{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:E2S7EF6WTM3WL3MBRWRMJLANJU","short_pith_number":"pith:E2S7EF6W","schema_version":"1.0","canonical_sha256":"26a5f217d69b3765ed818da2c4ac0d4d30b2a847b1199d11f1afeed257212d3b","source":{"kind":"arxiv","id":"1712.09444","version":2},"attestation_state":"computed","paper":{"title":"Letter-Based Speech Recognition with Gated ConvNets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gabriel Synnaeve, Ronan Collobert, Vitaliy Liptchinsky","submitted_at":"2017-12-22T17:42:15Z","abstract_excerpt":"In the recent literature, \"end-to-end\" speech systems often refer to letter-based acoustic models trained in a sequence-to-sequence manner, either via a recurrent model or via a structured output learning approach (such as CTC). In contrast to traditional phone (or senone)-based approaches, these \"end-to-end'' approaches alleviate the need of word pronunciation modeling, and do not require a \"forced alignment\" step at training time. Phone-based approaches remain however state of the art on classical benchmarks. In this paper, we propose a letter-based speech recognition system, leveraging a Co"},"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":"1712.09444","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-22T17:42:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5d0793a49ceadf95353a016f82315f14d4270b831b2519cce8de9dc536bcea1","abstract_canon_sha256":"de40a7b16e1bb4bc1de103584f197cf1f2bea93ff5e4e402c5901b52aeb95f5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:51.859285Z","signature_b64":"Osk7mBgQaEshRC5KlIzyY/v3r/gKJXVebfUG0FvwB8y7mJOfyZ9v+jgpQAuu6MdRd0Ns9PMDGp4CXy7AOMChCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26a5f217d69b3765ed818da2c4ac0d4d30b2a847b1199d11f1afeed257212d3b","last_reissued_at":"2026-05-17T23:53:51.858636Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:51.858636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Letter-Based Speech Recognition with Gated ConvNets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gabriel Synnaeve, Ronan Collobert, Vitaliy Liptchinsky","submitted_at":"2017-12-22T17:42:15Z","abstract_excerpt":"In the recent literature, \"end-to-end\" speech systems often refer to letter-based acoustic models trained in a sequence-to-sequence manner, either via a recurrent model or via a structured output learning approach (such as CTC). In contrast to traditional phone (or senone)-based approaches, these \"end-to-end'' approaches alleviate the need of word pronunciation modeling, and do not require a \"forced alignment\" step at training time. Phone-based approaches remain however state of the art on classical benchmarks. In this paper, we propose a letter-based speech recognition system, leveraging a Co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09444","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":"1712.09444","created_at":"2026-05-17T23:53:51.858728+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09444v2","created_at":"2026-05-17T23:53:51.858728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09444","created_at":"2026-05-17T23:53:51.858728+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2S7EF6WTM3W","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2S7EF6WTM3WL3MB","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2S7EF6W","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09426","citing_title":"End-to-End ASR for Code-switched Hindi-English Speech","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2S7EF6WTM3WL3MBRWRMJLANJU","json":"https://pith.science/pith/E2S7EF6WTM3WL3MBRWRMJLANJU.json","graph_json":"https://pith.science/api/pith-number/E2S7EF6WTM3WL3MBRWRMJLANJU/graph.json","events_json":"https://pith.science/api/pith-number/E2S7EF6WTM3WL3MBRWRMJLANJU/events.json","paper":"https://pith.science/paper/E2S7EF6W"},"agent_actions":{"view_html":"https://pith.science/pith/E2S7EF6WTM3WL3MBRWRMJLANJU","download_json":"https://pith.science/pith/E2S7EF6WTM3WL3MBRWRMJLANJU.json","view_paper":"https://pith.science/paper/E2S7EF6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09444&json=true","fetch_graph":"https://pith.science/api/pith-number/E2S7EF6WTM3WL3MBRWRMJLANJU/graph.json","fetch_events":"https://pith.science/api/pith-number/E2S7EF6WTM3WL3MBRWRMJLANJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2S7EF6WTM3WL3MBRWRMJLANJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2S7EF6WTM3WL3MBRWRMJLANJU/action/storage_attestation","attest_author":"https://pith.science/pith/E2S7EF6WTM3WL3MBRWRMJLANJU/action/author_attestation","sign_citation":"https://pith.science/pith/E2S7EF6WTM3WL3MBRWRMJLANJU/action/citation_signature","submit_replication":"https://pith.science/pith/E2S7EF6WTM3WL3MBRWRMJLANJU/action/replication_record"}},"created_at":"2026-05-17T23:53:51.858728+00:00","updated_at":"2026-05-17T23:53:51.858728+00:00"}