{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BW5XSFWW3LG3T3Z7YL2ER7LSV3","short_pith_number":"pith:BW5XSFWW","schema_version":"1.0","canonical_sha256":"0dbb7916d6dacdb9ef3fc2f448fd72aec2fa8c6a4435d9c5df3524edb76c2ce4","source":{"kind":"arxiv","id":"1701.02720","version":1},"attestation_state":"computed","paper":{"title":"Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Aaron Courville, Cesar Laurent Yoshua Bengio, Mohammad Pezeshki, Philemon Brakel, Saizheng Zhang, Ying Zhang","submitted_at":"2017-01-10T18:30:11Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs with Hidden Markov Models/Gaussian Mixture Models (HMMs/GMMs) have achieved the state-of-the-art in various benchmarks. Meanwhile, Connectionist Temporal Classification (CTC) with Recurrent Neural Networks (RNNs), which is proposed for labeling unsegmented sequences, makes it feasible to train an end-to-end speech recognition system instead of hybrid setting"},"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":"1701.02720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-10T18:30:11Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"98b579251ee164f3be33f56310a9cbe09e9e17d334d2a15ef1959bb93d47f60d","abstract_canon_sha256":"8e2b2d281b6cb9f0078e4cd97c600084a64c5dbe227dbf2abe933493852d6eaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:03.578220Z","signature_b64":"B/MsufoJlv04izEj78khPfh1LJvs+i3430bjkjJDLVrV6J18KnLmw2JE+d15BtjRdjtpg5Je/u0YyTJ7hazoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dbb7916d6dacdb9ef3fc2f448fd72aec2fa8c6a4435d9c5df3524edb76c2ce4","last_reissued_at":"2026-05-18T00:53:03.577755Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:03.577755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Aaron Courville, Cesar Laurent Yoshua Bengio, Mohammad Pezeshki, Philemon Brakel, Saizheng Zhang, Ying Zhang","submitted_at":"2017-01-10T18:30:11Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs with Hidden Markov Models/Gaussian Mixture Models (HMMs/GMMs) have achieved the state-of-the-art in various benchmarks. Meanwhile, Connectionist Temporal Classification (CTC) with Recurrent Neural Networks (RNNs), which is proposed for labeling unsegmented sequences, makes it feasible to train an end-to-end speech recognition system instead of hybrid setting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.02720","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":"1701.02720","created_at":"2026-05-18T00:53:03.577824+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.02720v1","created_at":"2026-05-18T00:53:03.577824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.02720","created_at":"2026-05-18T00:53:03.577824+00:00"},{"alias_kind":"pith_short_12","alias_value":"BW5XSFWW3LG3","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BW5XSFWW3LG3T3Z7","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BW5XSFWW","created_at":"2026-05-18T12:31:08.081275+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":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BW5XSFWW3LG3T3Z7YL2ER7LSV3","json":"https://pith.science/pith/BW5XSFWW3LG3T3Z7YL2ER7LSV3.json","graph_json":"https://pith.science/api/pith-number/BW5XSFWW3LG3T3Z7YL2ER7LSV3/graph.json","events_json":"https://pith.science/api/pith-number/BW5XSFWW3LG3T3Z7YL2ER7LSV3/events.json","paper":"https://pith.science/paper/BW5XSFWW"},"agent_actions":{"view_html":"https://pith.science/pith/BW5XSFWW3LG3T3Z7YL2ER7LSV3","download_json":"https://pith.science/pith/BW5XSFWW3LG3T3Z7YL2ER7LSV3.json","view_paper":"https://pith.science/paper/BW5XSFWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.02720&json=true","fetch_graph":"https://pith.science/api/pith-number/BW5XSFWW3LG3T3Z7YL2ER7LSV3/graph.json","fetch_events":"https://pith.science/api/pith-number/BW5XSFWW3LG3T3Z7YL2ER7LSV3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BW5XSFWW3LG3T3Z7YL2ER7LSV3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BW5XSFWW3LG3T3Z7YL2ER7LSV3/action/storage_attestation","attest_author":"https://pith.science/pith/BW5XSFWW3LG3T3Z7YL2ER7LSV3/action/author_attestation","sign_citation":"https://pith.science/pith/BW5XSFWW3LG3T3Z7YL2ER7LSV3/action/citation_signature","submit_replication":"https://pith.science/pith/BW5XSFWW3LG3T3Z7YL2ER7LSV3/action/replication_record"}},"created_at":"2026-05-18T00:53:03.577824+00:00","updated_at":"2026-05-18T00:53:03.577824+00:00"}