{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OA6EPVGGMLD26ZMYG7FYLAONRZ","short_pith_number":"pith:OA6EPVGG","schema_version":"1.0","canonical_sha256":"703c47d4c662c7af659837cb8581cd8e628051e78d8e9090a2f7a08bb482feb4","source":{"kind":"arxiv","id":"2210.16663","version":2},"attestation_state":"computed","paper":{"title":"BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Brian Yan, Shinji Watanabe, Siddhant Arora, Tetsuji Ogawa, Tetsunori Kobayashi, Yosuke Higuchi","submitted_at":"2022-10-29T18:19:44Z","abstract_excerpt":"This paper presents BERT-CTC, a novel formulation of end-to-end speech recognition that adapts BERT for connectionist temporal classification (CTC). Our formulation relaxes the conditional independence assumptions used in conventional CTC and incorporates linguistic knowledge through the explicit output dependency obtained by BERT contextual embedding. BERT-CTC attends to the full contexts of the input and hypothesized output sequences via the self-attention mechanism. This mechanism encourages a model to learn inner/inter-dependencies between the audio and token representations while maintain"},"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":"2210.16663","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-10-29T18:19:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"cb6e4422bc6e390b8b35637e90268fea4e93165695e8904e903a54a06232ffbc","abstract_canon_sha256":"2e315a930e08db13a92d13f7020e3615af1e50d62e45bb107226c9578792bd1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:47.447701Z","signature_b64":"y1biUPSp5q5A+ZHSxKbBIix2VVet2YLXD2Xn6K0sCUr205nztifRGwijnetGIScW+NiLugrcmmp+HW41QsOkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"703c47d4c662c7af659837cb8581cd8e628051e78d8e9090a2f7a08bb482feb4","last_reissued_at":"2026-07-05T06:02:47.447233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:47.447233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Brian Yan, Shinji Watanabe, Siddhant Arora, Tetsuji Ogawa, Tetsunori Kobayashi, Yosuke Higuchi","submitted_at":"2022-10-29T18:19:44Z","abstract_excerpt":"This paper presents BERT-CTC, a novel formulation of end-to-end speech recognition that adapts BERT for connectionist temporal classification (CTC). Our formulation relaxes the conditional independence assumptions used in conventional CTC and incorporates linguistic knowledge through the explicit output dependency obtained by BERT contextual embedding. BERT-CTC attends to the full contexts of the input and hypothesized output sequences via the self-attention mechanism. This mechanism encourages a model to learn inner/inter-dependencies between the audio and token representations while maintain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16663","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/2210.16663/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":"2210.16663","created_at":"2026-07-05T06:02:47.447291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16663v2","created_at":"2026-07-05T06:02:47.447291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16663","created_at":"2026-07-05T06:02:47.447291+00:00"},{"alias_kind":"pith_short_12","alias_value":"OA6EPVGGMLD2","created_at":"2026-07-05T06:02:47.447291+00:00"},{"alias_kind":"pith_short_16","alias_value":"OA6EPVGGMLD26ZMY","created_at":"2026-07-05T06:02:47.447291+00:00"},{"alias_kind":"pith_short_8","alias_value":"OA6EPVGG","created_at":"2026-07-05T06:02:47.447291+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/OA6EPVGGMLD26ZMYG7FYLAONRZ","json":"https://pith.science/pith/OA6EPVGGMLD26ZMYG7FYLAONRZ.json","graph_json":"https://pith.science/api/pith-number/OA6EPVGGMLD26ZMYG7FYLAONRZ/graph.json","events_json":"https://pith.science/api/pith-number/OA6EPVGGMLD26ZMYG7FYLAONRZ/events.json","paper":"https://pith.science/paper/OA6EPVGG"},"agent_actions":{"view_html":"https://pith.science/pith/OA6EPVGGMLD26ZMYG7FYLAONRZ","download_json":"https://pith.science/pith/OA6EPVGGMLD26ZMYG7FYLAONRZ.json","view_paper":"https://pith.science/paper/OA6EPVGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16663&json=true","fetch_graph":"https://pith.science/api/pith-number/OA6EPVGGMLD26ZMYG7FYLAONRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/OA6EPVGGMLD26ZMYG7FYLAONRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OA6EPVGGMLD26ZMYG7FYLAONRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OA6EPVGGMLD26ZMYG7FYLAONRZ/action/storage_attestation","attest_author":"https://pith.science/pith/OA6EPVGGMLD26ZMYG7FYLAONRZ/action/author_attestation","sign_citation":"https://pith.science/pith/OA6EPVGGMLD26ZMYG7FYLAONRZ/action/citation_signature","submit_replication":"https://pith.science/pith/OA6EPVGGMLD26ZMYG7FYLAONRZ/action/replication_record"}},"created_at":"2026-07-05T06:02:47.447291+00:00","updated_at":"2026-07-05T06:02:47.447291+00:00"}