Title :
Combining multisource Wiener filtering with parallel beamformers to reduce noise from interfering talkers
Author :
Ewalt, Heather E. ; Johnson, Michael T.
Author_Institution :
Dept. of Electr. & Comput. Eng., Marquette Univ., Milwaukee, WI, USA
fDate :
31 Aug.-4 Sept. 2004
Abstract :
The ability to extract a primary speech signal from an environment with multiple speakers is an important issue (B. Widrow, 2001; M. Brandstein and D. Ward, 2001) in speech processing. This paper presents a method for incorporating multiple parallel beamformers with a Wiener filter. By iterativeIy improving the spectral magnitude estimates of each speech source, substantial improvement in overall signal separation can be obtained. The performance of the algorithm is illustrated using a simulated multiple speaker environment with resulting SNR and sSNR plots.
Keywords :
Wiener filters; filtering theory; iterative methods; signal denoising; source separation; speech processing; interfering talker; multiple parallel beamformer; multisource Wiener filtering; noise reduction; primary speech signal; signal separation; simulated multiple speaker environment; spectral magnitude estimate; speech processing; speech source; Array signal processing; Delay estimation; Filtering; Iterative algorithms; Microphone arrays; Microwave integrated circuits; Noise reduction; Speech enhancement; Speech processing; Wiener filter;
Conference_Titel :
Signal Processing, 2004. Proceedings. ICSP '04. 2004 7th International Conference on
Print_ISBN :
0-7803-8406-7
DOI :
10.1109/ICOSP.2004.1452680
