HMM-TDNN(LFMMI) + LSTMLM

Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio1 result

Speech RecognitiononCHiME real
Percentage error· 2018-03-27
11.4
best: 7.8 (Distortion-Independent + WRBN + Utterance-Wise Recurrent Dropout + Magnitude Features)
SOTA
Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline arXiv:1803.10109