{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:P722CFBFI4PQZN4Y5FTVJBK7AS","short_pith_number":"pith:P722CFBF","schema_version":"1.0","canonical_sha256":"7ff5a11425471f0cb798e96754855f04a8ba0f676dcec955f257af3de0fab971","source":{"kind":"arxiv","id":"1902.01951","version":2},"attestation_state":"computed","paper":{"title":"Using multi-task learning to improve the performance of acoustic-to-word and conventional hybrid 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":"Alex Waibel, Sebastian Stueker, Thai-Son Nguyen","submitted_at":"2019-02-02T07:33:48Z","abstract_excerpt":"Acoustic-to-word (A2W) models that allow direct mapping from acoustic signals to word sequences are an appealing approach to end-to-end automatic speech recognition due to their simplicity. However, prior works have shown that modelling A2W typically encounters issues of data sparsity that prevent training such a model directly. So far, pre-training initialization is the only approach proposed to deal with this issue. In this work, we propose to build a shared neural network and optimize A2W and conventional hybrid models in a multi-task manner. Our results show that training an A2W model is m"},"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":"1902.01951","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-02-02T07:33:48Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"d726730e27c5213b6cf09ff6dc6f0f2aa6b3ed553fd10146fabdc645e2081cf5","abstract_canon_sha256":"4a00052a5622436736fd3e1e497a7e1965104c1ba5689280efe9dfdf0f7b4aa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:03.524162Z","signature_b64":"EthVALLtIDv/p1lcfh8K663TdxHQRxrX5tQoboShjbAuz9qmCcX8M9FbfynDX6C9PK7dTGqiqLkTmLnEo50zCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ff5a11425471f0cb798e96754855f04a8ba0f676dcec955f257af3de0fab971","last_reissued_at":"2026-05-17T23:46:03.523453Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:03.523453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using multi-task learning to improve the performance of acoustic-to-word and conventional hybrid 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":"Alex Waibel, Sebastian Stueker, Thai-Son Nguyen","submitted_at":"2019-02-02T07:33:48Z","abstract_excerpt":"Acoustic-to-word (A2W) models that allow direct mapping from acoustic signals to word sequences are an appealing approach to end-to-end automatic speech recognition due to their simplicity. However, prior works have shown that modelling A2W typically encounters issues of data sparsity that prevent training such a model directly. So far, pre-training initialization is the only approach proposed to deal with this issue. In this work, we propose to build a shared neural network and optimize A2W and conventional hybrid models in a multi-task manner. Our results show that training an A2W model is m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01951","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":"1902.01951","created_at":"2026-05-17T23:46:03.523571+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.01951v2","created_at":"2026-05-17T23:46:03.523571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01951","created_at":"2026-05-17T23:46:03.523571+00:00"},{"alias_kind":"pith_short_12","alias_value":"P722CFBFI4PQ","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"P722CFBFI4PQZN4Y","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"P722CFBF","created_at":"2026-05-18T12:33:24.271573+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/P722CFBFI4PQZN4Y5FTVJBK7AS","json":"https://pith.science/pith/P722CFBFI4PQZN4Y5FTVJBK7AS.json","graph_json":"https://pith.science/api/pith-number/P722CFBFI4PQZN4Y5FTVJBK7AS/graph.json","events_json":"https://pith.science/api/pith-number/P722CFBFI4PQZN4Y5FTVJBK7AS/events.json","paper":"https://pith.science/paper/P722CFBF"},"agent_actions":{"view_html":"https://pith.science/pith/P722CFBFI4PQZN4Y5FTVJBK7AS","download_json":"https://pith.science/pith/P722CFBFI4PQZN4Y5FTVJBK7AS.json","view_paper":"https://pith.science/paper/P722CFBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.01951&json=true","fetch_graph":"https://pith.science/api/pith-number/P722CFBFI4PQZN4Y5FTVJBK7AS/graph.json","fetch_events":"https://pith.science/api/pith-number/P722CFBFI4PQZN4Y5FTVJBK7AS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P722CFBFI4PQZN4Y5FTVJBK7AS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P722CFBFI4PQZN4Y5FTVJBK7AS/action/storage_attestation","attest_author":"https://pith.science/pith/P722CFBFI4PQZN4Y5FTVJBK7AS/action/author_attestation","sign_citation":"https://pith.science/pith/P722CFBFI4PQZN4Y5FTVJBK7AS/action/citation_signature","submit_replication":"https://pith.science/pith/P722CFBFI4PQZN4Y5FTVJBK7AS/action/replication_record"}},"created_at":"2026-05-17T23:46:03.523571+00:00","updated_at":"2026-05-17T23:46:03.523571+00:00"}