"2026-07-05T00:15:09.497680+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.11430v3","created_at":"2026-07-05T00:15:09.497680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11430","created_at":"2026-07-05T00:15:09.497680+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TYTDPCEA3NI","created_at":"2026-07-05T00:15:09.497680+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TYTDPCEA3NIW2MH","created_at":"2026-07-05T00:15:09.497680+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TYTDPCE","created_at":"2026-07-05T00:15:09.497680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.01512","citing_title":"MCAT: Scaling Many-to-Many Speech-to-Text Translation with MLLMs to 70 Languages","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7TYTDPCEA3NIW2MH7L6NNPNLKH","json":"https://pith.science/pith/7TYTDPCEA3NIW2MH7L6NNPNLKH.json","graph_json":"https://pith.science/api/pith-number/7TYTDPCEA3NIW2MH7L6NNPNLKH/graph.json","events_json":"https://pith.science/api/pith-number/7TYTDPCEA3NIW2MH7L6NNPNLKH/events.json","paper":"https://pith.science/paper/7TYTDPCE"},"agent_actions":{"view_html":"https://pith.science/pith/7TYTDPCEA3NIW2MH7L6NNPNLKH","download_json":"https://pith.science/pith/7TYTDPCEA3NIW2MH7L6NNPNLKH.json","view_paper":"https://pith.science/paper/7TYTDPCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.11430&json=true","fetch_graph":"https://pith.science/api/pith-number/7TYTDPCEA3NIW2MH7L6NNPNLKH/graph.json","fetch_events":"https://pith.science/api/pith-number/7TYTDPCEA3NIW2MH7L6NNPNLKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TYTDPCEA3NIW2MH7L6NNPNLKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TYTDPCEA3NIW2MH7L6NNPNLKH/action/storage_attestation","attest_author":"https://pith.science/pith/7TYTDPCEA3NIW2MH7L6NNPNLKH/action/author_attestation","sign_citation":"https://pith.science/pith/7TYTDPCEA3NIW2MH7L6NNPNLKH/action/citation_signature","submit_replication":"https://pith.science/pith/7TYTDPCEA3NIW2MH7L6NNPNLKH/action/replication_record"}},"created_at":"2026-07-05T00:15:09.497680+00:00","updated_at":"2026-07-05T00:15:09.497680+00:00"}