Baseline for Keyword Spotting in Latvian Broadcast Speech
Roberts Darģis, Znoti ncedil scaron Art umacr rs · Frontiers in artificial intelligence and applications · 2014
This paper describes the first efforts of keyword identification in unconstrained Latvian broadcast speech. During this research a large vocabulary continuous speech recognition (LVCSR), spotting in LVCSR lattices and acoustic keyword spotting had been compared. Open source tools and recently created 100 hours of Latvian Speech Recognition Corpus have been used.