{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JJAL75PICZ4SXRVPDJFK7XAQKQ","short_pith_number":"pith:JJAL75PI","schema_version":"1.0","canonical_sha256":"4a40bff5e816792bc6af1a4aafdc105431fc23cb6d3ea2434c1fa218509d7b3b","source":{"kind":"arxiv","id":"2306.13114","version":1},"attestation_state":"computed","paper":{"title":"A Reference-less Quality Metric for Automatic Speech Recognition via Contrastive-Learning of a Multi-Language Model with Self-Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Ahmet Gunduz, Golara Javadi, Kamer Ali Yuksel, Mohamed Al-Badrashiny, Thiago Ferreira","submitted_at":"2023-06-21T21:33:39Z","abstract_excerpt":"The common standard for quality evaluation of automatic speech recognition (ASR) systems is reference-based metrics such as the Word Error Rate (WER), computed using manual ground-truth transcriptions that are time-consuming and expensive to obtain. This work proposes a multi-language referenceless quality metric, which allows comparing the performance of different ASR models on a speech dataset without ground truth transcriptions. To estimate the quality of ASR hypotheses, a pre-trained language model (LM) is fine-tuned with contrastive learning in a self-supervised learning manner. In experi"},"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":"2306.13114","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-21T21:33:39Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d3f9c58a0ea05e343ce2803c0f39343f7d45d7b274d5cca1788b9d12221a688c","abstract_canon_sha256":"6e5394adc900f5956c6311a94a64618a453e1e7a8d34234bfc63e0f148a6c59a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:01.824349Z","signature_b64":"CF8HBeCJPXi7z8EgrbG+iBH++hqbahZP/+K4shRQHCq6ZPi2ZbTq/SvHvXkcnWKNGmuF9cZLsP2eS3lvm0cvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a40bff5e816792bc6af1a4aafdc105431fc23cb6d3ea2434c1fa218509d7b3b","last_reissued_at":"2026-07-05T06:24:01.823949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:01.823949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Reference-less Quality Metric for Automatic Speech Recognition via Contrastive-Learning of a Multi-Language Model with Self-Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Ahmet Gunduz, Golara Javadi, Kamer Ali Yuksel, Mohamed Al-Badrashiny, Thiago Ferreira","submitted_at":"2023-06-21T21:33:39Z","abstract_excerpt":"The common standard for quality evaluation of automatic speech recognition (ASR) systems is reference-based metrics such as the Word Error Rate (WER), computed using manual ground-truth transcriptions that are time-consuming and expensive to obtain. This work proposes a multi-language referenceless quality metric, which allows comparing the performance of different ASR models on a speech dataset without ground truth transcriptions. To estimate the quality of ASR hypotheses, a pre-trained language model (LM) is fine-tuned with contrastive learning in a self-supervised learning manner. In experi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13114","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/2306.13114/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":"2306.13114","created_at":"2026-07-05T06:24:01.824008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.13114v1","created_at":"2026-07-05T06:24:01.824008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13114","created_at":"2026-07-05T06:24:01.824008+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJAL75PICZ4S","created_at":"2026-07-05T06:24:01.824008+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJAL75PICZ4SXRVP","created_at":"2026-07-05T06:24:01.824008+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJAL75PI","created_at":"2026-07-05T06:24:01.824008+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/JJAL75PICZ4SXRVPDJFK7XAQKQ","json":"https://pith.science/pith/JJAL75PICZ4SXRVPDJFK7XAQKQ.json","graph_json":"https://pith.science/api/pith-number/JJAL75PICZ4SXRVPDJFK7XAQKQ/graph.json","events_json":"https://pith.science/api/pith-number/JJAL75PICZ4SXRVPDJFK7XAQKQ/events.json","paper":"https://pith.science/paper/JJAL75PI"},"agent_actions":{"view_html":"https://pith.science/pith/JJAL75PICZ4SXRVPDJFK7XAQKQ","download_json":"https://pith.science/pith/JJAL75PICZ4SXRVPDJFK7XAQKQ.json","view_paper":"https://pith.science/paper/JJAL75PI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.13114&json=true","fetch_graph":"https://pith.science/api/pith-number/JJAL75PICZ4SXRVPDJFK7XAQKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JJAL75PICZ4SXRVPDJFK7XAQKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJAL75PICZ4SXRVPDJFK7XAQKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJAL75PICZ4SXRVPDJFK7XAQKQ/action/storage_attestation","attest_author":"https://pith.science/pith/JJAL75PICZ4SXRVPDJFK7XAQKQ/action/author_attestation","sign_citation":"https://pith.science/pith/JJAL75PICZ4SXRVPDJFK7XAQKQ/action/citation_signature","submit_replication":"https://pith.science/pith/JJAL75PICZ4SXRVPDJFK7XAQKQ/action/replication_record"}},"created_at":"2026-07-05T06:24:01.824008+00:00","updated_at":"2026-07-05T06:24:01.824008+00:00"}