{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:G43ATGPK3Q3J3XQY2RR2QLAC7G","short_pith_number":"pith:G43ATGPK","schema_version":"1.0","canonical_sha256":"37360999eadc369dde18d463a82c02f9968f2a0325b33782f293401f4bb86eb8","source":{"kind":"arxiv","id":"2103.09903","version":1},"attestation_state":"computed","paper":{"title":"Transformer-based ASR Incorporating Time-reduction Layer and Fine-tuning with Self-Knowledge Distillation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chao Xing, Md Akmal Haidar, Mehdi Rezagholizadeh","submitted_at":"2021-03-17T21:02:36Z","abstract_excerpt":"End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the semantic representation properly. Therefore, the models that are constructed by the lower frame-rate of speech encoder lead to better performance. For Transformer-based ASR, the lower frame-rate is not only important for learning better semantic representation but also for reducing the computational complexity due to the self-attention mechanism which has O"},"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":"2103.09903","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-17T21:02:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"00e2d7c7b6a64a1ddc7a8f61c9359435371f3c2d1b0c32c896b1547f064cfa4f","abstract_canon_sha256":"9cb9604c3ef895c2d3278384b07481ed4efa821aa23b44d50e7329e1dec86649"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:14.906744Z","signature_b64":"WiERlKg+v73RYwjgksvjZDFVWLtXofwg6EiXAQscNr7hJhAQNXii7vYtm7mzKPc2GQc8UyEgcCvPcIk/vm0uDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37360999eadc369dde18d463a82c02f9968f2a0325b33782f293401f4bb86eb8","last_reissued_at":"2026-07-05T02:24:14.906383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:14.906383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer-based ASR Incorporating Time-reduction Layer and Fine-tuning with Self-Knowledge Distillation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chao Xing, Md Akmal Haidar, Mehdi Rezagholizadeh","submitted_at":"2021-03-17T21:02:36Z","abstract_excerpt":"End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the semantic representation properly. Therefore, the models that are constructed by the lower frame-rate of speech encoder lead to better performance. For Transformer-based ASR, the lower frame-rate is not only important for learning better semantic representation but also for reducing the computational complexity due to the self-attention mechanism which has O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09903","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/2103.09903/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":"2103.09903","created_at":"2026-07-05T02:24:14.906444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.09903v1","created_at":"2026-07-05T02:24:14.906444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09903","created_at":"2026-07-05T02:24:14.906444+00:00"},{"alias_kind":"pith_short_12","alias_value":"G43ATGPK3Q3J","created_at":"2026-07-05T02:24:14.906444+00:00"},{"alias_kind":"pith_short_16","alias_value":"G43ATGPK3Q3J3XQY","created_at":"2026-07-05T02:24:14.906444+00:00"},{"alias_kind":"pith_short_8","alias_value":"G43ATGPK","created_at":"2026-07-05T02:24:14.906444+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/G43ATGPK3Q3J3XQY2RR2QLAC7G","json":"https://pith.science/pith/G43ATGPK3Q3J3XQY2RR2QLAC7G.json","graph_json":"https://pith.science/api/pith-number/G43ATGPK3Q3J3XQY2RR2QLAC7G/graph.json","events_json":"https://pith.science/api/pith-number/G43ATGPK3Q3J3XQY2RR2QLAC7G/events.json","paper":"https://pith.science/paper/G43ATGPK"},"agent_actions":{"view_html":"https://pith.science/pith/G43ATGPK3Q3J3XQY2RR2QLAC7G","download_json":"https://pith.science/pith/G43ATGPK3Q3J3XQY2RR2QLAC7G.json","view_paper":"https://pith.science/paper/G43ATGPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.09903&json=true","fetch_graph":"https://pith.science/api/pith-number/G43ATGPK3Q3J3XQY2RR2QLAC7G/graph.json","fetch_events":"https://pith.science/api/pith-number/G43ATGPK3Q3J3XQY2RR2QLAC7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G43ATGPK3Q3J3XQY2RR2QLAC7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G43ATGPK3Q3J3XQY2RR2QLAC7G/action/storage_attestation","attest_author":"https://pith.science/pith/G43ATGPK3Q3J3XQY2RR2QLAC7G/action/author_attestation","sign_citation":"https://pith.science/pith/G43ATGPK3Q3J3XQY2RR2QLAC7G/action/citation_signature","submit_replication":"https://pith.science/pith/G43ATGPK3Q3J3XQY2RR2QLAC7G/action/replication_record"}},"created_at":"2026-07-05T02:24:14.906444+00:00","updated_at":"2026-07-05T02:24:14.906444+00:00"}