{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WTYZ3PIEMI5IGXJKWN7X5TZIPL","short_pith_number":"pith:WTYZ3PIE","schema_version":"1.0","canonical_sha256":"b4f19dbd04623a835d2ab37f7ecf287af3e24bb49a4fad38c27b7f1c7e62d278","source":{"kind":"arxiv","id":"1807.09597","version":2},"attestation_state":"computed","paper":{"title":"Acoustic-to-Word Recognition with Sequence-to-Sequence Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Florian Metze, Shruti Palaskar","submitted_at":"2018-07-23T06:29:43Z","abstract_excerpt":"Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the out-of-vocabulary problem, word models can be simpler to decode and may also be able to directly recognize semantically meaningful units. We present effective methods to train Sequence-to-Sequence models for direct word-level recognition (and character-level recognition) and show an absolute improvement of 4.4-5.0\\% in Word Error Rate on the Switchboard corpus compa"},"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":"1807.09597","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-07-23T06:29:43Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"4ee30725c2dafa5c262e29e8b74eade6e5ceb156887bea0db3f9ba07f5ba2bdf","abstract_canon_sha256":"1e0b734953dba606bebd0f513a5d123ff71f9a54b1bb8103c70705a1da36b33c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:40.029961Z","signature_b64":"1eu7gnA7E8Zd2AJI/SF4W0kjSv3G0bQGQQga1ucNpqTlNLRJZiYLvUrK4s1806ZwBjd/zEYPzBJU/kcUViItBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4f19dbd04623a835d2ab37f7ecf287af3e24bb49a4fad38c27b7f1c7e62d278","last_reissued_at":"2026-05-18T00:07:40.029240Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:40.029240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Acoustic-to-Word Recognition with Sequence-to-Sequence Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Florian Metze, Shruti Palaskar","submitted_at":"2018-07-23T06:29:43Z","abstract_excerpt":"Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the out-of-vocabulary problem, word models can be simpler to decode and may also be able to directly recognize semantically meaningful units. We present effective methods to train Sequence-to-Sequence models for direct word-level recognition (and character-level recognition) and show an absolute improvement of 4.4-5.0\\% in Word Error Rate on the Switchboard corpus compa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09597","kind":"arxiv","version":2},"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":"1807.09597","created_at":"2026-05-18T00:07:40.029351+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.09597v2","created_at":"2026-05-18T00:07:40.029351+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09597","created_at":"2026-05-18T00:07:40.029351+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTYZ3PIEMI5I","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTYZ3PIEMI5IGXJK","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTYZ3PIE","created_at":"2026-05-18T12:33:01.666342+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/WTYZ3PIEMI5IGXJKWN7X5TZIPL","json":"https://pith.science/pith/WTYZ3PIEMI5IGXJKWN7X5TZIPL.json","graph_json":"https://pith.science/api/pith-number/WTYZ3PIEMI5IGXJKWN7X5TZIPL/graph.json","events_json":"https://pith.science/api/pith-number/WTYZ3PIEMI5IGXJKWN7X5TZIPL/events.json","paper":"https://pith.science/paper/WTYZ3PIE"},"agent_actions":{"view_html":"https://pith.science/pith/WTYZ3PIEMI5IGXJKWN7X5TZIPL","download_json":"https://pith.science/pith/WTYZ3PIEMI5IGXJKWN7X5TZIPL.json","view_paper":"https://pith.science/paper/WTYZ3PIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.09597&json=true","fetch_graph":"https://pith.science/api/pith-number/WTYZ3PIEMI5IGXJKWN7X5TZIPL/graph.json","fetch_events":"https://pith.science/api/pith-number/WTYZ3PIEMI5IGXJKWN7X5TZIPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTYZ3PIEMI5IGXJKWN7X5TZIPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTYZ3PIEMI5IGXJKWN7X5TZIPL/action/storage_attestation","attest_author":"https://pith.science/pith/WTYZ3PIEMI5IGXJKWN7X5TZIPL/action/author_attestation","sign_citation":"https://pith.science/pith/WTYZ3PIEMI5IGXJKWN7X5TZIPL/action/citation_signature","submit_replication":"https://pith.science/pith/WTYZ3PIEMI5IGXJKWN7X5TZIPL/action/replication_record"}},"created_at":"2026-05-18T00:07:40.029351+00:00","updated_at":"2026-05-18T00:07:40.029351+00:00"}