{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PCIW72XMN4BXPM24XA3TWFE2E4","short_pith_number":"pith:PCIW72XM","schema_version":"1.0","canonical_sha256":"78916feaec6f0377b35cb8373b149a2721a48aa424b4868203955528b8e52209","source":{"kind":"arxiv","id":"2005.11978","version":2},"attestation_state":"computed","paper":{"title":"Masked Pre-trained Encoder base on Joint CTC-Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Lu Liu, Yiheng Huang","submitted_at":"2020-05-25T08:41:37Z","abstract_excerpt":"This study (The work was accomplished during the internship in Tencent AI lab) addresses semi-supervised acoustic modeling, i.e. attaining high-level representations from unsupervised audio data and fine-tuning the parameters of pre-trained model with supervised data. The proposed approach adopts a two-stage training framework, consisting of masked pre-trained encoder (MPE) and Joint CTC-Transformer (JCT). In the MPE framework, part of input frames are masked and reconstructed after the encoder with massive unsupervised data. In JCT framework, compared with original Transformer, acoustic featu"},"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":"2005.11978","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-25T08:41:37Z","cross_cats_sorted":[],"title_canon_sha256":"7e5585d64b0c8cab81ad710877e5801e486cb2b9567fb7685cc9ca001f964ac1","abstract_canon_sha256":"c26b389548ca56a28614b1f98b8fcb8aa7f27004dfb63efd7467bf5553e7da11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:51.922752Z","signature_b64":"gKpICiVMQ6L+/LJZfQYPW6ijFyTDz9yGkMceAaWfUjuMW5s5pRX3P0ZgBQV2YwQ3qkmUg050LxRfJPqTve6KAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78916feaec6f0377b35cb8373b149a2721a48aa424b4868203955528b8e52209","last_reissued_at":"2026-07-05T01:26:51.922348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:51.922348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Pre-trained Encoder base on Joint CTC-Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Lu Liu, Yiheng Huang","submitted_at":"2020-05-25T08:41:37Z","abstract_excerpt":"This study (The work was accomplished during the internship in Tencent AI lab) addresses semi-supervised acoustic modeling, i.e. attaining high-level representations from unsupervised audio data and fine-tuning the parameters of pre-trained model with supervised data. The proposed approach adopts a two-stage training framework, consisting of masked pre-trained encoder (MPE) and Joint CTC-Transformer (JCT). In the MPE framework, part of input frames are masked and reconstructed after the encoder with massive unsupervised data. In JCT framework, compared with original Transformer, acoustic featu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.11978","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/2005.11978/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":"2005.11978","created_at":"2026-07-05T01:26:51.922405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.11978v2","created_at":"2026-07-05T01:26:51.922405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.11978","created_at":"2026-07-05T01:26:51.922405+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCIW72XMN4BX","created_at":"2026-07-05T01:26:51.922405+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCIW72XMN4BXPM24","created_at":"2026-07-05T01:26:51.922405+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCIW72XM","created_at":"2026-07-05T01:26:51.922405+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/PCIW72XMN4BXPM24XA3TWFE2E4","json":"https://pith.science/pith/PCIW72XMN4BXPM24XA3TWFE2E4.json","graph_json":"https://pith.science/api/pith-number/PCIW72XMN4BXPM24XA3TWFE2E4/graph.json","events_json":"https://pith.science/api/pith-number/PCIW72XMN4BXPM24XA3TWFE2E4/events.json","paper":"https://pith.science/paper/PCIW72XM"},"agent_actions":{"view_html":"https://pith.science/pith/PCIW72XMN4BXPM24XA3TWFE2E4","download_json":"https://pith.science/pith/PCIW72XMN4BXPM24XA3TWFE2E4.json","view_paper":"https://pith.science/paper/PCIW72XM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.11978&json=true","fetch_graph":"https://pith.science/api/pith-number/PCIW72XMN4BXPM24XA3TWFE2E4/graph.json","fetch_events":"https://pith.science/api/pith-number/PCIW72XMN4BXPM24XA3TWFE2E4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCIW72XMN4BXPM24XA3TWFE2E4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCIW72XMN4BXPM24XA3TWFE2E4/action/storage_attestation","attest_author":"https://pith.science/pith/PCIW72XMN4BXPM24XA3TWFE2E4/action/author_attestation","sign_citation":"https://pith.science/pith/PCIW72XMN4BXPM24XA3TWFE2E4/action/citation_signature","submit_replication":"https://pith.science/pith/PCIW72XMN4BXPM24XA3TWFE2E4/action/replication_record"}},"created_at":"2026-07-05T01:26:51.922405+00:00","updated_at":"2026-07-05T01:26:51.922405+00:00"}