{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TVC5IAIR3XYYCIBIRHWXJ7VBO3","short_pith_number":"pith:TVC5IAIR","schema_version":"1.0","canonical_sha256":"9d45d40111ddf181202889ed74fea176f14ee1b6ed6416d4a7267975fe2f0fdd","source":{"kind":"arxiv","id":"1904.02147","version":1},"attestation_state":"computed","paper":{"title":"Learning Shared Encoding Representation for End-to-End Speech Recognition Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alex Waibel, Sebastian Stueker, Thai-Son Nguyen","submitted_at":"2019-03-31T20:46:13Z","abstract_excerpt":"In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria. Our experiments show that the multi-task training not only tackles the complexity of optimizing CTC models such as acoustic-to-word but also results in significant improvement compared to the plain-task training with an optimal setup. Furthermore, we propose to use the encoding representation learned by the multi-task network to initialize the encoder of attention-based models. Thereb"},"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":"1904.02147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-03-31T20:46:13Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"99002373941e3596a6bd0d84eb8fef77bcc2957a98aa121ec7b63a7387b2382f","abstract_canon_sha256":"1ede85c591410d544f7e2b9472b44af54eada8c89cd875475fb566e985b72dae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:28.375854Z","signature_b64":"a+OtR+p3IoPV0pztDnhdVpAeNSNT9p6LY+GeztVvhabOT4f8bDQijSCY0LoLtz12Jxxr8Bn7NHAwpW22Ob0vCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d45d40111ddf181202889ed74fea176f14ee1b6ed6416d4a7267975fe2f0fdd","last_reissued_at":"2026-05-17T23:49:28.375135Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:28.375135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Shared Encoding Representation for End-to-End Speech Recognition Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alex Waibel, Sebastian Stueker, Thai-Son Nguyen","submitted_at":"2019-03-31T20:46:13Z","abstract_excerpt":"In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria. Our experiments show that the multi-task training not only tackles the complexity of optimizing CTC models such as acoustic-to-word but also results in significant improvement compared to the plain-task training with an optimal setup. Furthermore, we propose to use the encoding representation learned by the multi-task network to initialize the encoder of attention-based models. Thereb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02147","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":"1904.02147","created_at":"2026-05-17T23:49:28.375247+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02147v1","created_at":"2026-05-17T23:49:28.375247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02147","created_at":"2026-05-17T23:49:28.375247+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVC5IAIR3XYY","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVC5IAIR3XYYCIBI","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVC5IAIR","created_at":"2026-05-18T12:33:30.264802+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/TVC5IAIR3XYYCIBIRHWXJ7VBO3","json":"https://pith.science/pith/TVC5IAIR3XYYCIBIRHWXJ7VBO3.json","graph_json":"https://pith.science/api/pith-number/TVC5IAIR3XYYCIBIRHWXJ7VBO3/graph.json","events_json":"https://pith.science/api/pith-number/TVC5IAIR3XYYCIBIRHWXJ7VBO3/events.json","paper":"https://pith.science/paper/TVC5IAIR"},"agent_actions":{"view_html":"https://pith.science/pith/TVC5IAIR3XYYCIBIRHWXJ7VBO3","download_json":"https://pith.science/pith/TVC5IAIR3XYYCIBIRHWXJ7VBO3.json","view_paper":"https://pith.science/paper/TVC5IAIR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02147&json=true","fetch_graph":"https://pith.science/api/pith-number/TVC5IAIR3XYYCIBIRHWXJ7VBO3/graph.json","fetch_events":"https://pith.science/api/pith-number/TVC5IAIR3XYYCIBIRHWXJ7VBO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVC5IAIR3XYYCIBIRHWXJ7VBO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVC5IAIR3XYYCIBIRHWXJ7VBO3/action/storage_attestation","attest_author":"https://pith.science/pith/TVC5IAIR3XYYCIBIRHWXJ7VBO3/action/author_attestation","sign_citation":"https://pith.science/pith/TVC5IAIR3XYYCIBIRHWXJ7VBO3/action/citation_signature","submit_replication":"https://pith.science/pith/TVC5IAIR3XYYCIBIRHWXJ7VBO3/action/replication_record"}},"created_at":"2026-05-17T23:49:28.375247+00:00","updated_at":"2026-05-17T23:49:28.375247+00:00"}