{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:JJ4IBUSFG7ROX3YDHDT2NZGXL4","short_pith_number":"pith:JJ4IBUSF","schema_version":"1.0","canonical_sha256":"4a7880d24537e2ebef0338e7a6e4d75f0dc28fa5bf4a1c97d614904320d04a81","source":{"kind":"arxiv","id":"1508.01211","version":2},"attestation_state":"computed","paper":{"title":"Listen, Attend and Spell","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CL","authors_text":"Navdeep Jaitly, Oriol Vinyals, Quoc V. Le, William Chan","submitted_at":"2015-08-05T20:17:58Z","abstract_excerpt":"We present Listen, Attend and Spell (LAS), a neural network that learns to transcribe speech utterances to characters. Unlike traditional DNN-HMM models, this model learns all the components of a speech recognizer jointly. Our system has two components: a listener and a speller. The listener is a pyramidal recurrent network encoder that accepts filter bank spectra as inputs. The speller is an attention-based recurrent network decoder that emits characters as outputs. The network produces character sequences without making any independence assumptions between the characters. This is the key imp"},"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":"1508.01211","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-05T20:17:58Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"dd79e17cec79e12d6982812ad57e2f34e46a132c4008f6aa226e742036c6bd3d","abstract_canon_sha256":"bbd96463902cc9f2305e044b87f1cb7d23eac68a6b80ca26f8b48bf387f4ba0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:01.615957Z","signature_b64":"8YiOXTtCaU4VqA497S3VAh6FVJNW7BWZhDJmPWTdQsUDxwe90pNSTZMhKKXecDmBpViqa5Itfq6yQlu62SnuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a7880d24537e2ebef0338e7a6e4d75f0dc28fa5bf4a1c97d614904320d04a81","last_reissued_at":"2026-05-18T01:35:01.615323Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:01.615323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Listen, Attend and Spell","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CL","authors_text":"Navdeep Jaitly, Oriol Vinyals, Quoc V. Le, William Chan","submitted_at":"2015-08-05T20:17:58Z","abstract_excerpt":"We present Listen, Attend and Spell (LAS), a neural network that learns to transcribe speech utterances to characters. Unlike traditional DNN-HMM models, this model learns all the components of a speech recognizer jointly. Our system has two components: a listener and a speller. The listener is a pyramidal recurrent network encoder that accepts filter bank spectra as inputs. The speller is an attention-based recurrent network decoder that emits characters as outputs. The network produces character sequences without making any independence assumptions between the characters. This is the key imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.01211","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":"1508.01211","created_at":"2026-05-18T01:35:01.615416+00:00"},{"alias_kind":"arxiv_version","alias_value":"1508.01211v2","created_at":"2026-05-18T01:35:01.615416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.01211","created_at":"2026-05-18T01:35:01.615416+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJ4IBUSFG7RO","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJ4IBUSFG7ROX3YD","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJ4IBUSF","created_at":"2026-05-18T12:29:27.538025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2605.23463","citing_title":"StepAudio 2.5 Technical Report","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"1907.03233","citing_title":"NIESR: Nuisance Invariant End-to-end Speech Recognition","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07769","citing_title":"Hierarchical Sequence to Sequence Voice Conversion with Limited Data","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"1907.10726","citing_title":"Cross-Attention End-to-End ASR for Two-Party Conversations","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16555","citing_title":"MedASR: An Open-Source Model for High-Accuracy Medical Dictation","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2506.10779","citing_title":"Improving Speech Recognition of Named Entities in Classroom Speech with LLM Revision and Phonetic-Semantic Context","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2209.11895","citing_title":"In-context Learning and Induction Heads","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJ4IBUSFG7ROX3YDHDT2NZGXL4","json":"https://pith.science/pith/JJ4IBUSFG7ROX3YDHDT2NZGXL4.json","graph_json":"https://pith.science/api/pith-number/JJ4IBUSFG7ROX3YDHDT2NZGXL4/graph.json","events_json":"https://pith.science/api/pith-number/JJ4IBUSFG7ROX3YDHDT2NZGXL4/events.json","paper":"https://pith.science/paper/JJ4IBUSF"},"agent_actions":{"view_html":"https://pith.science/pith/JJ4IBUSFG7ROX3YDHDT2NZGXL4","download_json":"https://pith.science/pith/JJ4IBUSFG7ROX3YDHDT2NZGXL4.json","view_paper":"https://pith.science/paper/JJ4IBUSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1508.01211&json=true","fetch_graph":"https://pith.science/api/pith-number/JJ4IBUSFG7ROX3YDHDT2NZGXL4/graph.json","fetch_events":"https://pith.science/api/pith-number/JJ4IBUSFG7ROX3YDHDT2NZGXL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJ4IBUSFG7ROX3YDHDT2NZGXL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJ4IBUSFG7ROX3YDHDT2NZGXL4/action/storage_attestation","attest_author":"https://pith.science/pith/JJ4IBUSFG7ROX3YDHDT2NZGXL4/action/author_attestation","sign_citation":"https://pith.science/pith/JJ4IBUSFG7ROX3YDHDT2NZGXL4/action/citation_signature","submit_replication":"https://pith.science/pith/JJ4IBUSFG7ROX3YDHDT2NZGXL4/action/replication_record"}},"created_at":"2026-05-18T01:35:01.615416+00:00","updated_at":"2026-05-18T01:35:01.615416+00:00"}