Original post · AI translation
@shobhitbanga，“愚弄率”（Fool Rate）真是一个很容易向语音团队以外的人解释的数字。
我们能在网站上听听一些真人与 AI 语音的配对样本吗？
第 2/15 条
我们真的在衡量语音 AI 模型最终应实现的目标吗？
最好的 AI 语音正变得越来越难以区分。
是彼此之间难以区分，而不是与真人语音难以区分。
🚀 推出 Turing TTS：一项评测，衡量人类听众有多大比例会把 AI 生成的语音误认为真人语音。
我们用真人语音测试了领先的 TTS 模型。即使是表现最好的模型，也只有约 10% 的时候能让听众误以为是真人语音。
我们希望通过 Turing TTS，为研究界关于如何衡量语音 AI 进展的更广泛讨论作出贡献。
如果我们的目标之一是开发出与真人语音无法区分的语音，现有的评测方法在多大程度上能反映我们朝这一目标取得的进展？
我们并不声称 Turing TTS 是正确的前进方向，也不认为与真人语音无法区分应该是每个 TTS 系统的目标。
我们希望这些发现能促使研究界共同审视：对自然度进行盲法成对人工评测是否足够，以及我们还可能需要衡量什么。
结果现已在 @voicearena_ai 上发布。
Original
Drop 2/15 Are we actually measuring the things we ultimately want our voice AI models to achieve? The best AI voices are becoming hard to tell apart. From each other. Not from humans. 🚀 Introducing Turing TTS: an evaluation that measures how often human listeners mistake AI-generated speech for real human speech. We tested leading TTS models against real human speech. Even the best model fooled listeners only ~10% of the time. With Turing TTS, we hope to contribute to a broader discussion within the research community about how we measure progress in voice AI. If one of our goals is to develop speech that is indistinguishable from human speech, how well do our current evaluation methods capture progress toward that goal? We don’t claim that Turing TTS is the right way forward, or that human indistinguishability should be the goal of every TTS system. Rather, we hope these findings encourage the community to collectively examine whether blind pairwise human evaluations of naturalness are sufficient, and what else we might need to measure. Results are now live on @voicearena_ai.