{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SO3RDK2WQZCA2CR2WSEVXB2Y4V","short_pith_number":"pith:SO3RDK2W","schema_version":"1.0","canonical_sha256":"93b711ab5686440d0a3ab4895b8758e548eae9f1cb23da12ba0a356974592a7d","source":{"kind":"arxiv","id":"2408.13008","version":1},"attestation_state":"computed","paper":{"title":"Focused Discriminative Training For Streaming CTC-Trained Automatic Speech Recognition Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adnan Haider, Erik McDermott, Tim Ng, Xiaodan Zhuang, Xingyu Na, Zhen Huang","submitted_at":"2024-08-23T11:54:25Z","abstract_excerpt":"This paper introduces a novel training framework called Focused Discriminative Training (FDT) to further improve streaming word-piece end-to-end (E2E) automatic speech recognition (ASR) models trained using either CTC or an interpolation of CTC and attention-based encoder-decoder (AED) loss. The proposed approach presents a novel framework to identify and improve a model's recognition on challenging segments of an audio. Notably, this training framework is independent of hidden Markov models (HMMs) and lattices, eliminating the need for substantial decision-making regarding HMM topology, lexic"},"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":"2408.13008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-23T11:54:25Z","cross_cats_sorted":[],"title_canon_sha256":"425aa7e0ab9f475f0181dac05d9dc0485305495533ab9018b48839c807fb0b3a","abstract_canon_sha256":"f9d042b3e0060bc19e86706ba2f7ce0fcb1bfee03da7bea8482ba81e0b7e95b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:33.789204Z","signature_b64":"aoJb3f6dLxChgcsKHmb0djvOYsDCVK9oMZKsO4IRnMlXZMHOH1b6NjDq6uDHkBSVbirM2kzIbaK4jJzi02EcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93b711ab5686440d0a3ab4895b8758e548eae9f1cb23da12ba0a356974592a7d","last_reissued_at":"2026-07-05T08:58:33.788803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:33.788803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Focused Discriminative Training For Streaming CTC-Trained Automatic Speech Recognition Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adnan Haider, Erik McDermott, Tim Ng, Xiaodan Zhuang, Xingyu Na, Zhen Huang","submitted_at":"2024-08-23T11:54:25Z","abstract_excerpt":"This paper introduces a novel training framework called Focused Discriminative Training (FDT) to further improve streaming word-piece end-to-end (E2E) automatic speech recognition (ASR) models trained using either CTC or an interpolation of CTC and attention-based encoder-decoder (AED) loss. The proposed approach presents a novel framework to identify and improve a model's recognition on challenging segments of an audio. Notably, this training framework is independent of hidden Markov models (HMMs) and lattices, eliminating the need for substantial decision-making regarding HMM topology, lexic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13008","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/2408.13008/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":"2408.13008","created_at":"2026-07-05T08:58:33.788858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.13008v1","created_at":"2026-07-05T08:58:33.788858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13008","created_at":"2026-07-05T08:58:33.788858+00:00"},{"alias_kind":"pith_short_12","alias_value":"SO3RDK2WQZCA","created_at":"2026-07-05T08:58:33.788858+00:00"},{"alias_kind":"pith_short_16","alias_value":"SO3RDK2WQZCA2CR2","created_at":"2026-07-05T08:58:33.788858+00:00"},{"alias_kind":"pith_short_8","alias_value":"SO3RDK2W","created_at":"2026-07-05T08:58:33.788858+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/SO3RDK2WQZCA2CR2WSEVXB2Y4V","json":"https://pith.science/pith/SO3RDK2WQZCA2CR2WSEVXB2Y4V.json","graph_json":"https://pith.science/api/pith-number/SO3RDK2WQZCA2CR2WSEVXB2Y4V/graph.json","events_json":"https://pith.science/api/pith-number/SO3RDK2WQZCA2CR2WSEVXB2Y4V/events.json","paper":"https://pith.science/paper/SO3RDK2W"},"agent_actions":{"view_html":"https://pith.science/pith/SO3RDK2WQZCA2CR2WSEVXB2Y4V","download_json":"https://pith.science/pith/SO3RDK2WQZCA2CR2WSEVXB2Y4V.json","view_paper":"https://pith.science/paper/SO3RDK2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.13008&json=true","fetch_graph":"https://pith.science/api/pith-number/SO3RDK2WQZCA2CR2WSEVXB2Y4V/graph.json","fetch_events":"https://pith.science/api/pith-number/SO3RDK2WQZCA2CR2WSEVXB2Y4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SO3RDK2WQZCA2CR2WSEVXB2Y4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SO3RDK2WQZCA2CR2WSEVXB2Y4V/action/storage_attestation","attest_author":"https://pith.science/pith/SO3RDK2WQZCA2CR2WSEVXB2Y4V/action/author_attestation","sign_citation":"https://pith.science/pith/SO3RDK2WQZCA2CR2WSEVXB2Y4V/action/citation_signature","submit_replication":"https://pith.science/pith/SO3RDK2WQZCA2CR2WSEVXB2Y4V/action/replication_record"}},"created_at":"2026-07-05T08:58:33.788858+00:00","updated_at":"2026-07-05T08:58:33.788858+00:00"}