{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:SYETSMFFJSRNN74K6R77CHSYSW","short_pith_number":"pith:SYETSMFF","schema_version":"1.0","canonical_sha256":"96093930a54ca2d6ff8af47ff11e5895831b97922b46b35d35d97fe2cd0e7c45","source":{"kind":"arxiv","id":"1506.07503","version":1},"attestation_state":"computed","paper":{"title":"Attention-Based Models for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CL","authors_text":"Dmitriy Serdyuk, Dzmitry Bahdanau, Jan Chorowski, Kyunghyun Cho, Yoshua Bengio","submitted_at":"2015-06-24T19:10:33Z","abstract_excerpt":"Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image caption gen- eration. We extend the attention-mechanism with features needed for speech recognition. We show that while an adaptation of the model used for machine translation in reaches a competitive 18.7% phoneme error rate (PER) on the TIMIT phoneme recognition task, it can only be applied to utterances which are roughly as long as the ones it was trained on. We offer a qualitativ"},"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":"1506.07503","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-24T19:10:33Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"2227bcfa08d5e2e2de74ebea17e6d0ebb081cb6ca257d7d7db1f18bb36911c75","abstract_canon_sha256":"70b13eebf8211de5dfe657903a0f93078eaeab574f3d6c2253aae73669a30982"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:39:53.888026Z","signature_b64":"o2iBFRcm8pJs1t94MEqfgeGhETxPVsJpdEioyf2xRY4VAkluUnHU2SL6/l1zNTuQ1gI9wK95d3S8adI8Y6Z6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96093930a54ca2d6ff8af47ff11e5895831b97922b46b35d35d97fe2cd0e7c45","last_reissued_at":"2026-05-18T01:39:53.887391Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:39:53.887391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention-Based Models for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CL","authors_text":"Dmitriy Serdyuk, Dzmitry Bahdanau, Jan Chorowski, Kyunghyun Cho, Yoshua Bengio","submitted_at":"2015-06-24T19:10:33Z","abstract_excerpt":"Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image caption gen- eration. We extend the attention-mechanism with features needed for speech recognition. We show that while an adaptation of the model used for machine translation in reaches a competitive 18.7% phoneme error rate (PER) on the TIMIT phoneme recognition task, it can only be applied to utterances which are roughly as long as the ones it was trained on. We offer a qualitativ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.07503","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":"1506.07503","created_at":"2026-05-18T01:39:53.887484+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.07503v1","created_at":"2026-05-18T01:39:53.887484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.07503","created_at":"2026-05-18T01:39:53.887484+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYETSMFFJSRN","created_at":"2026-05-18T12:29:42.218222+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYETSMFFJSRNN74K","created_at":"2026-05-18T12:29:42.218222+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYETSMFF","created_at":"2026-05-18T12:29:42.218222+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.07769","citing_title":"Hierarchical Sequence to Sequence Voice Conversion with Limited Data","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2603.15045","citing_title":"LLMs and Speech: Integration vs. Combination","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SYETSMFFJSRNN74K6R77CHSYSW","json":"https://pith.science/pith/SYETSMFFJSRNN74K6R77CHSYSW.json","graph_json":"https://pith.science/api/pith-number/SYETSMFFJSRNN74K6R77CHSYSW/graph.json","events_json":"https://pith.science/api/pith-number/SYETSMFFJSRNN74K6R77CHSYSW/events.json","paper":"https://pith.science/paper/SYETSMFF"},"agent_actions":{"view_html":"https://pith.science/pith/SYETSMFFJSRNN74K6R77CHSYSW","download_json":"https://pith.science/pith/SYETSMFFJSRNN74K6R77CHSYSW.json","view_paper":"https://pith.science/paper/SYETSMFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.07503&json=true","fetch_graph":"https://pith.science/api/pith-number/SYETSMFFJSRNN74K6R77CHSYSW/graph.json","fetch_events":"https://pith.science/api/pith-number/SYETSMFFJSRNN74K6R77CHSYSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYETSMFFJSRNN74K6R77CHSYSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYETSMFFJSRNN74K6R77CHSYSW/action/storage_attestation","attest_author":"https://pith.science/pith/SYETSMFFJSRNN74K6R77CHSYSW/action/author_attestation","sign_citation":"https://pith.science/pith/SYETSMFFJSRNN74K6R77CHSYSW/action/citation_signature","submit_replication":"https://pith.science/pith/SYETSMFFJSRNN74K6R77CHSYSW/action/replication_record"}},"created_at":"2026-05-18T01:39:53.887484+00:00","updated_at":"2026-05-18T01:39:53.887484+00:00"}