TY - GEN
T1 - Signal and feature domain enhancement approaches for robust speech recognition
AU - Lee, Jinkyu
AU - Baek, Soonho
AU - Kang, Hong Goo
PY - 2011
Y1 - 2011
N2 - This paper analyzes the impact of various preprocessing modules to improve the performance of automatic speech recognition system (ASR) in noisy environment. After choosing the state-of-the-art algorithms designed in the signal domain and feature domain, their performances in various noise conditions are thoroughly evaluated. Since the enhancement has been directly made to the features that are actually used for recognition, the feature domain approach is more appropriate than the signal domain approach. Experimental results show that the noise reduction in the feature domain gives the best performance.
AB - This paper analyzes the impact of various preprocessing modules to improve the performance of automatic speech recognition system (ASR) in noisy environment. After choosing the state-of-the-art algorithms designed in the signal domain and feature domain, their performances in various noise conditions are thoroughly evaluated. Since the enhancement has been directly made to the features that are actually used for recognition, the feature domain approach is more appropriate than the signal domain approach. Experimental results show that the noise reduction in the feature domain gives the best performance.
UR - http://www.scopus.com/inward/record.url?scp=84860636351&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84860636351&partnerID=8YFLogxK
U2 - 10.1109/ICICS.2011.6173538
DO - 10.1109/ICICS.2011.6173538
M3 - Conference contribution
AN - SCOPUS:84860636351
SN - 9781457700309
T3 - ICICS 2011 - 8th International Conference on Information, Communications and Signal Processing
BT - ICICS 2011 - 8th International Conference on Information, Communications and Signal Processing
T2 - 8th International Conference on Information, Communications and Signal Processing, ICICS 2011
Y2 - 13 December 2011 through 16 December 2011
ER -