A combined evaluation of established and new approaches for speech recognition in varied reverberation conditions

Robustness to reverberation is a key concern for distant-microphone ASR. Various approaches have been proposed, including single-channel or multichannel dereverberation, robust feature extraction, alternative acoustic models, and acoustic model adaptation. We conduct a series of experiments to assess the impact of various dereverberation and acoustic model adaptation approaches on the ASR performance in the wide range of reverberation conditions found in real domestic environments. We consider both  established approaches and newer approaches, whose performance has not been reported before in this context, and we employ them in combination. Our results indicate that weighted prediction error (WPE) based dereverberation and i-vector based model adaptation outperform more recent approaches.