{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DHJIO57MQMXVN5W2XWENRN3PSL","short_pith_number":"pith:DHJIO57M","schema_version":"1.0","canonical_sha256":"19d28777ec832f56f6dabd88d8b76f92fd0a914506a9e5032c9cce350b35625b","source":{"kind":"arxiv","id":"2008.01300","version":2},"attestation_state":"computed","paper":{"title":"Weakly Supervised Construction of ASR Systems with Massive Video Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chengyu Wang, Jun Huang, Mengli Cheng, Xiaobo Wang, Xu Hu","submitted_at":"2020-08-04T03:11:32Z","abstract_excerpt":"Building Automatic Speech Recognition (ASR) systems from scratch is significantly challenging, mostly due to the time-consuming and financially-expensive process of annotating a large amount of audio data with transcripts. Although several unsupervised pre-training models have been proposed, applying such models directly might still be sub-optimal if more labeled, training data could be obtained without a large cost. In this paper, we present a weakly supervised framework for constructing ASR systems with massive video data. As videos often contain human-speech audios aligned with subtitles, w"},"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":"2008.01300","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-04T03:11:32Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"b91c6200cac94838302fd42e27968e7f9d28f35e89ba8e0c6d20dbad16deb334","abstract_canon_sha256":"a26045361cf741d9eac3a7b066265b3b4f3dc918b223d1ccbf5b4523972dfd5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:36:31.533635Z","signature_b64":"2AqMwW6YsmM2VLcwoE5cd3JLHtPN/p4y1Qu/68TaEZ91pTy5hpS4lBlTnBwPYuc0Se1R1kPqRx5i9Cxob9j0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19d28777ec832f56f6dabd88d8b76f92fd0a914506a9e5032c9cce350b35625b","last_reissued_at":"2026-07-05T01:36:31.533195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:36:31.533195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weakly Supervised Construction of ASR Systems with Massive Video Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chengyu Wang, Jun Huang, Mengli Cheng, Xiaobo Wang, Xu Hu","submitted_at":"2020-08-04T03:11:32Z","abstract_excerpt":"Building Automatic Speech Recognition (ASR) systems from scratch is significantly challenging, mostly due to the time-consuming and financially-expensive process of annotating a large amount of audio data with transcripts. Although several unsupervised pre-training models have been proposed, applying such models directly might still be sub-optimal if more labeled, training data could be obtained without a large cost. In this paper, we present a weakly supervised framework for constructing ASR systems with massive video data. As videos often contain human-speech audios aligned with subtitles, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.01300","kind":"arxiv","version":2},"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/2008.01300/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":"2008.01300","created_at":"2026-07-05T01:36:31.533255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.01300v2","created_at":"2026-07-05T01:36:31.533255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.01300","created_at":"2026-07-05T01:36:31.533255+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHJIO57MQMXV","created_at":"2026-07-05T01:36:31.533255+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHJIO57MQMXVN5W2","created_at":"2026-07-05T01:36:31.533255+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHJIO57M","created_at":"2026-07-05T01:36:31.533255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04491","citing_title":"Refining Transcripts With TV Subtitles by Prompt-Based Weakly Supervised Training of ASR","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DHJIO57MQMXVN5W2XWENRN3PSL","json":"https://pith.science/pith/DHJIO57MQMXVN5W2XWENRN3PSL.json","graph_json":"https://pith.science/api/pith-number/DHJIO57MQMXVN5W2XWENRN3PSL/graph.json","events_json":"https://pith.science/api/pith-number/DHJIO57MQMXVN5W2XWENRN3PSL/events.json","paper":"https://pith.science/paper/DHJIO57M"},"agent_actions":{"view_html":"https://pith.science/pith/DHJIO57MQMXVN5W2XWENRN3PSL","download_json":"https://pith.science/pith/DHJIO57MQMXVN5W2XWENRN3PSL.json","view_paper":"https://pith.science/paper/DHJIO57M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.01300&json=true","fetch_graph":"https://pith.science/api/pith-number/DHJIO57MQMXVN5W2XWENRN3PSL/graph.json","fetch_events":"https://pith.science/api/pith-number/DHJIO57MQMXVN5W2XWENRN3PSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHJIO57MQMXVN5W2XWENRN3PSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHJIO57MQMXVN5W2XWENRN3PSL/action/storage_attestation","attest_author":"https://pith.science/pith/DHJIO57MQMXVN5W2XWENRN3PSL/action/author_attestation","sign_citation":"https://pith.science/pith/DHJIO57MQMXVN5W2XWENRN3PSL/action/citation_signature","submit_replication":"https://pith.science/pith/DHJIO57MQMXVN5W2XWENRN3PSL/action/replication_record"}},"created_at":"2026-07-05T01:36:31.533255+00:00","updated_at":"2026-07-05T01:36:31.533255+00:00"}