Title
Speech enhancement using a frequency-specific composite Wiener function
Abstract
This paper introduces a new speech enhancement approach based on the design of a frequency-specific composite gain function for Wiener filtering. Motivated by the recently established finding that the acoustic cues at low frequencies can improve speech recognition in noise by the combined electric and acoustic stimulation technique, a less aggressive gain function is applied to replace the Wiener filter's conventional rigid gain function at low frequencies. With this modification, the proposed approach is able to recover more low frequency (LF) components and enhance the speech quality in noisy environments. An adaptive procedure is utilized to determine the low frequency boundary. Objective evaluation, based on the PESQ measure, revealed that the proposed approach with adaptive LF boundary improved significantly the PESQ scores compared to the scores obtained with the conventional Wiener filter in steady-state noise, white noise and babble interference conditions. Speech quality was also found to be significantly enhanced in the car noise conditions when the less aggressive gain function was selectively applied only to the consonants.
Year
DOI
Venue
2010
10.1109/ICASSP.2010.5495166
ICASSP
Keywords
Field
DocType
speech enhancement,wiener filtering,perceptual evaluation of speech quality (pesq),wiener filters,frequency-specific composite wiener function,low frequency components,speech quality,gain,speech recognition,low frequency noise,white noise,noise measurement,steady state,low frequency,speech,wiener filter,acoustic noise,frequency,signal to noise ratio
Speech enhancement,Noise,Wiener filter,Pattern recognition,Noise measurement,Computer science,Signal-to-noise ratio,White noise,Speech recognition,Artificial intelligence,Interference (wave propagation),PESQ
Conference
ISSN
ISBN
Citations 
1520-6149 E-ISBN : 978-1-4244-4296-6
978-1-4244-4296-6
2
PageRank 
References 
Authors
0.70
7
2
Name
Order
Citations
PageRank
Fei Chen12512.25
Philipos C. Loizou299171.00