Artificial Analysis 发布 TTS 发音鲁棒性评测
Pronunciation Robustness measures whether Text to Speech models correctly pronounce challenging text across four categories, with human reviewers judging each c
Artificial Analysis 推出 Pronunciation Robustness 评测，由人工评审按四类挑战性文本判断 TTS 模型发音是否正确。Eleven v4 Turbo 在缩写展开项以 91.9% 排第二，落后 Eleven v4 的 94.1%，高于 Gemini 3.8 Flash TTS 的 86.1%；语境适配项得 95.8%，Gemini 3.8 Flash TTS 以 97.9% 领先。精确序列保留项 Eleven v4 Turbo 为 73.9%，高于 Eleven v3 的 71.2%，SpaceXAI TTS 以 85.7% 居首。
正文
当前显示原文，中文全文译文尚未就绪。
Pronunciation Robustness measures whether Text to Speech models correctly pronounce challenging text across four categories, with human reviewers judging each clip against pre-agreed accepted pronunciations.
➤ Expanding Shorthand: Eleven v4 Turbo ranks #2 at 91.9%, behind Eleven v4 at 94.1% and ahead of Gemini 3.8 Flash TTS at 86.1%.
➤ Contextually Appropriate: Eleven v4 Turbo scores 95.8%, ahead of Eleven v4 at 94.1%, with Gemini 3.8 Flash TTS leading at 97.9%.
➤ Standalone Terms: Eleven v4 Turbo scores 91.4%, with Eleven v3 Conversational leading at 95.1%.
➤ Preserving Exact Sequences: Eleven v4 Turbo scores 73.9%, ahead of Eleven v3 at 71.2%, with SpaceXAI TTS leading at 85.7%.