翻译：Practical Hidden Voice Attacks against Speech and Speaker Recognition Systems
原文链接：https://arxiv.org/pdf/1904.05734.pdf 是NDSS-2019 accepted paper 初次接触语音攻击方面的文章，翻译不当的地方，望大家指正。 摘要——目前已广泛部署的语音处理系统(VPS)，通过应用机器学习方面的最新进展，已大大提高了准确度。然而，对抗式机器学习也取得了类似的进展，并被用来证明VPS易受注入隐藏命令的影响——音频被VPS能正确识
相关文章
- 1. Practical Black-Box Attacks against Machine Learning
- 2. Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody
- 3. Hidden Voice Attack | Adversarial Attack on Audio
- 4. Visual Speech Recognition: Lip Segmentation and Mapping
- 5. [paper]Practical Black-Box Attacks against Machine Learning
- 6. Interspeech 2017 | Self-adaptive Speech Recognition Technology
- 7. 5 Open Source Speech Recognition/Speech-to-Text Systems
- 8. SPEAKER-AWARE SPEECH-TRANSFORMER
- 9. Interspeech 2017 | Far-field Speech Recognition Technology
- 10. Almost Unsupervised Text to Speech and Automatic Speech Recognition
- 更多相关文章...
- • Eclipse 编译项目 - Eclipse 教程
- • XSL-FO table-and-caption 对象 - XSL-FO 教程
- • RxJava操作符（七）Conditional and Boolean
- • Docker容器实战(七) - 容器眼光下的文件系统
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. Practical Black-Box Attacks against Machine Learning
- 2. Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody
- 3. Hidden Voice Attack | Adversarial Attack on Audio
- 4. Visual Speech Recognition: Lip Segmentation and Mapping
- 5. [paper]Practical Black-Box Attacks against Machine Learning
- 6. Interspeech 2017 | Self-adaptive Speech Recognition Technology
- 7. 5 Open Source Speech Recognition/Speech-to-Text Systems
- 8. SPEAKER-AWARE SPEECH-TRANSFORMER
- 9. Interspeech 2017 | Far-field Speech Recognition Technology
- 10. Almost Unsupervised Text to Speech and Automatic Speech Recognition