EURASIP Journal on Audio, Speech, and Music Processing

Table 2 Comparison of WERs (%) of ESniff MMSR with other approaches when using FE feature vectors

From: Compensation of SNR and noise type mismatch using an environmental sniffing based speech recognition solution

Approach	WER (%)
	Set A	Set B	Set C	Average
CLEAN	38.66	44.25	33.86	39.94
VTS	28.23	29.31	24.95	28.00
PMC	20.70	18.82	21.98	20.20
MTR	12.23	13.75	16.42	13.68
ESniff MMSR	8.92	16.64	15.09	13.24

Back to article page