{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UIMVMKQXXG5POVTUN6U6CRE4RX","short_pith_number":"pith:UIMVMKQX","schema_version":"1.0","canonical_sha256":"a219562a17b9baf756746fa9e1449c8de1e15ae5c157c03a087f91823056ac38","source":{"kind":"arxiv","id":"1907.01957","version":2},"attestation_state":"computed","paper":{"title":"End-to-End Speech Recognition with High-Frame-Rate Features Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Cong-Thanh Do","submitted_at":"2019-07-03T14:14:27Z","abstract_excerpt":"State-of-the-art end-to-end automatic speech recognition (ASR) extracts acoustic features from input speech signal every 10 ms which corresponds to a frame rate of 100 frames/second. In this report, we investigate the use of high-frame-rate features extraction in end-to-end ASR. High frame rates of 200 and 400 frames/second are used in the features extraction and provide additional information for end-to-end ASR. The effectiveness of high-frame-rate features extraction is evaluated independently and in combination with speed perturbation based data augmentation. Experiments performed on two sp"},"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":"1907.01957","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-07-03T14:14:27Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"fdb32fe9c4b30e742c50918ce2ccca95a83cba6a50cfbc8ae167f8cdc3f50205","abstract_canon_sha256":"8a1ee487ec677e257b520bd17fdc43b80f72782ab1da25cd18c9b1a2a5aa1cec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:48.610711Z","signature_b64":"DjJCOEBoz8icUUCfKddLMuz9ol7vp4+gsjL7JLJ0nOiM/8J/KsrUT61wrOYM7L814Ta7+bFrIDXHtbbwHGcuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a219562a17b9baf756746fa9e1449c8de1e15ae5c157c03a087f91823056ac38","last_reissued_at":"2026-05-17T23:40:48.610047Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:48.610047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Speech Recognition with High-Frame-Rate Features Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Cong-Thanh Do","submitted_at":"2019-07-03T14:14:27Z","abstract_excerpt":"State-of-the-art end-to-end automatic speech recognition (ASR) extracts acoustic features from input speech signal every 10 ms which corresponds to a frame rate of 100 frames/second. In this report, we investigate the use of high-frame-rate features extraction in end-to-end ASR. High frame rates of 200 and 400 frames/second are used in the features extraction and provide additional information for end-to-end ASR. The effectiveness of high-frame-rate features extraction is evaluated independently and in combination with speed perturbation based data augmentation. Experiments performed on two sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01957","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":""},"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":"1907.01957","created_at":"2026-05-17T23:40:48.610137+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.01957v2","created_at":"2026-05-17T23:40:48.610137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01957","created_at":"2026-05-17T23:40:48.610137+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIMVMKQXXG5P","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIMVMKQXXG5POVTU","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIMVMKQX","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.01957","citing_title":"End-to-End Speech Recognition with High-Frame-Rate Features Extraction","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UIMVMKQXXG5POVTUN6U6CRE4RX","json":"https://pith.science/pith/UIMVMKQXXG5POVTUN6U6CRE4RX.json","graph_json":"https://pith.science/api/pith-number/UIMVMKQXXG5POVTUN6U6CRE4RX/graph.json","events_json":"https://pith.science/api/pith-number/UIMVMKQXXG5POVTUN6U6CRE4RX/events.json","paper":"https://pith.science/paper/UIMVMKQX"},"agent_actions":{"view_html":"https://pith.science/pith/UIMVMKQXXG5POVTUN6U6CRE4RX","download_json":"https://pith.science/pith/UIMVMKQXXG5POVTUN6U6CRE4RX.json","view_paper":"https://pith.science/paper/UIMVMKQX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.01957&json=true","fetch_graph":"https://pith.science/api/pith-number/UIMVMKQXXG5POVTUN6U6CRE4RX/graph.json","fetch_events":"https://pith.science/api/pith-number/UIMVMKQXXG5POVTUN6U6CRE4RX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIMVMKQXXG5POVTUN6U6CRE4RX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIMVMKQXXG5POVTUN6U6CRE4RX/action/storage_attestation","attest_author":"https://pith.science/pith/UIMVMKQXXG5POVTUN6U6CRE4RX/action/author_attestation","sign_citation":"https://pith.science/pith/UIMVMKQXXG5POVTUN6U6CRE4RX/action/citation_signature","submit_replication":"https://pith.science/pith/UIMVMKQXXG5POVTUN6U6CRE4RX/action/replication_record"}},"created_at":"2026-05-17T23:40:48.610137+00:00","updated_at":"2026-05-17T23:40:48.610137+00:00"}