语音克隆听起来很现实,但 (尚未) 超现实
Nadine Lavan1, Mairi Irvine1, Victor Rosi2
1Centre for Brain and Behaviour, School of Biological and Behavioural Sciences, Queen Mary University of London, London, United Kingdom.
PloS one
|September 24, 2025
概括
人工智能产生的声音听起来和人类声音一样真实,难以区分. 然而,在AI面孔中观察到的"超现实效应"在AI声音中没有观察到,这些声音被认为更为主导.
科学领域:
- 人与计算机的交互
- 语音处理 语音处理
- 心理学 心理学 心理学
背景情况:
- 人工智能产生的声音在日常生活中变得越来越常见.
- 以前的研究发现,人工智能产生的面孔具有"超现实效应".
- 人工智能产生的声音的感知需要进一步调查.
研究的目的:
- 为了确定人工智能产生的声音是否表现出"超现实效应".
- 评估人类听众区分人工智能声音和人类声音的能力.
- 检查人工智能和人类声音的社会特征 (可信度,主导地位).
主要方法:
- 经过测试的人工智能声音产生与或没有人类对应物 (语音克隆与潜伏空间模型).
- 评估了听众辨别人工智能与人类声音的能力.
- 评估声音的可信度和主导地位.
主要成果:
- 语音克隆与人类声音一样真实,难以区分.
- 对人工智能生成的声音没有观察到"超现实效应".
- 人工智能声音被认为比人类声音更具主导性;一些也被认为更值得信赖.
结论:
- 当前的人工智能语音技术不会产生与人工智能面孔相比的"超现实效应".
- 声音和图像之间的感知差异可能解释了缺乏超现实主义的原因.
- 现实的AI声音存在错误信息和欺诈的风险,但也提供有益的应用.
相关概念视频
Modeling and Similitude
617
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
617
Nonconscious Mimicry
5.1K
Nonconscious mimicry occurs when individuals alter their mannerisms to match the behaviors and expressions of those nearby, without intention.
5.1K
Unrealistic Optimism Bias
211
Unrealistic optimism bias is the tendency to overestimate the likelihood of positive outcomes. This cognitive bias makes individuals believe they are less likely to experience failures, setbacks, or risks and more likely to succeed than others. For example, people may assume they are less prone to health issues, accidents, or financial struggles than their peers, even when they share similar risk factors.One key component of this bias is the above-average effect, where individuals perceive...
211
Facial Feedback Hypothesis
588
Charles Darwin proposed that facial expressions are an evolutionary adaptation for communication. He argued that these expressions are not influenced by culture but are universal across species. For example, a snarling expression with exposed teeth signals a threat in many animals, including humans. Darwin also suggested that displaying an emotion can intensify the feeling. Smiling, for example, could enhance one's sense of happiness. This idea laid the foundation for understanding the role...
588
Impression Management Techniques IV: Altercasting
173
Altercasting is a strategic communication technique in which an individual imposes a specific identity or social role onto another person to influence their behavior and shape the interaction. By presuming a role—such as “responsible leader” or “patient person”—altercasting encourages the target to conform to that identity, often aligning their behavior with the expectations associated with the role. The power of this tactic lies in its subtlety; once a role...
173
Auditory Perception
1.0K
The auditory system is essential for sound perception, utilizing various critical structures. When sound waves enter the outer ear, they travel through the ear canal and cause the eardrum to vibrate. These vibrations are then transmitted to the middle ear, where three tiny bones – the malleus, incus, and stapes – amplify the sound. This amplification is crucial, as it ensures that the sound vibrations are strong enough to be conveyed to the inner ear. These vibrations then reach the...
1.0K


