{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6FMJS3RVBGQUS2PSCYYKMLDSQR","short_pith_number":"pith:6FMJS3RV","schema_version":"1.0","canonical_sha256":"f158996e3509a14969f21630a62c72847668bf831351171c2c2acb8fa288c545","source":{"kind":"arxiv","id":"1812.02308","version":1},"attestation_state":"computed","paper":{"title":"On the Inductive Bias of Word-Character-Level Multi-Task Learning for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Jan Kremer, Lars Maal{\\o}e, Lasse Borgholt","submitted_at":"2018-11-28T10:37:24Z","abstract_excerpt":"End-to-end automatic speech recognition (ASR) commonly transcribes audio signals into sequences of characters while its performance is evaluated by measuring the word-error rate (WER). This suggests that predicting sequences of words directly may be helpful instead. However, training with word-level supervision can be more difficult due to the sparsity of examples per label class. In this paper we analyze an end-to-end ASR model that combines a word-and-character representation in a multi-task learning (MTL) framework. We show that it improves on the WER and study how the word-level model can "},"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":"1812.02308","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-28T10:37:24Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f7b8c22f9c7057f4efd6a23480cadd5f6d0cbfd5ba1fd55a6f02ae3935ff81b8","abstract_canon_sha256":"feb403a1e97f436ae9dbc89f3038c29b8f206785039a2a9816dd73dd187fe2d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:56.628545Z","signature_b64":"NHiuFIB7Z6iQG9yIL9y7HHcoW3eOSw2MZu9YucINJo60jvrXaUcSsy1WZEWjAGauW7God6TGSWfCEGqTsZJQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f158996e3509a14969f21630a62c72847668bf831351171c2c2acb8fa288c545","last_reissued_at":"2026-05-17T23:58:56.628115Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:56.628115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Inductive Bias of Word-Character-Level Multi-Task Learning for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Jan Kremer, Lars Maal{\\o}e, Lasse Borgholt","submitted_at":"2018-11-28T10:37:24Z","abstract_excerpt":"End-to-end automatic speech recognition (ASR) commonly transcribes audio signals into sequences of characters while its performance is evaluated by measuring the word-error rate (WER). This suggests that predicting sequences of words directly may be helpful instead. However, training with word-level supervision can be more difficult due to the sparsity of examples per label class. In this paper we analyze an end-to-end ASR model that combines a word-and-character representation in a multi-task learning (MTL) framework. We show that it improves on the WER and study how the word-level model can "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02308","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":"1812.02308","created_at":"2026-05-17T23:58:56.628181+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.02308v1","created_at":"2026-05-17T23:58:56.628181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02308","created_at":"2026-05-17T23:58:56.628181+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FMJS3RVBGQU","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FMJS3RVBGQUS2PS","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FMJS3RV","created_at":"2026-05-18T12:32:08.215937+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/6FMJS3RVBGQUS2PSCYYKMLDSQR","json":"https://pith.science/pith/6FMJS3RVBGQUS2PSCYYKMLDSQR.json","graph_json":"https://pith.science/api/pith-number/6FMJS3RVBGQUS2PSCYYKMLDSQR/graph.json","events_json":"https://pith.science/api/pith-number/6FMJS3RVBGQUS2PSCYYKMLDSQR/events.json","paper":"https://pith.science/paper/6FMJS3RV"},"agent_actions":{"view_html":"https://pith.science/pith/6FMJS3RVBGQUS2PSCYYKMLDSQR","download_json":"https://pith.science/pith/6FMJS3RVBGQUS2PSCYYKMLDSQR.json","view_paper":"https://pith.science/paper/6FMJS3RV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.02308&json=true","fetch_graph":"https://pith.science/api/pith-number/6FMJS3RVBGQUS2PSCYYKMLDSQR/graph.json","fetch_events":"https://pith.science/api/pith-number/6FMJS3RVBGQUS2PSCYYKMLDSQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FMJS3RVBGQUS2PSCYYKMLDSQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FMJS3RVBGQUS2PSCYYKMLDSQR/action/storage_attestation","attest_author":"https://pith.science/pith/6FMJS3RVBGQUS2PSCYYKMLDSQR/action/author_attestation","sign_citation":"https://pith.science/pith/6FMJS3RVBGQUS2PSCYYKMLDSQR/action/citation_signature","submit_replication":"https://pith.science/pith/6FMJS3RVBGQUS2PSCYYKMLDSQR/action/replication_record"}},"created_at":"2026-05-17T23:58:56.628181+00:00","updated_at":"2026-05-17T23:58:56.628181+00:00"}