TY - JOUR AB - We present single-channel approaches to robust automatic speech recognition (ASR) in reverberant environments based on non-intrusive estimation of the clarity index (C 50). Our best performing method includes the estimated value of C 50 in the ASR feature vector and also uses C 50 to select the most suitable ASR acoustic model according to the reverberation level. We evaluate our method on the REVERB Challenge database employing two different C 50 estimators and show that our method outperforms the best baseline of the challenge achieved without unsupervised acoustic model adaptation, i.e. using multi-condition hidden Markov models (HMMs). Our approach achieves a 22.4 % relative word error rate reduction in comparison to the best baseline of the challenge. AU - Parada,PP AU - Sharma,D AU - Naylor,PA AU - van,Waterschoot T DO - 10.1186/s13634-015-0237-7 EP - 12 PY - 2015/// SN - 1687-6180 SP - 1 TI - Reverberant speech recognition exploiting clarity index estimation T2 - Eurasip Journal on Advances in Signal Processing UR - http://dx.doi.org/10.1186/s13634-015-0237-7 UR - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000358321400001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202 UR - http://hdl.handle.net/10044/1/32163 VL - 2016 ER -