EURASIP Journal on Audio, Speech, and Music Processing

Table 1 WERs[%] for CU-Move in-vehicle task with different front ends/speaker normalization algorithms.

From: Towards an Intelligent Acoustic Front End for Automatic Speech Recognition: Built-in Speaker Normalization

System/WER	Female	Male	Overall
MFCC			11.12
PMVDR			7.11
PMVDR w/Spkr. norm.
VTLN			5.66
BISN			5.61
BISN w/BTS			5.61
BISN w/MS-BTS			5.59

Back to article page