{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.24648", "kind": "paper", "url": "https://arxiv.org/abs/2606.24648"}], "authors": ["Jisu Jeon", "Seungyeon Jwa", "Joosung Lee", "Jinhyeon Kim", "Woojin Chung", "Hwiyeol Jo", "Jeonghoon Kim", "Jonghyun Choi", "Soyoon Kim"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.24648", "source_url": "https://arxiv.org/abs/2606.24648"}, "categories": ["General AI", "Speech & Audio", "cs.SD"], "description": {"en": "ParaPairAudioBench evaluates LALMs as judges for paralinguistic speech across five dimensions with 5,175 audio pairs."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.24648", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.24648", "title": "ParaPairAudioBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Hongik University", "Seoul National University", "Naver (South Korea)", "Korea Advanced Institute of Science and Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.24648", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.24648", "source_url": "https://openalex.org/W7165794617"}, "key": "claire-radar:2606.24648", "modality": null, "name": "ParaPairAudioBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_parapairaudiobench_e7d0c4ed", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "00f28de0fd947c5d7de86d1c2480fb176b4c4484d9e56669010a9509a54700a2", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.24648"}, "publisher": null, "released": "2026-06-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.24648", "source_url": "https://arxiv.org/abs/2606.24648"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-24648", "source": "claire_radar", "source_benchmark_id": "2606.24648", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Speech & Audio", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.24648", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "a5089523d7a6a8813f7a7aeb60994920afc28666734033e8eabb5f1f552f6607", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ParaPairAudioBench evaluates LALMs as judges for paralinguistic speech across five dimensions with 5,175 audio pairs.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We introduce ParaPairAudioBench, a pairwise benchmark of 5,175 audio pairs across five paralinguistic dimensions: Style, Rate, Emphasis, Age, and Gender."}, "familyId": "bmf_7892b914cd26", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_parapairaudiobench_e7d0c4ed", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.24648", "paper": "https://arxiv.org/abs/2606.24648", "pdf": "https://arxiv.org/pdf/2606.24648", "project": null, "report": "https://arxiv.org/abs/2606.24648"}, "metrics": [], "motivation": "Large Audio-Language Models (LALMs) have been widely used as judge models for the automatic evaluation of generated speech.", "name": "ParaPairAudioBench", "oneLine": "ParaPairAudioBench evaluates LALMs as judges for paralinguistic speech across five dimensions with 5,175 audio pairs.", "paperTitle": "ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to Interspeech 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.24648", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "Interspeech 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-23", "source": {"authors": ["Jisu Jeon", "Seungyeon Jwa", "Joosung Lee", "Jinhyeon Kim", "Woojin Chung", "Hwiyeol Jo", "Jeonghoon Kim", "Jonghyun Choi", "Soyoon Kim"], "categories": ["cs.SD", "cs.CL", "eess.AS"], "id": "2606.24648", "title": "ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge", "type": "arxiv", "url": "https://arxiv.org/abs/2606.24648"}, "sourceUpdatedAt": "2026-06-23T14:43:43Z", "topics": ["cs.SD"], "venueAttempts": [{"decisionRaw": "Accepted to Interspeech 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to Interspeech 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.24648"}], "reviewStatus": "accepted", "venueName": "Interspeech 2026"}], "whyItMatters": "Targets fine-grained paralinguistic distinctions that prior benchmarks overlook, enabling calibration-aware assessment of judge reliability."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
