{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.14846", "kind": "paper", "url": "https://arxiv.org/abs/2607.14846"}], "authors": ["David Ayllon", "Alice Baird", "Jeffrey Brooks", "Franc Camps-Febrer", "Jakub Piotr Cłapa", "Theo Lebryk", "Jens Madsen", "Olya Ossipova", "Sharath Rao", "Hoon Shin", "Tigran Soghbatyan", "Georg Streich", "Rashish Tandon", "Panagiotis Tzirakis"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.14846", "source_url": "https://arxiv.org/abs/2607.14846"}, "categories": ["General AI", "Speech & Audio", "cs.SD"], "description": {"en": "The Real World Voice EQ Bench evaluates voice AI systems across TTS, STS, SU, and ASR, focusing on how well models use acoustic information beyond text. It assesses dimensions like naturalness, expressiveness, identity stability, reliability, vocal affect use, and robustness to real-world conditions such as accent, emotion, noise, and conversation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.14846", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.14846", "title": "RW-Voice-EQ Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.14846", "modality": null, "name": "RW-Voice-EQ Bench", "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_rw-voice-eq-bench_67940c5c", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "d61a1e784230c00b9d4eeb279caf81569738d34476f5838f547dd33fc490f320", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.14846"}, "publisher": null, "released": "2026-07-16", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.14846", "source_url": "https://arxiv.org/abs/2607.14846"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-14846", "source": "claire_radar", "source_benchmark_id": "2607.14846", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "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": 11, "hfPaperUrl": "https://huggingface.co/papers/2607.14846", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "ab5af34bf14d8c9c9d952b5298f5eb8f486506392ed9d8dc6ac6f83dbcc56f99", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "The Real World Voice EQ Bench evaluates voice AI systems across TTS, STS, SU, and ASR, focusing on how well models use acoustic information beyond text. It assesses dimensions like naturalness, expressiveness, identity stability, reliability, vocal affect use, and robustness to real-world conditions such as accent, emotion, noise, and conversation.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To this end, we introduce the Real World Voice EQ Bench, a multidimensional benchmark for evaluating voice AI across text-to-speech (TTS), speech-to-speech (STS), speech understanding (SU), and automatic speech recognition (ASR)."}, "familyId": "bmf_19d351184c25", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_rw-voice-eq-bench_67940c5c", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.14846", "paper": "https://arxiv.org/abs/2607.14846", "pdf": "https://arxiv.org/pdf/2607.14846", "project": null, "report": "https://arxiv.org/abs/2607.14846"}, "metrics": [], "motivation": "Current voice AI benchmarks typically evaluate isolated capabilities such as speech intelligibility, word error rate, or text-based dialogue quality, but they rarely test whether systems harness the acoustic information that distinguishes spoken language from its textual representation.", "name": "RW-Voice-EQ Bench", "oneLine": "The Real World Voice EQ Bench evaluates voice AI systems across TTS, STS, SU, and ASR, focusing on how well models use acoustic information beyond text. It assesses dimensions like naturalness, expressiveness, identity stability, reliability, vocal affect use, and robustness to real-world conditions such as accent, emotion, noise, and conversation.", "paperTitle": "RW-Voice-EQ Bench: A Real World Benchmark for Evaluating Voice AI Systems", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.14846", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.4390696100905538, "value": 11}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 49}, "method": "attention-ranking-v13", "rank": null, "score": 49}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-16", "source": {"authors": ["David Ayllon", "Alice Baird", "Jeffrey Brooks", "Franc Camps-Febrer", "Jakub Piotr C{\\l}apa", "Theo Lebryk", "Jens Madsen", "Olya Ossipova", "Sharath Rao", "Hoon Shin", "Tigran Soghbatyan", "Georg Streich", "Rashish Tandon", "Panagiotis Tzirakis"], "categories": ["cs.SD", "cs.AI"], "id": "2607.14846", "title": "RW-Voice-EQ Bench: A Real World Benchmark for Evaluating Voice AI Systems", "type": "arxiv", "url": "https://arxiv.org/abs/2607.14846"}, "sourceUpdatedAt": "2026-07-16T11:15:16Z", "topics": ["cs.SD"], "venueAttempts": [], "whyItMatters": "Current voice AI benchmarks often evaluate isolated capabilities like word error rate or text-based dialogue quality, missing how systems harness acoustic information central to spoken language. This benchmark highlights that performance varies across dimensions, showing that a single aggregate score is insufficient and that real-world conditions expose failures not captured by clean-speech tests. It supports more nuanced evaluation and improvement of voice AI systems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
