{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PJFVXMX5A3ASKR6RMPNFDWCP6J","short_pith_number":"pith:PJFVXMX5","schema_version":"1.0","canonical_sha256":"7a4b5bb2fd06c12547d163da51d84ff242db0388aaf3c4e0db28ded5b3c60386","source":{"kind":"arxiv","id":"2502.14685","version":1},"attestation_state":"computed","paper":{"title":"SegAug: CTC-Aligned Segmented Augmentation For Robust RNN-Transducer Based Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Duc Thanh Chau, Dung Tran, Khanh Le, Tuan Vu Ho","submitted_at":"2025-02-20T16:13:17Z","abstract_excerpt":"RNN-Transducer (RNN-T) is a widely adopted architecture in speech recognition, integrating acoustic and language modeling in an end-to-end framework. However, the RNN-T predictor tends to over-rely on consecutive word dependencies in training data, leading to high deletion error rates, particularly with less common or out-of-domain phrases. Existing solutions, such as regularization and data augmentation, often compromise other aspects of performance. We propose SegAug, an alignment-based augmentation technique that generates contextually varied audio-text pairs with low sentence-level semanti"},"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":"2502.14685","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-20T16:13:17Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d01afee2773c8dc426a502182fe363d3a18dc6c9639ff56d5c721350e615a84f","abstract_canon_sha256":"17a16733c69d2d2b0a03a838ad0a6543a481a88ceeb3adf47dd175f17d0af92e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:31.193830Z","signature_b64":"2Mxc6vecY+To+kAaomeryUvXjXvyWPoBarJGV0HjwFJFrqlVuJ2WJEjH+8lFd95lO8qKhoPkGbe+v56sWwJtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a4b5bb2fd06c12547d163da51d84ff242db0388aaf3c4e0db28ded5b3c60386","last_reissued_at":"2026-07-05T10:17:31.193369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:31.193369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SegAug: CTC-Aligned Segmented Augmentation For Robust RNN-Transducer Based Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Duc Thanh Chau, Dung Tran, Khanh Le, Tuan Vu Ho","submitted_at":"2025-02-20T16:13:17Z","abstract_excerpt":"RNN-Transducer (RNN-T) is a widely adopted architecture in speech recognition, integrating acoustic and language modeling in an end-to-end framework. However, the RNN-T predictor tends to over-rely on consecutive word dependencies in training data, leading to high deletion error rates, particularly with less common or out-of-domain phrases. Existing solutions, such as regularization and data augmentation, often compromise other aspects of performance. We propose SegAug, an alignment-based augmentation technique that generates contextually varied audio-text pairs with low sentence-level semanti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14685","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/2502.14685/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":"2502.14685","created_at":"2026-07-05T10:17:31.193430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14685v1","created_at":"2026-07-05T10:17:31.193430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14685","created_at":"2026-07-05T10:17:31.193430+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJFVXMX5A3AS","created_at":"2026-07-05T10:17:31.193430+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJFVXMX5A3ASKR6R","created_at":"2026-07-05T10:17:31.193430+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJFVXMX5","created_at":"2026-07-05T10:17:31.193430+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/PJFVXMX5A3ASKR6RMPNFDWCP6J","json":"https://pith.science/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J.json","graph_json":"https://pith.science/api/pith-number/PJFVXMX5A3ASKR6RMPNFDWCP6J/graph.json","events_json":"https://pith.science/api/pith-number/PJFVXMX5A3ASKR6RMPNFDWCP6J/events.json","paper":"https://pith.science/paper/PJFVXMX5"},"agent_actions":{"view_html":"https://pith.science/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J","download_json":"https://pith.science/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J.json","view_paper":"https://pith.science/paper/PJFVXMX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14685&json=true","fetch_graph":"https://pith.science/api/pith-number/PJFVXMX5A3ASKR6RMPNFDWCP6J/graph.json","fetch_events":"https://pith.science/api/pith-number/PJFVXMX5A3ASKR6RMPNFDWCP6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J/action/storage_attestation","attest_author":"https://pith.science/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J/action/author_attestation","sign_citation":"https://pith.science/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J/action/citation_signature","submit_replication":"https://pith.science/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J/action/replication_record"}},"created_at":"2026-07-05T10:17:31.193430+00:00","updated_at":"2026-07-05T10:17:31.193430+00:00"}