{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:JEEN3JXLIUYUMDH3VVPJ5LCAEP","short_pith_number":"pith:JEEN3JXL","schema_version":"1.0","canonical_sha256":"4908dda6eb4531460cfbad5e9eac4023f2aa46a352634ce721f8f491e624486e","source":{"kind":"arxiv","id":"1412.5567","version":2},"attestation_state":"computed","paper":{"title":"Deep Speech: Scaling up end-to-end speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Adam Coates, Andrew Y. Ng, Awni Hannun, Bryan Catanzaro, Carl Case, Erich Elsen, Greg Diamos, Jared Casper, Ryan Prenger, Sanjeev Satheesh, Shubho Sengupta","submitted_at":"2014-12-17T20:39:45Z","abstract_excerpt":"We present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, our system does not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learns a function that is robust to such effects. We do not need a phoneme dictionary, nor even the concept of a \"phoneme.\" Key to ou"},"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":"1412.5567","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-12-17T20:39:45Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"047f011461634c57b8287f2025c6164a153661646f98754de8b5ea1fd2011712","abstract_canon_sha256":"4baf4a7f3f3d38d7b7386f1ee58e6f23c6006cb58f4300a552220fce30c8151a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:30:46.682556Z","signature_b64":"PGw0pLl+xJtG3PfPid4I3F+lRN+jfQp+4CxO1NSfJh/6JY7NtXb1fe5t2OGxCjPboKD3oIc8SkfqvSr3TOqWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4908dda6eb4531460cfbad5e9eac4023f2aa46a352634ce721f8f491e624486e","last_reissued_at":"2026-05-18T02:30:46.682127Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:30:46.682127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Speech: Scaling up end-to-end speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Adam Coates, Andrew Y. Ng, Awni Hannun, Bryan Catanzaro, Carl Case, Erich Elsen, Greg Diamos, Jared Casper, Ryan Prenger, Sanjeev Satheesh, Shubho Sengupta","submitted_at":"2014-12-17T20:39:45Z","abstract_excerpt":"We present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, our system does not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learns a function that is robust to such effects. We do not need a phoneme dictionary, nor even the concept of a \"phoneme.\" Key to ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.5567","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":"1412.5567","created_at":"2026-05-18T02:30:46.682184+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.5567v2","created_at":"2026-05-18T02:30:46.682184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.5567","created_at":"2026-05-18T02:30:46.682184+00:00"},{"alias_kind":"pith_short_12","alias_value":"JEEN3JXLIUYU","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_16","alias_value":"JEEN3JXLIUYUMDH3","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_8","alias_value":"JEEN3JXL","created_at":"2026-05-18T12:28:33.132498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"1906.11604","citing_title":"Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02479","citing_title":"Fine-grained robust prosody transfer for single-speaker neural text-to-speech","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2309.12802","citing_title":"Deepfake audio as a data augmentation technique for training automatic speech to text transcription models","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2508.18948","citing_title":"Gauge-covariant stochastic neural fields: Stability and finite-width effects","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2510.03093","citing_title":"Revisiting Direct Speech-to-Text Translation with Speech LLMs: Better Scaling than CoT Prompting?","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2402.13228","citing_title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","ref_index":239,"is_internal_anchor":true},{"citing_arxiv_id":"2601.17097","citing_title":"Sink or SWIM: Tackling Real-Time ASR at Scale","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"1710.03740","citing_title":"Mixed Precision Training","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"1712.00409","citing_title":"Deep Learning Scaling is Predictable, Empirically","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08405","citing_title":"SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20842","citing_title":"SpeechParaling-Bench: A Comprehensive Benchmark for Paralinguistic-Aware Speech Generation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JEEN3JXLIUYUMDH3VVPJ5LCAEP","json":"https://pith.science/pith/JEEN3JXLIUYUMDH3VVPJ5LCAEP.json","graph_json":"https://pith.science/api/pith-number/JEEN3JXLIUYUMDH3VVPJ5LCAEP/graph.json","events_json":"https://pith.science/api/pith-number/JEEN3JXLIUYUMDH3VVPJ5LCAEP/events.json","paper":"https://pith.science/paper/JEEN3JXL"},"agent_actions":{"view_html":"https://pith.science/pith/JEEN3JXLIUYUMDH3VVPJ5LCAEP","download_json":"https://pith.science/pith/JEEN3JXLIUYUMDH3VVPJ5LCAEP.json","view_paper":"https://pith.science/paper/JEEN3JXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.5567&json=true","fetch_graph":"https://pith.science/api/pith-number/JEEN3JXLIUYUMDH3VVPJ5LCAEP/graph.json","fetch_events":"https://pith.science/api/pith-number/JEEN3JXLIUYUMDH3VVPJ5LCAEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JEEN3JXLIUYUMDH3VVPJ5LCAEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JEEN3JXLIUYUMDH3VVPJ5LCAEP/action/storage_attestation","attest_author":"https://pith.science/pith/JEEN3JXLIUYUMDH3VVPJ5LCAEP/action/author_attestation","sign_citation":"https://pith.science/pith/JEEN3JXLIUYUMDH3VVPJ5LCAEP/action/citation_signature","submit_replication":"https://pith.science/pith/JEEN3JXLIUYUMDH3VVPJ5LCAEP/action/replication_record"}},"created_at":"2026-05-18T02:30:46.682184+00:00","updated_at":"2026-05-18T02:30:46.682184+00:00"}