{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IPH6XZZEHXJFT2ZSSMIN3K7DOX","short_pith_number":"pith:IPH6XZZE","schema_version":"1.0","canonical_sha256":"43cfebe7243dd259eb329310ddabe375e7a4895e95c3312094446600809e7e77","source":{"kind":"arxiv","id":"2306.12577","version":1},"attestation_state":"computed","paper":{"title":"NoRefER: a Referenceless Quality Metric for Automatic Speech Recognition via Semi-Supervised Language Model Fine-Tuning with Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ahmet Gunduz, Golara Javadi, Kamer Ali Yuksel, Mohamed El-Badrashiny, Thiago Ferreira","submitted_at":"2023-06-21T21:26:19Z","abstract_excerpt":"This paper introduces NoRefER, a novel referenceless quality metric for automatic speech recognition (ASR) systems. Traditional reference-based metrics for evaluating ASR systems require costly ground-truth transcripts. NoRefER overcomes this limitation by fine-tuning a multilingual language model for pair-wise ranking ASR hypotheses using contrastive learning with Siamese network architecture. The self-supervised NoRefER exploits the known quality relationships between hypotheses from multiple compression levels of an ASR for learning to rank intra-sample hypotheses by quality, which is essen"},"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":"2306.12577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-21T21:26:19Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"83be44704a13059f0ae8da0240af98085d1d20860b9df866d627ead9c009a65c","abstract_canon_sha256":"d6ee16c4545af43afdc5cf6362358b0f4408656d202492d61455b88d9d501166"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:40.094785Z","signature_b64":"YU00qtlcwlYG8rAgbCx6PwQpFeNcsI21QNu19gCwozUerml4q2fUUphE2nLcVK14alwXIPAstQ2jmv7fIYrOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43cfebe7243dd259eb329310ddabe375e7a4895e95c3312094446600809e7e77","last_reissued_at":"2026-07-05T06:23:40.094379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:40.094379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NoRefER: a Referenceless Quality Metric for Automatic Speech Recognition via Semi-Supervised Language Model Fine-Tuning with Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ahmet Gunduz, Golara Javadi, Kamer Ali Yuksel, Mohamed El-Badrashiny, Thiago Ferreira","submitted_at":"2023-06-21T21:26:19Z","abstract_excerpt":"This paper introduces NoRefER, a novel referenceless quality metric for automatic speech recognition (ASR) systems. Traditional reference-based metrics for evaluating ASR systems require costly ground-truth transcripts. NoRefER overcomes this limitation by fine-tuning a multilingual language model for pair-wise ranking ASR hypotheses using contrastive learning with Siamese network architecture. The self-supervised NoRefER exploits the known quality relationships between hypotheses from multiple compression levels of an ASR for learning to rank intra-sample hypotheses by quality, which is essen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12577","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/2306.12577/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":"2306.12577","created_at":"2026-07-05T06:23:40.094435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.12577v1","created_at":"2026-07-05T06:23:40.094435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12577","created_at":"2026-07-05T06:23:40.094435+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPH6XZZEHXJF","created_at":"2026-07-05T06:23:40.094435+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPH6XZZEHXJFT2ZS","created_at":"2026-07-05T06:23:40.094435+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPH6XZZE","created_at":"2026-07-05T06:23:40.094435+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/IPH6XZZEHXJFT2ZSSMIN3K7DOX","json":"https://pith.science/pith/IPH6XZZEHXJFT2ZSSMIN3K7DOX.json","graph_json":"https://pith.science/api/pith-number/IPH6XZZEHXJFT2ZSSMIN3K7DOX/graph.json","events_json":"https://pith.science/api/pith-number/IPH6XZZEHXJFT2ZSSMIN3K7DOX/events.json","paper":"https://pith.science/paper/IPH6XZZE"},"agent_actions":{"view_html":"https://pith.science/pith/IPH6XZZEHXJFT2ZSSMIN3K7DOX","download_json":"https://pith.science/pith/IPH6XZZEHXJFT2ZSSMIN3K7DOX.json","view_paper":"https://pith.science/paper/IPH6XZZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.12577&json=true","fetch_graph":"https://pith.science/api/pith-number/IPH6XZZEHXJFT2ZSSMIN3K7DOX/graph.json","fetch_events":"https://pith.science/api/pith-number/IPH6XZZEHXJFT2ZSSMIN3K7DOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPH6XZZEHXJFT2ZSSMIN3K7DOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPH6XZZEHXJFT2ZSSMIN3K7DOX/action/storage_attestation","attest_author":"https://pith.science/pith/IPH6XZZEHXJFT2ZSSMIN3K7DOX/action/author_attestation","sign_citation":"https://pith.science/pith/IPH6XZZEHXJFT2ZSSMIN3K7DOX/action/citation_signature","submit_replication":"https://pith.science/pith/IPH6XZZEHXJFT2ZSSMIN3K7DOX/action/replication_record"}},"created_at":"2026-07-05T06:23:40.094435+00:00","updated_at":"2026-07-05T06:23:40.094435+00:00"}