A Parallel Meeting Diarist

摘要

The following article presents an application for browsing meeting recordings by speaker, keyword, and pre-defined acoustic events (e.g., laughter), which we call the Meeting Diarist. The goal of the system is to enable browsing of the content with rich meta-data in a graphical user interface (GUI) shortly after the end of meeting, even when the application runs on a contemporary laptop. We therefore developed novel parallel methods for speaker diarization and speech recognition that are optimized to run on multicore and manycore architectures. This paper presents the application and the underlying parallel speaker diarization and speech recognition realizations.