Speech Recognition for Turkish Broadcast News

Abstract

The aim of this study is to develop a speech recognition system for Turkish broadcast news. The state-of-the-art speech recognition systems utilize statistical models. A large amount of data is required to reliably estimate these models. For this study, a large Turkish Broadcast News database, consisting of the speech signal and corresponding transcriptions, is being collected. In this paper, information about this database and experiments performed using the system developed on the collected data are presented. In addition to the baseline system, various adaptation schemes and subword language models were tried. Currently, our best systems has lower than 20% error on clean speech.