{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6Y5NJAS4NU7TGJI5EILX5G6UL6","short_pith_number":"pith:6Y5NJAS4","schema_version":"1.0","canonical_sha256":"f63ad4825c6d3f33251d22177e9bd45fa6041491960d55d9f876033a0026a565","source":{"kind":"arxiv","id":"1912.11040","version":1},"attestation_state":"computed","paper":{"title":"end-to-end training of a large vocabulary end-to-end speech recognition system","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP","stat.ML"],"primary_cat":"eess.AS","authors_text":"Abhinav Garg, Changwoo Han, Chanwoo Kim, Dhananjaya Gowda, Eunhyang Kim, Jiyeon Kim, Kwangyoun Kim, Kyungmin Lee, Larry Heck, Mehul Kumar, Minkyoo Shin, Shatrughan Singh, Sungsoo Kim","submitted_at":"2019-12-22T02:59:28Z","abstract_excerpt":"In this paper, we present an end-to-end training framework for building state-of-the-art end-to-end speech recognition systems. Our training system utilizes a cluster of Central Processing Units(CPUs) and Graphics Processing Units (GPUs). The entire data reading, large scale data augmentation, neural network parameter updates are all performed \"on-the-fly\". We use vocal tract length perturbation [1] and an acoustic simulator [2] for data augmentation. The processed features and labels are sent to the GPU cluster. The Horovod allreduce approach is employed to train neural network parameters. We"},"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":"1912.11040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-12-22T02:59:28Z","cross_cats_sorted":["cs.LG","cs.SD","eess.SP","stat.ML"],"title_canon_sha256":"d57a4292ec509c14560d01373d5b455b2b2d5985d074f4f28d723b39de4fcb70","abstract_canon_sha256":"c33f3e1acf4cccf8ee50957c96c06a02fc6debb71dc810a0824f86bab1c916c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:16.389675Z","signature_b64":"qPs+ZULgP6FP3iniS3jus+ZEBUCRf0t7+lwQpfen/1pWQsR+LS39xHGMlSgWvVTl1sDCJCG08qVX56hO8D/1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f63ad4825c6d3f33251d22177e9bd45fa6041491960d55d9f876033a0026a565","last_reissued_at":"2026-07-05T00:28:16.389102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:16.389102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"end-to-end training of a large vocabulary end-to-end speech recognition system","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP","stat.ML"],"primary_cat":"eess.AS","authors_text":"Abhinav Garg, Changwoo Han, Chanwoo Kim, Dhananjaya Gowda, Eunhyang Kim, Jiyeon Kim, Kwangyoun Kim, Kyungmin Lee, Larry Heck, Mehul Kumar, Minkyoo Shin, Shatrughan Singh, Sungsoo Kim","submitted_at":"2019-12-22T02:59:28Z","abstract_excerpt":"In this paper, we present an end-to-end training framework for building state-of-the-art end-to-end speech recognition systems. Our training system utilizes a cluster of Central Processing Units(CPUs) and Graphics Processing Units (GPUs). The entire data reading, large scale data augmentation, neural network parameter updates are all performed \"on-the-fly\". We use vocal tract length perturbation [1] and an acoustic simulator [2] for data augmentation. The processed features and labels are sent to the GPU cluster. The Horovod allreduce approach is employed to train neural network parameters. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.11040","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.11040/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1912.11040","created_at":"2026-07-05T00:28:16.389166+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.11040v1","created_at":"2026-07-05T00:28:16.389166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.11040","created_at":"2026-07-05T00:28:16.389166+00:00"},{"alias_kind":"pith_short_12","alias_value":"6Y5NJAS4NU7T","created_at":"2026-07-05T00:28:16.389166+00:00"},{"alias_kind":"pith_short_16","alias_value":"6Y5NJAS4NU7TGJI5","created_at":"2026-07-05T00:28:16.389166+00:00"},{"alias_kind":"pith_short_8","alias_value":"6Y5NJAS4","created_at":"2026-07-05T00:28:16.389166+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6Y5NJAS4NU7TGJI5EILX5G6UL6","json":"https://pith.science/pith/6Y5NJAS4NU7TGJI5EILX5G6UL6.json","graph_json":"https://pith.science/api/pith-number/6Y5NJAS4NU7TGJI5EILX5G6UL6/graph.json","events_json":"https://pith.science/api/pith-number/6Y5NJAS4NU7TGJI5EILX5G6UL6/events.json","paper":"https://pith.science/paper/6Y5NJAS4"},"agent_actions":{"view_html":"https://pith.science/pith/6Y5NJAS4NU7TGJI5EILX5G6UL6","download_json":"https://pith.science/pith/6Y5NJAS4NU7TGJI5EILX5G6UL6.json","view_paper":"https://pith.science/paper/6Y5NJAS4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.11040&json=true","fetch_graph":"https://pith.science/api/pith-number/6Y5NJAS4NU7TGJI5EILX5G6UL6/graph.json","fetch_events":"https://pith.science/api/pith-number/6Y5NJAS4NU7TGJI5EILX5G6UL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6Y5NJAS4NU7TGJI5EILX5G6UL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6Y5NJAS4NU7TGJI5EILX5G6UL6/action/storage_attestation","attest_author":"https://pith.science/pith/6Y5NJAS4NU7TGJI5EILX5G6UL6/action/author_attestation","sign_citation":"https://pith.science/pith/6Y5NJAS4NU7TGJI5EILX5G6UL6/action/citation_signature","submit_replication":"https://pith.science/pith/6Y5NJAS4NU7TGJI5EILX5G6UL6/action/replication_record"}},"created_at":"2026-07-05T00:28:16.389166+00:00","updated_at":"2026-07-05T00:28:16.389166+00:00"}