{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D3PVCEARELLTYX3FTIB7YNOHYD","short_pith_number":"pith:D3PVCEAR","schema_version":"1.0","canonical_sha256":"1edf51101122d73c5f659a03fc35c7c0f2cf40dfbd99621b294bd5cbe63be267","source":{"kind":"arxiv","id":"2309.15701","version":2},"attestation_state":"computed","paper":{"title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao-Han Huck Yang, Chen Chen, Eng Siong Chng, Pin-Yu Chen, Sabato Macro Siniscalchi, Yuchen Hu","submitted_at":"2023-09-27T14:44:10Z","abstract_excerpt":"Advancements in deep neural networks have allowed automatic speech recognition (ASR) systems to attain human parity on several publicly available clean speech datasets. However, even state-of-the-art ASR systems experience performance degradation when confronted with adverse conditions, as a well-trained acoustic model is sensitive to variations in the speech domain, e.g., background noise. Intuitively, humans address this issue by relying on their linguistic knowledge: the meaning of ambiguous spoken terms is usually inferred from contextual cues thereby reducing the dependency on the auditor"},"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":"2309.15701","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-27T14:44:10Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"feed96be5c245ced05ebdad0d3e7d99c05ab7677f6890fd1c11e2412275dfbc2","abstract_canon_sha256":"d4d67c71121d753666bbb8b643ef400f7351e38fdeeb38afe4caa8e56c8139d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:06.063560Z","signature_b64":"AwpNbtTmVJzcR/W56PfhIUcVvu8297bSxxaRb4MadCjz0hZhMSrV5To26dAERyZinkvuk7YOSRKfaiGNylL7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1edf51101122d73c5f659a03fc35c7c0f2cf40dfbd99621b294bd5cbe63be267","last_reissued_at":"2026-07-05T07:01:06.063070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:06.063070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao-Han Huck Yang, Chen Chen, Eng Siong Chng, Pin-Yu Chen, Sabato Macro Siniscalchi, Yuchen Hu","submitted_at":"2023-09-27T14:44:10Z","abstract_excerpt":"Advancements in deep neural networks have allowed automatic speech recognition (ASR) systems to attain human parity on several publicly available clean speech datasets. However, even state-of-the-art ASR systems experience performance degradation when confronted with adverse conditions, as a well-trained acoustic model is sensitive to variations in the speech domain, e.g., background noise. Intuitively, humans address this issue by relying on their linguistic knowledge: the meaning of ambiguous spoken terms is usually inferred from contextual cues thereby reducing the dependency on the auditor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15701","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/2309.15701/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":"2309.15701","created_at":"2026-07-05T07:01:06.063129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15701v2","created_at":"2026-07-05T07:01:06.063129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15701","created_at":"2026-07-05T07:01:06.063129+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3PVCEARELLT","created_at":"2026-07-05T07:01:06.063129+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3PVCEARELLTYX3F","created_at":"2026-07-05T07:01:06.063129+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3PVCEAR","created_at":"2026-07-05T07:01:06.063129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.07285","citing_title":"Non-Intrusive Automatic Speech Recognition Refinement: A Survey","ref_index":121,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D3PVCEARELLTYX3FTIB7YNOHYD","json":"https://pith.science/pith/D3PVCEARELLTYX3FTIB7YNOHYD.json","graph_json":"https://pith.science/api/pith-number/D3PVCEARELLTYX3FTIB7YNOHYD/graph.json","events_json":"https://pith.science/api/pith-number/D3PVCEARELLTYX3FTIB7YNOHYD/events.json","paper":"https://pith.science/paper/D3PVCEAR"},"agent_actions":{"view_html":"https://pith.science/pith/D3PVCEARELLTYX3FTIB7YNOHYD","download_json":"https://pith.science/pith/D3PVCEARELLTYX3FTIB7YNOHYD.json","view_paper":"https://pith.science/paper/D3PVCEAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15701&json=true","fetch_graph":"https://pith.science/api/pith-number/D3PVCEARELLTYX3FTIB7YNOHYD/graph.json","fetch_events":"https://pith.science/api/pith-number/D3PVCEARELLTYX3FTIB7YNOHYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3PVCEARELLTYX3FTIB7YNOHYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3PVCEARELLTYX3FTIB7YNOHYD/action/storage_attestation","attest_author":"https://pith.science/pith/D3PVCEARELLTYX3FTIB7YNOHYD/action/author_attestation","sign_citation":"https://pith.science/pith/D3PVCEARELLTYX3FTIB7YNOHYD/action/citation_signature","submit_replication":"https://pith.science/pith/D3PVCEARELLTYX3FTIB7YNOHYD/action/replication_record"}},"created_at":"2026-07-05T07:01:06.063129+00:00","updated_at":"2026-07-05T07:01:06.063129+00:00"}