Real-Time Speech Recognition in a Multi-Talker Reverberated Acoustic Scenario

This paper proposes a real-time algorithmic framework for Automatic Speech Recognition (ASR) in presence of multiple sources in reverberated environment. The addressed real-life acoustic scenario definitely asks for a robust signal processing solution to reduce the impact of source mixing and reverberation on ASR performances. Here the authors show how the implemented approach allows to improve recognition accuracies under real-time processing constraints and overlapping distant-talking speakers. A suitable database has been generated on purpose, by adapting an existing large vocabulary continuous speech recognition (LVCSR) corpus to deal with the acoustic conditions under study.