Kozo Okuda Tatsuya Kawahara Satoshi Nakamura 0001 Speaking rate compensation based on likelihood criterion in acoustic model training and decoding. 2002 INTERSPEECH https://doi.org/10.21437/ICSLP.2002-343 conf/interspeech/2002 db/conf/interspeech/interspeech2002.html#OkudaKN02 2589-2592