{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GGSV7WW77P4XHOHIYFF5KZVFKH","short_pith_number":"pith:GGSV7WW7","schema_version":"1.0","canonical_sha256":"31a55fdadffbf973b8e8c14bd566a551d3f67afa95c775d066f6ffecb5e6486f","source":{"kind":"arxiv","id":"2210.15876","version":2},"attestation_state":"computed","paper":{"title":"Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Haihua Xu, Lu Lu, Tao Han, Tze Yuang Chong, Van Tung Pham, Yerbolat Khassanov, Yi He, Yist Y. Lin, Zejun Ma","submitted_at":"2022-10-28T03:54:57Z","abstract_excerpt":"One of limitations in end-to-end automatic speech recognition (ASR) framework is its performance would be compromised if train-test utterance lengths are mismatched. In this paper, we propose an on-the-fly random utterance concatenation (RUC) based data augmentation method to alleviate train-test utterance length mismatch issue for short-video ASR task. Specifically, we are motivated by observations that our human-transcribed training utterances tend to be much shorter for short-video spontaneous speech (~3 seconds on average), while our test utterance generated from voice activity detection f"},"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":"2210.15876","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-10-28T03:54:57Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"dfbc981f1c7ad658e82c3bb713ab0d1f04366591bd2a6deaa8bdb3557cbd6268","abstract_canon_sha256":"6c19f20b4c026c7df5415af6f13a204435e1740584e9d6a3171b9c5619967ebb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:37.264748Z","signature_b64":"ORkz5IbUoJ/ey04ShJ04aRZHbN5vuWlx9d/P3A9HJ5r+XSCbSvrbyMYfk9ieWJHVWuyYifc/ENAHtTay4hP5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31a55fdadffbf973b8e8c14bd566a551d3f67afa95c775d066f6ffecb5e6486f","last_reissued_at":"2026-07-05T06:13:37.264251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:37.264251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Haihua Xu, Lu Lu, Tao Han, Tze Yuang Chong, Van Tung Pham, Yerbolat Khassanov, Yi He, Yist Y. Lin, Zejun Ma","submitted_at":"2022-10-28T03:54:57Z","abstract_excerpt":"One of limitations in end-to-end automatic speech recognition (ASR) framework is its performance would be compromised if train-test utterance lengths are mismatched. In this paper, we propose an on-the-fly random utterance concatenation (RUC) based data augmentation method to alleviate train-test utterance length mismatch issue for short-video ASR task. Specifically, we are motivated by observations that our human-transcribed training utterances tend to be much shorter for short-video spontaneous speech (~3 seconds on average), while our test utterance generated from voice activity detection f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15876","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/2210.15876/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":"2210.15876","created_at":"2026-07-05T06:13:37.264308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.15876v2","created_at":"2026-07-05T06:13:37.264308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15876","created_at":"2026-07-05T06:13:37.264308+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGSV7WW77P4X","created_at":"2026-07-05T06:13:37.264308+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGSV7WW77P4XHOHI","created_at":"2026-07-05T06:13:37.264308+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGSV7WW7","created_at":"2026-07-05T06:13:37.264308+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/GGSV7WW77P4XHOHIYFF5KZVFKH","json":"https://pith.science/pith/GGSV7WW77P4XHOHIYFF5KZVFKH.json","graph_json":"https://pith.science/api/pith-number/GGSV7WW77P4XHOHIYFF5KZVFKH/graph.json","events_json":"https://pith.science/api/pith-number/GGSV7WW77P4XHOHIYFF5KZVFKH/events.json","paper":"https://pith.science/paper/GGSV7WW7"},"agent_actions":{"view_html":"https://pith.science/pith/GGSV7WW77P4XHOHIYFF5KZVFKH","download_json":"https://pith.science/pith/GGSV7WW77P4XHOHIYFF5KZVFKH.json","view_paper":"https://pith.science/paper/GGSV7WW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.15876&json=true","fetch_graph":"https://pith.science/api/pith-number/GGSV7WW77P4XHOHIYFF5KZVFKH/graph.json","fetch_events":"https://pith.science/api/pith-number/GGSV7WW77P4XHOHIYFF5KZVFKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGSV7WW77P4XHOHIYFF5KZVFKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGSV7WW77P4XHOHIYFF5KZVFKH/action/storage_attestation","attest_author":"https://pith.science/pith/GGSV7WW77P4XHOHIYFF5KZVFKH/action/author_attestation","sign_citation":"https://pith.science/pith/GGSV7WW77P4XHOHIYFF5KZVFKH/action/citation_signature","submit_replication":"https://pith.science/pith/GGSV7WW77P4XHOHIYFF5KZVFKH/action/replication_record"}},"created_at":"2026-07-05T06:13:37.264308+00:00","updated_at":"2026-07-05T06:13:37.264308+00:00"}