{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LRU45WTJAMYSQXWGN2VUCLGUDM","short_pith_number":"pith:LRU45WTJ","schema_version":"1.0","canonical_sha256":"5c69ceda690331285ec66eab412cd41b347cd8dbd2c35c026dc89cc0c40207fc","source":{"kind":"arxiv","id":"1908.05227","version":1},"attestation_state":"computed","paper":{"title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Franck Dernoncourt, Petr Motlicek, Subhadeep Dey, Trung Bui","submitted_at":"2019-08-08T19:21:49Z","abstract_excerpt":"In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework. The first step in our approach involves training a seed model on the limited amount of labelled data. Additional unlabelled speech data is employed through a data selection mechanism to obtain the best hypothesized output, further used to retrain the seed model. However, uncertainties of the model may not be well captured with a single hypothesis. As opposed to this technique, we apply a dropout mechanism to capture the uncertainty by obtaining multiple hypot"},"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":"1908.05227","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-08-08T19:21:49Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"47386814c2b3cbc36eca51c9099fb0bb78622907ca068688decc80404fc371ae","abstract_canon_sha256":"e1811948ae11261b5199017f2081c8595d782519d2d59df2eb8e3c20eee0e943"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:56:37.734547Z","signature_b64":"pjT99aihg8vglu11zwL9UXeBMJZ+0QKRHgs6+xermpyuTO/5rCX0AmqnwpbYOn7Yz1ozpvu+8xeAobCA1asNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c69ceda690331285ec66eab412cd41b347cd8dbd2c35c026dc89cc0c40207fc","last_reissued_at":"2026-07-04T23:56:37.734136Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:56:37.734136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Franck Dernoncourt, Petr Motlicek, Subhadeep Dey, Trung Bui","submitted_at":"2019-08-08T19:21:49Z","abstract_excerpt":"In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework. The first step in our approach involves training a seed model on the limited amount of labelled data. Additional unlabelled speech data is employed through a data selection mechanism to obtain the best hypothesized output, further used to retrain the seed model. However, uncertainties of the model may not be well captured with a single hypothesis. As opposed to this technique, we apply a dropout mechanism to capture the uncertainty by obtaining multiple hypot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05227","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/1908.05227/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":"1908.05227","created_at":"2026-07-04T23:56:37.734194+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05227v1","created_at":"2026-07-04T23:56:37.734194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05227","created_at":"2026-07-04T23:56:37.734194+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRU45WTJAMYS","created_at":"2026-07-04T23:56:37.734194+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRU45WTJAMYSQXWG","created_at":"2026-07-04T23:56:37.734194+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRU45WTJ","created_at":"2026-07-04T23:56:37.734194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.05227","citing_title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRU45WTJAMYSQXWGN2VUCLGUDM","json":"https://pith.science/pith/LRU45WTJAMYSQXWGN2VUCLGUDM.json","graph_json":"https://pith.science/api/pith-number/LRU45WTJAMYSQXWGN2VUCLGUDM/graph.json","events_json":"https://pith.science/api/pith-number/LRU45WTJAMYSQXWGN2VUCLGUDM/events.json","paper":"https://pith.science/paper/LRU45WTJ"},"agent_actions":{"view_html":"https://pith.science/pith/LRU45WTJAMYSQXWGN2VUCLGUDM","download_json":"https://pith.science/pith/LRU45WTJAMYSQXWGN2VUCLGUDM.json","view_paper":"https://pith.science/paper/LRU45WTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05227&json=true","fetch_graph":"https://pith.science/api/pith-number/LRU45WTJAMYSQXWGN2VUCLGUDM/graph.json","fetch_events":"https://pith.science/api/pith-number/LRU45WTJAMYSQXWGN2VUCLGUDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRU45WTJAMYSQXWGN2VUCLGUDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRU45WTJAMYSQXWGN2VUCLGUDM/action/storage_attestation","attest_author":"https://pith.science/pith/LRU45WTJAMYSQXWGN2VUCLGUDM/action/author_attestation","sign_citation":"https://pith.science/pith/LRU45WTJAMYSQXWGN2VUCLGUDM/action/citation_signature","submit_replication":"https://pith.science/pith/LRU45WTJAMYSQXWGN2VUCLGUDM/action/replication_record"}},"created_at":"2026-07-04T23:56:37.734194+00:00","updated_at":"2026-07-04T23:56:37.734194+00:00"}