Microsoft MAVIS: Audio Video Indexing System

Microsoft research has been working in the area of speech recognition for over a decade. Recently, Microsoft Research Asia (MSRA) has developed software tools and APIs that can be used in conjunction with Microsoft Sharepoint or SQL to enable audio and video search with the same user experience and indexing infrastructure used for full text […]

Microsoft research has been working in the area of speech recognition for over a decade. Recently, Microsoft Research Asia (MSRA) has developed software tools and APIs that can be used in conjunction with Microsoft Sharepoint or SQL to enable audio and video search with the same user experience and indexing infrastructure used for full text document search. This software package referred to as the Microsoft Audio Video Indexing System (MAVIS), uses speech recognition technology to index the spoken content of recorded conversations, whether they are from meetings, conference calls, voice mails, presentations, online lectures, or even Internet video. “Washington State Digital Archives trying this out. Select audio recordings from their site and then search for a word like salmon. Now be sure to click on the emboldened salmon in the results. You’re taken to the exact point in the audio stream where the word occurs.”

More infoMAVIS