{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XWJDO62OUQTR5E7KM54PLBNIJ4","short_pith_number":"pith:XWJDO62O","schema_version":"1.0","canonical_sha256":"bd92377b4ea4271e93ea6778f585a84f20291ddfd3ca2d6233f1d6fb733bc105","source":{"kind":"arxiv","id":"1904.02619","version":1},"attestation_state":"computed","paper":{"title":"Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ann Lee, Awni Hannun, Qiantong Xu, Ronan Collobert","submitted_at":"2019-04-04T15:44:39Z","abstract_excerpt":"We propose a fully convolutional sequence-to-sequence encoder architecture with a simple and efficient decoder. Our model improves WER on LibriSpeech while being an order of magnitude more efficient than a strong RNN baseline. Key to our approach is a time-depth separable convolution block which dramatically reduces the number of parameters in the model while keeping the receptive field large. We also give a stable and efficient beam search inference procedure which allows us to effectively integrate a language model. Coupled with a convolutional language model, our time-depth separable convol"},"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":"1904.02619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-04T15:44:39Z","cross_cats_sorted":[],"title_canon_sha256":"a9e74f8d80e3ff6b9eb4153ff1b90250d830d011cdcc0b28bbaaee9f4a56b8ef","abstract_canon_sha256":"f1dd36b73ca1ec587678b0fe7585af25d10a447f675587c0032774055dd65c16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:23.171418Z","signature_b64":"y3ox5TIVtDh2BKG+gA3Nh4rAcWwIspHWJsBu62M5+SFDx5+3UCTHkG3bi/1vsadVElBEoRh0dDen964FIBlgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd92377b4ea4271e93ea6778f585a84f20291ddfd3ca2d6233f1d6fb733bc105","last_reissued_at":"2026-05-17T23:49:23.170945Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:23.170945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ann Lee, Awni Hannun, Qiantong Xu, Ronan Collobert","submitted_at":"2019-04-04T15:44:39Z","abstract_excerpt":"We propose a fully convolutional sequence-to-sequence encoder architecture with a simple and efficient decoder. Our model improves WER on LibriSpeech while being an order of magnitude more efficient than a strong RNN baseline. Key to our approach is a time-depth separable convolution block which dramatically reduces the number of parameters in the model while keeping the receptive field large. We also give a stable and efficient beam search inference procedure which allows us to effectively integrate a language model. Coupled with a convolutional language model, our time-depth separable convol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02619","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":"1904.02619","created_at":"2026-05-17T23:49:23.171011+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02619v1","created_at":"2026-05-17T23:49:23.171011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02619","created_at":"2026-05-17T23:49:23.171011+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWJDO62OUQTR","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWJDO62OUQTR5E7K","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWJDO62O","created_at":"2026-05-18T12:33:33.725879+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/XWJDO62OUQTR5E7KM54PLBNIJ4","json":"https://pith.science/pith/XWJDO62OUQTR5E7KM54PLBNIJ4.json","graph_json":"https://pith.science/api/pith-number/XWJDO62OUQTR5E7KM54PLBNIJ4/graph.json","events_json":"https://pith.science/api/pith-number/XWJDO62OUQTR5E7KM54PLBNIJ4/events.json","paper":"https://pith.science/paper/XWJDO62O"},"agent_actions":{"view_html":"https://pith.science/pith/XWJDO62OUQTR5E7KM54PLBNIJ4","download_json":"https://pith.science/pith/XWJDO62OUQTR5E7KM54PLBNIJ4.json","view_paper":"https://pith.science/paper/XWJDO62O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02619&json=true","fetch_graph":"https://pith.science/api/pith-number/XWJDO62OUQTR5E7KM54PLBNIJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/XWJDO62OUQTR5E7KM54PLBNIJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWJDO62OUQTR5E7KM54PLBNIJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWJDO62OUQTR5E7KM54PLBNIJ4/action/storage_attestation","attest_author":"https://pith.science/pith/XWJDO62OUQTR5E7KM54PLBNIJ4/action/author_attestation","sign_citation":"https://pith.science/pith/XWJDO62OUQTR5E7KM54PLBNIJ4/action/citation_signature","submit_replication":"https://pith.science/pith/XWJDO62OUQTR5E7KM54PLBNIJ4/action/replication_record"}},"created_at":"2026-05-17T23:49:23.171011+00:00","updated_at":"2026-05-17T23:49:23.171011+00:00"}