This is a kaldi recipe for the 4th CHiME Speech Separation and Recognition Challenge (CHiME-4). The
challenge revisits the datasets originally recorded for CHiME-3, i.e., Wall Street Journal corpus sentences
spoken by talkers situated in challenging noisy environments recorded using a 6-channel tablet based
microphone array. CHiME-4 increases the level of difficulty by constraining the number of microphones
available for testing (i.e., separate 1, 2 and 6 channel tracks).
See http://spandh.dcs.shef.ac.uk/chime_challenge/ for more detailed information.
s5_1ch: 1 channel track
s5_2ch: 2 channel track
s5_6ch: 6 channel track