{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.24714", "kind": "paper", "url": "https://arxiv.org/abs/2606.24714"}], "authors": ["Shijun Luo"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.24714", "source_url": "https://arxiv.org/abs/2606.24714"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "CN-NewsTTS Bench v0.1 evaluates Chinese news TTS pronunciation of dense written forms (scores, model names, ranges, units, percentages, abbreviations) from raw text, using 800 public test records and a 992-target auto-evaluable subset with ASR-ensemble transcripts and an automatic target scorer."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.24714", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.24714", "title": "CN-NewsTTS Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["NetEase (China)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.24714", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.24714", "source_url": "https://openalex.org/W7165731643"}, "key": "claire-radar:2606.24714", "modality": null, "name": "CN-NewsTTS 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_cn-newstts-bench_e74cef36", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "6f74fff53237d9edd28292ba8a5ecd818e5ae1b63accb6259fd6fc861d19eb1a", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.24714"}, "publisher": null, "released": "2026-06-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.24714", "source_url": "https://arxiv.org/abs/2606.24714"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-24714", "source": "claire_radar", "source_benchmark_id": "2606.24714", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "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/2606.24714", "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": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "38c0273a14823ec91b9d167248829d6271e3703be38dc2f02ba287f2596a65e2", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CN-NewsTTS Bench v0.1 evaluates Chinese news TTS pronunciation of dense written forms (scores, model names, ranges, units, percentages, abbreviations) from raw text, using 800 public test records and a 992-target auto-evaluable subset with ASR-ensemble transcripts and an automatic target scorer.", "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"], "snippet": "We introduce CN-NewsTTS Bench v0.1, an open target-level benchmark for evaluating whether Chinese news TTS products pronounce such targets correctly from raw text, without user-side rules, LLM rewriting, SSML hints, or manual edits."}, "familyId": "bmf_c1b15a4e7ff6", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_cn-newstts-bench_e74cef36", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.24714", "paper": "https://arxiv.org/abs/2606.24714", "pdf": "https://arxiv.org/pdf/2606.24714", "project": null, "report": "https://arxiv.org/abs/2606.24714"}, "metrics": [], "motivation": "Chinese news text contains dense written forms such as scores, hyphenated model names, ranges, unit symbols, percentages, English abbreviations, and mixed Chinese-Latin-digit names.", "name": "CN-NewsTTS Bench", "oneLine": "CN-NewsTTS Bench v0.1 evaluates Chinese news TTS pronunciation of dense written forms (scores, model names, ranges, units, percentages, abbreviations) from raw text, using 800 public test records and a 992-target auto-evaluable subset with ASR-ensemble transcripts and an automatic target scorer.", "paperTitle": "CN-NewsTTS Bench: a target-level automatic benchmark for raw-input Chinese news TTS pronunciation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.24714", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-23", "source": {"authors": ["Shijun Luo"], "categories": ["cs.CL", "cs.SD", "eess.AS"], "id": "2606.24714", "title": "CN-NewsTTS Bench: a target-level automatic benchmark for raw-input Chinese news TTS pronunciation", "type": "arxiv", "url": "https://arxiv.org/abs/2606.24714"}, "sourceUpdatedAt": "2026-06-23T15:34:58Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Addresses the gap where TTS systems may preserve written strings while altering spoken meaning in Chinese news. Provides a reproducible target-level scoring contract for comparing pronunciation accuracy across systems without manual intervention."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
