AI 与机器学习2019arxiv.org
Speech2Face:从声音学习背后的面孔
Speech2Face: Learning the Face Behind a Voice
进阶 · 约 35 分钟读完前置知识:深度学习基础、计算机视觉与人脸处理、语音信号处理基础
导读
论文提出 Speech2Face:用大量「说话人正脸 + 语音」的网络视频训练模型,从一段简短语音直接重建说话人的面部图像。结果显示重建人脸能还原年龄、性别、种族等若干面部属性,但并一定是说话人本人的真实长相。作者也讨论了这类方法的隐私与伦理风险。
HN 关注点:的不是重建精度,而是它暴露的隐私风险:声音能泄露多少人口统计学信息,以及这类技术可能被用于监控和身份推断。
后来怎么样
它让“从语音推断人脸/人口属性”进入公众与隐私研究视野,成为讨论语音生物特征与去身份化风险的常见引例;但并未成为实际人脸重建的标准方法。
HN 评论精选
这几条评论里:质疑 3 补充 1
补充语音科学家指出,模型本质上是高效判断性别、种族和年龄的分类器,说明声音携带的社会信息极强。
我是一名言语科学家。这篇论文的想法很巧妙,结果也有意思,但和我预期的方向不同。我原本希望它能研究能从声音中推断出多少与个人生理有关的信息,比如唇开合度、牙齿咬合、声道大小、鼻孔开张程度;从语音感知的角度看,这很有意思。但它的有趣之处更多在于能从声音推断出多少社会性信息:它看起来是一个相当高效的分类器,以声音为输入即可判断性别、种族和年龄。我相信这不是第一次有人做到,但看到它实际跑起来还是很不错。它也带来一个值得记住的提醒:如果神经网络能从音频中如此好地推断社会、种族和性别信息,人类只会更强。「言语是一种社会建构」这个观点因此更加切题。
wanderfowl查看英文原文
I'm a speech scientist. This paper is a neat idea, and the results are interesting, but not in the way I'd expected. I had hoped it would the domain of how much person-specific information this can deduce from a voice, e.g. lip aperture, overbite, size of the vocal tract, openness of the nares. This is interesting from a speech perception standpoint. Instead, it's interesting more in the domain of how much social information it can deduce from a voice. This appears to be a relatively efficient classifier for gender, race, and age, taking voice as input. I'm sure this isn't the first time it's been done, but it's pretty neat to see it in action, and it's a worthwhile reminder: If a neural net is this good at inferring social, racial, and gender information from audio, humans are even better. And the idea of speech as a social construct becomes even more relevant.
质疑论文中的「人脸归一化」流水线相当于数字嫌犯照;同时可用刻板口音欺骗族裔推断。
PDF 里很酷的一点是,能从视频帧构造出归一化的人脸(配图链接)。基本上是取一帧视频,把脸转正、去除光照以得到纯反照率(albedo),并去掉眼镜等配饰。就追踪个人而言这非常惊人,等于一张数字嫌犯照。另外我觉得有意思的是,分类器能以很高准确率判断族裔。从隐私角度看,要骗过这项技术,似乎简单办法就是刻意用某族裔的刻板口音说话。
daenz查看英文原文
One of the really cool things from the pdf is the ability to construct a normalized face from a video frame: https://i.imgur.com/SdRHCJ0.png Basically they are taking a video frame, making it face forward, cancelling out lighting for pure albedo, and removing accessories like glasses. This is incredible in terms of tracking individuals. It's a digital mugshot. Also, I think it's interesting that the classifiers can pick out ethnicity with a high degree of accuracy. Seems like an easy way to fool this tech, from a privacy perspective, is to talk stereotypically like a specific ethnicity.
质疑担忧其与声纹、键鼠声识别结合后形成「环境声音指纹」式的无感监控。
太可怕了。如果把这个和「根据键盘、鼠标等输入设备发出的声音推测身份」的模型结合起来,基本上就得到了一种「环境声音指纹识别」技术:设备附近发出的声音可以用来准确判断站在旁边的人是谁。如果再把它和中国的面部识别结合起来,想到机器学习和大数据正把我们的社会变得多么「加图卡式」(Gattaca),我就不寒而栗。
echopom查看英文原文
Absolutely terrifying. If you add this to the model that guesses identity based on the sound produced by inputs (keyboard , mouse...) you basically end up with an "ambiant sound fingerprinting" tech , where the sounds emitted nearby a device can be used to accurately determine the individual that's standing close to it... If you add this to china's facial recognition , it scares me to think how "Gattaguesque" our societies are turning thanks to Machine Learning and Big Data...
质疑对「极少数据即可推断大量个人特质」的忧虑,认为监管和社会认知都尚未准备好。
我觉得我们完全没准备好面对一件事:机器学习可能从我们身上、从极少的信息里推断出多少东西。再加上 Facebook、Google 等以高分辨率追踪我们的行为,我们正径直走向《千钧一发》(Gattaca)那样的未来,只不过他们根本不需要检测你的 DNA。只要把你朋友、员工或孩子的短视频上传到 videotherapist.ai,就能知道他们更可能成为纵火犯还是物理学家!
hedgew查看英文原文
I don't think that we're prepared at all for how much, and from how little, machine learning might be able to deduce about us. Combined with how our behavior is tracked in high resolution by Facebook, Google, and the rest, we're heading straight for the kind of future depicted in films like Gattaca, but they won't even need to test your DNA for it. Just upload a short video of your friend/employee/kid to videotherapist.ai and find out if they're more likely to be an arsonist or a physicist!
相关资源
从这篇论文所有 HN 讨论帖的全部评论里整理出来的链接。
历次讨论
- 2019Hacker News 讨论帖143 分 · 54 评
同领域还值得读
DeepSeek-R1:通过强化学习激励 LLM 的推理能力
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
研究如何用强化学习激励大语言模型的推理能力,提出 DeepSeek-R1,并探讨 RL 训练对模型推理表现的影响。
AI 与机器学习2025 · 1,351 分 · 1,056 评 · 引用 30进阶 · 约 80 分钟编辑精选1-bit LLM 时代:面向低成本计算的三值参数
The Era of 1-bit LLMs: ternary parameters for cost-effective computing
提出用三值参数 {-1, 0, 1} 替代 LLM 中的浮点权重,即所谓“1-bit LLM”。
AI 与机器学习2024 · 1,040 分 · 447 评 · 引用 19进阶 · 约 45 分钟编辑精选DeepSeek-V3.2:推进开放大语言模型的前沿
DeepSeek-v3.2: Pushing the frontier of open large language models
这是 DeepSeek-V3.2 的技术报告,延续了 DeepSeek 开源权重模型的路线,目标是让开放模型继续逼近甚至追平前沿闭源模型。
AI 与机器学习2025 · 982 分 · 465 评进阶 · 约 90 分钟编辑精选通过自我对弈与通用强化学习掌握国际象棋和将棋(AlphaZero)
Mastering Chess and Shogi by Self-Play with General Reinforcement Learning
DeepMind 的 AlphaZero 论文:用通用强化学习算法(自我博弈 + MCTS + 神经网络),从零开始仅数小时训练便在国际象棋和将棋上击败了世界顶级引擎 Stock…
AI 与机器学习2017 · 539 分 · 270 评 · 引用 13进阶 · 约 90 分钟编辑精选用强化学习发现更快的矩阵乘法算法
Discovering faster matrix multiplication algorithms with reinforcement learning
论文提出 AlphaTensor,用强化学习搜索矩阵乘法算法。
AI 与机器学习2022 · 518 分 · 111 评专业 · 约 90 分钟编辑精选