{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UWYUCC53V4KQV2W6FKORAVGDUH","short_pith_number":"pith:UWYUCC53","schema_version":"1.0","canonical_sha256":"a5b1410bbbaf150aeade2a9d1054c3a1d0a5808b95c8f15598fa749727c84b0d","source":{"kind":"arxiv","id":"1805.04699","version":4},"attestation_state":"computed","paper":{"title":"TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fran\\c{c}ois Hernandez, Natalia Tomashenko, Sahar Ghannay, Vincent Nguyen, Yannick Est\\`eve","submitted_at":"2018-05-12T11:06:47Z","abstract_excerpt":"In this paper, we present TED-LIUM release 3 corpus dedicated to speech recognition in English, that multiplies by more than two the available data to train acoustic models in comparison with TED-LIUM 2. We present the recent development on Automatic Speech Recognition (ASR) systems in comparison with the two previous releases of the TED-LIUM Corpus from 2012 and 2014. We demonstrate that, passing from 207 to 452 hours of transcribed speech training data is really more useful for end-to-end ASR systems than for HMM-based state-of-the-art ones, even if the HMM-based ASR system still outperforms"},"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":"1805.04699","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-12T11:06:47Z","cross_cats_sorted":[],"title_canon_sha256":"d1e1ceedd16ee95b7830acdd2e6c364ccdbcc4e0910d750e039739ec0bf4fe5e","abstract_canon_sha256":"5f59c9499cc7eca3c9cb7cb794a2699d9b42ebbd822d8ba456437e852f91bae9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:28.427970Z","signature_b64":"CPFBJpwvmEnkwPRqa/SbGAxe+AjVdX6Mb3Kbasa5xLcKyzD/ctGyB1Z/KBykv33NsH8CHyZKFFoL90M56lbiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5b1410bbbaf150aeade2a9d1054c3a1d0a5808b95c8f15598fa749727c84b0d","last_reissued_at":"2026-05-17T23:43:28.427465Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:28.427465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fran\\c{c}ois Hernandez, Natalia Tomashenko, Sahar Ghannay, Vincent Nguyen, Yannick Est\\`eve","submitted_at":"2018-05-12T11:06:47Z","abstract_excerpt":"In this paper, we present TED-LIUM release 3 corpus dedicated to speech recognition in English, that multiplies by more than two the available data to train acoustic models in comparison with TED-LIUM 2. We present the recent development on Automatic Speech Recognition (ASR) systems in comparison with the two previous releases of the TED-LIUM Corpus from 2012 and 2014. We demonstrate that, passing from 207 to 452 hours of transcribed speech training data is really more useful for end-to-end ASR systems than for HMM-based state-of-the-art ones, even if the HMM-based ASR system still outperforms"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04699","kind":"arxiv","version":4},"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":"1805.04699","created_at":"2026-05-17T23:43:28.427556+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.04699v4","created_at":"2026-05-17T23:43:28.427556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04699","created_at":"2026-05-17T23:43:28.427556+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWYUCC53V4KQ","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWYUCC53V4KQV2W6","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWYUCC53","created_at":"2026-05-18T12:32:56.356000+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/UWYUCC53V4KQV2W6FKORAVGDUH","json":"https://pith.science/pith/UWYUCC53V4KQV2W6FKORAVGDUH.json","graph_json":"https://pith.science/api/pith-number/UWYUCC53V4KQV2W6FKORAVGDUH/graph.json","events_json":"https://pith.science/api/pith-number/UWYUCC53V4KQV2W6FKORAVGDUH/events.json","paper":"https://pith.science/paper/UWYUCC53"},"agent_actions":{"view_html":"https://pith.science/pith/UWYUCC53V4KQV2W6FKORAVGDUH","download_json":"https://pith.science/pith/UWYUCC53V4KQV2W6FKORAVGDUH.json","view_paper":"https://pith.science/paper/UWYUCC53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.04699&json=true","fetch_graph":"https://pith.science/api/pith-number/UWYUCC53V4KQV2W6FKORAVGDUH/graph.json","fetch_events":"https://pith.science/api/pith-number/UWYUCC53V4KQV2W6FKORAVGDUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWYUCC53V4KQV2W6FKORAVGDUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWYUCC53V4KQV2W6FKORAVGDUH/action/storage_attestation","attest_author":"https://pith.science/pith/UWYUCC53V4KQV2W6FKORAVGDUH/action/author_attestation","sign_citation":"https://pith.science/pith/UWYUCC53V4KQV2W6FKORAVGDUH/action/citation_signature","submit_replication":"https://pith.science/pith/UWYUCC53V4KQV2W6FKORAVGDUH/action/replication_record"}},"created_at":"2026-05-17T23:43:28.427556+00:00","updated_at":"2026-05-17T23:43:28.427556+00:00"}