首页|Study Findings on Machine Learning Discussed by Researchers at Okayama Universit y (A Protection Scheme With Speech Processing Against Audio Adversarial Examples )
Study Findings on Machine Learning Discussed by Researchers at Okayama Universit y (A Protection Scheme With Speech Processing Against Audio Adversarial Examples )
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News-Researchers detail new data in artific ial intelligence. According to news originatingfrom Okayama, Japan, by NewsRx e ditors, the research stated, "Machine learning technologies haveimproved the ac curacy of speech recognition systems, and devices using those systems, such as s martspeakers and AI assistants, are now in wide use."The news reporters obtained a quote from the research from Okayama University: " However, speechrecognition systems have security vulnerabilities. In particular , a known machine learning vulnerabilitycalled audio adversarial examples (AAEs ), which causes misrecognition in speech recognition systems,has become a probl em. We propose a scheme for using speech processing to protect speech recognitio nsystems from AAEs, preventing misrecognitions by slight processing of input sp eech that does not affectthe recognition of normal speech. We use two kinds of processing: speed and frequency."
NETL
NSTL
