{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.17812", "kind": "paper", "url": "https://arxiv.org/abs/2607.17812"}], "authors": ["Fernando López", "Ana Ayala", "Guillermo Segovia", "Fernando Ibáñez", "Ana Martínez", "Pablo Gómez", "Jordi Luque"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.17812", "source_url": "https://arxiv.org/abs/2607.17812"}, "categories": ["General AI", "Reasoning", "Speech & Audio"], "description": {"en": "ESCUCHA is a Spanish speech understanding benchmark evaluating LALMs across heterogeneous acoustic conditions and reasoning abilities. It includes 1,000 human-curated audio-question pairs spanning perceptual and reasoning categories, with multiple accents and non-normative speech."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.17812", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.17812", "title": "ESCUCHA"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Universidad Autónoma de Madrid"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.17812", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.17812", "source_url": "https://openalex.org/W7169877215"}, "key": "claire-radar:2607.17812", "modality": null, "name": "ESCUCHA", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "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_escucha_bdd66fa8", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "03eb9e3aee8a65b6440e26aeedc09bc2519b7375b36489580696be499ea232c8", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.17812"}, "publisher": null, "released": "2026-07-20", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.17812", "source_url": "https://arxiv.org/abs/2607.17812"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-17812", "source": "claire_radar", "source_benchmark_id": "2607.17812", "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/2607.17812", "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": ["Reasoning"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "58de95993e993265778207d70af3e7fafb275cd603138bd1e7434fb757a5617e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ESCUCHA is a Spanish speech understanding benchmark evaluating LALMs across heterogeneous acoustic conditions and reasoning abilities. It includes 1,000 human-curated audio-question pairs spanning perceptual and reasoning categories, with multiple accents and non-normative speech.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "We introduce ESCUCHA, the first Spanish speech understanding benchmark designed to evaluate LALMs across heterogeneous acoustic conditions and reasoning abilities."}, "familyId": "bmf_07214793264e", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_escucha_bdd66fa8", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.17812", "paper": "https://arxiv.org/abs/2607.17812", "pdf": "https://arxiv.org/pdf/2607.17812", "project": null, "report": "https://arxiv.org/abs/2607.17812"}, "metrics": [], "motivation": "As large audio language models (LALMs) advance, robust evaluation frameworks have become essential.", "name": "ESCUCHA", "oneLine": "ESCUCHA is a Spanish speech understanding benchmark evaluating LALMs across heterogeneous acoustic conditions and reasoning abilities. It includes 1,000 human-curated audio-question pairs spanning perceptual and reasoning categories, with multiple accents and non-normative speech.", "paperTitle": "ESCUCHA: A Spanish Speech Benchmark for Heterogeneous Acoustic Conditions", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.17812", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-20", "source": {"authors": ["Fernando L\\'opez", "Ana Ayala", "Guillermo Segovia", "Fernando Ib\\'a\\~nez", "Ana Mart\\'inez", "Pablo G\\'omez", "Jordi Luque"], "categories": ["cs.CL"], "id": "2607.17812", "title": "ESCUCHA: A Spanish Speech Benchmark for Heterogeneous Acoustic Conditions", "type": "arxiv", "url": "https://arxiv.org/abs/2607.17812"}, "sourceUpdatedAt": "2026-07-20T10:59:15Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "The benchmark addresses the lack of robust evaluation for Spanish speech understanding under realistic conditions. It provides practical value in assessing model performance across diverse acoustic environments and reasoning tasks, highlighting gaps relative to human performance."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
