{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4KI3BRD2MIKHV7LWRDBW3IRXQ5","short_pith_number":"pith:4KI3BRD2","schema_version":"1.0","canonical_sha256":"e291b0c47a62147afd7688c36da2378742ee51a8106064f8fc638976a12a0daf","source":{"kind":"arxiv","id":"1906.09292","version":3},"attestation_state":"computed","paper":{"title":"Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Antoine Bruguier, Golan Pundak, Ke Hu, Rohit Prabhavalkar, Tara N. Sainath","submitted_at":"2019-06-21T19:04:39Z","abstract_excerpt":"Contextual automatic speech recognition, i.e., biasing recognition towards a given context (e.g. user's playlists, or contacts), is challenging in end-to-end (E2E) models. Such models maintain a limited number of candidates during beam-search decoding, and have been found to recognize rare named entities poorly. The problem is exacerbated when biasing towards proper nouns in foreign languages, e.g., geographic location names, which are virtually unseen in training and are thus out-of-vocabulary (OOV). While grapheme or wordpiece E2E models might have a difficult time spelling OOV words, phonem"},"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":"1906.09292","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-21T19:04:39Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"6b60fc87474eba403c17f0b32ad0cb29e161b04f64fd05c89428f0f705e67a6b","abstract_canon_sha256":"c1647ec8fdb8533bce99582e17491dec84c272006a47cffe6906631ded365f22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:03.285354Z","signature_b64":"dUadMNS/EM7KB0y3URMNZ52tKxqIjc92CykFhE2Xp/7FcDneQSbabfE6+rboOkjNYL5z6K0etPC7+POISDTHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e291b0c47a62147afd7688c36da2378742ee51a8106064f8fc638976a12a0daf","last_reissued_at":"2026-05-17T23:40:03.284681Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:03.284681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Antoine Bruguier, Golan Pundak, Ke Hu, Rohit Prabhavalkar, Tara N. Sainath","submitted_at":"2019-06-21T19:04:39Z","abstract_excerpt":"Contextual automatic speech recognition, i.e., biasing recognition towards a given context (e.g. user's playlists, or contacts), is challenging in end-to-end (E2E) models. Such models maintain a limited number of candidates during beam-search decoding, and have been found to recognize rare named entities poorly. The problem is exacerbated when biasing towards proper nouns in foreign languages, e.g., geographic location names, which are virtually unseen in training and are thus out-of-vocabulary (OOV). While grapheme or wordpiece E2E models might have a difficult time spelling OOV words, phonem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09292","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":""},"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":"1906.09292","created_at":"2026-05-17T23:40:03.284792+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.09292v3","created_at":"2026-05-17T23:40:03.284792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09292","created_at":"2026-05-17T23:40:03.284792+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KI3BRD2MIKH","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KI3BRD2MIKHV7LW","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KI3BRD2","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09292","citing_title":"Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4KI3BRD2MIKHV7LWRDBW3IRXQ5","json":"https://pith.science/pith/4KI3BRD2MIKHV7LWRDBW3IRXQ5.json","graph_json":"https://pith.science/api/pith-number/4KI3BRD2MIKHV7LWRDBW3IRXQ5/graph.json","events_json":"https://pith.science/api/pith-number/4KI3BRD2MIKHV7LWRDBW3IRXQ5/events.json","paper":"https://pith.science/paper/4KI3BRD2"},"agent_actions":{"view_html":"https://pith.science/pith/4KI3BRD2MIKHV7LWRDBW3IRXQ5","download_json":"https://pith.science/pith/4KI3BRD2MIKHV7LWRDBW3IRXQ5.json","view_paper":"https://pith.science/paper/4KI3BRD2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.09292&json=true","fetch_graph":"https://pith.science/api/pith-number/4KI3BRD2MIKHV7LWRDBW3IRXQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/4KI3BRD2MIKHV7LWRDBW3IRXQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KI3BRD2MIKHV7LWRDBW3IRXQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KI3BRD2MIKHV7LWRDBW3IRXQ5/action/storage_attestation","attest_author":"https://pith.science/pith/4KI3BRD2MIKHV7LWRDBW3IRXQ5/action/author_attestation","sign_citation":"https://pith.science/pith/4KI3BRD2MIKHV7LWRDBW3IRXQ5/action/citation_signature","submit_replication":"https://pith.science/pith/4KI3BRD2MIKHV7LWRDBW3IRXQ5/action/replication_record"}},"created_at":"2026-05-17T23:40:03.284792+00:00","updated_at":"2026-05-17T23:40:03.284792+00:00"}