{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:LB5E6XQRL2WIEUB74A6BT4ZGXN","short_pith_number":"pith:LB5E6XQR","schema_version":"1.0","canonical_sha256":"587a4f5e115eac82503fe03c19f326bb4eac667ce8617618daa2c749f9d0129d","source":{"kind":"arxiv","id":"1505.05899","version":1},"attestation_state":"computed","paper":{"title":"The IBM 2015 English Conversational Telephone Speech Recognition System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"George Saon, Hong-Kwang J. Kuo, Michael Picheny, Steven Rennie","submitted_at":"2015-05-21T20:49:32Z","abstract_excerpt":"We describe the latest improvements to the IBM English conversational telephone speech recognition system. Some of the techniques that were found beneficial are: maxout networks with annealed dropout rates; networks with a very large number of outputs trained on 2000 hours of data; joint modeling of partially unfolded recurrent neural networks and convolutional nets by combining the bottleneck and output layers and retraining the resulting model; and lastly, sophisticated language model rescoring with exponential and neural network LMs. These techniques result in an 8.0% word error rate on the"},"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":"1505.05899","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-05-21T20:49:32Z","cross_cats_sorted":[],"title_canon_sha256":"7196f87bf6203bc897e8b5bd09060fedbd72d7954f53e7ce8e7e1505a1eb1a2a","abstract_canon_sha256":"a2c4cefc4e9b97a667200e98eb5afae1c89e897a422a02f414978f2c492bb559"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:03:49.739723Z","signature_b64":"5lmBBnVdc2mIAIuuKcu4+spgPDyMysZG18hGbhe6jYi3lgT6xszTqd4ihT7j22550/TwobJob3D1avGOfw50BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"587a4f5e115eac82503fe03c19f326bb4eac667ce8617618daa2c749f9d0129d","last_reissued_at":"2026-05-18T02:03:49.738950Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:03:49.738950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The IBM 2015 English Conversational Telephone Speech Recognition System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"George Saon, Hong-Kwang J. Kuo, Michael Picheny, Steven Rennie","submitted_at":"2015-05-21T20:49:32Z","abstract_excerpt":"We describe the latest improvements to the IBM English conversational telephone speech recognition system. Some of the techniques that were found beneficial are: maxout networks with annealed dropout rates; networks with a very large number of outputs trained on 2000 hours of data; joint modeling of partially unfolded recurrent neural networks and convolutional nets by combining the bottleneck and output layers and retraining the resulting model; and lastly, sophisticated language model rescoring with exponential and neural network LMs. These techniques result in an 8.0% word error rate on the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.05899","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":"1505.05899","created_at":"2026-05-18T02:03:49.739068+00:00"},{"alias_kind":"arxiv_version","alias_value":"1505.05899v1","created_at":"2026-05-18T02:03:49.739068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.05899","created_at":"2026-05-18T02:03:49.739068+00:00"},{"alias_kind":"pith_short_12","alias_value":"LB5E6XQRL2WI","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_16","alias_value":"LB5E6XQRL2WIEUB7","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_8","alias_value":"LB5E6XQR","created_at":"2026-05-18T12:29:29.992203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11307","citing_title":"One Size Does Not Fit All: Quantifying and Exposing the Accuracy-Latency Trade-off in Machine Learning Cloud Service APIs via Tolerance Tiers","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LB5E6XQRL2WIEUB74A6BT4ZGXN","json":"https://pith.science/pith/LB5E6XQRL2WIEUB74A6BT4ZGXN.json","graph_json":"https://pith.science/api/pith-number/LB5E6XQRL2WIEUB74A6BT4ZGXN/graph.json","events_json":"https://pith.science/api/pith-number/LB5E6XQRL2WIEUB74A6BT4ZGXN/events.json","paper":"https://pith.science/paper/LB5E6XQR"},"agent_actions":{"view_html":"https://pith.science/pith/LB5E6XQRL2WIEUB74A6BT4ZGXN","download_json":"https://pith.science/pith/LB5E6XQRL2WIEUB74A6BT4ZGXN.json","view_paper":"https://pith.science/paper/LB5E6XQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1505.05899&json=true","fetch_graph":"https://pith.science/api/pith-number/LB5E6XQRL2WIEUB74A6BT4ZGXN/graph.json","fetch_events":"https://pith.science/api/pith-number/LB5E6XQRL2WIEUB74A6BT4ZGXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LB5E6XQRL2WIEUB74A6BT4ZGXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LB5E6XQRL2WIEUB74A6BT4ZGXN/action/storage_attestation","attest_author":"https://pith.science/pith/LB5E6XQRL2WIEUB74A6BT4ZGXN/action/author_attestation","sign_citation":"https://pith.science/pith/LB5E6XQRL2WIEUB74A6BT4ZGXN/action/citation_signature","submit_replication":"https://pith.science/pith/LB5E6XQRL2WIEUB74A6BT4ZGXN/action/replication_record"}},"created_at":"2026-05-18T02:03:49.739068+00:00","updated_at":"2026-05-18T02:03:49.739068+00:00"}