A New Speech Enhancement Algorithm for Car Environment Noise Cancellation with MBD and Kalman Filtering
Summary :
We present a new speech enhancement algorithm in a car environment with two microphones. The car audio signals and other background noises are the target noises to be suppressed. Our algorithm is composed of two main parts, i.e., the spatial and the temporal processes. The multi-channel blind deconvolution (MBD) is applied to the spatial process while the Kalman filter with a second-order high pass filter, for the temporal one. For the fast convergence, the MBD is newly expressed in frequency-domain with a normalization matrix. The final performance evaluated with the severely car noise corrupted speech shows that our algorithm produces noticeably enhanced speech.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E88-A No.3 pp.685-689
- Publication Date
- 2005/03/01
- Publicized
- Online ISSN
- DOI
- 10.1093/ietfec/e88-a.3.685
- Type of Manuscript
- Special Section LETTER (Special Section on Adaptive Signal Processing and Its Applications)
- Category
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Seungkwon BEACK, Seung H. NAM, Minsoo HAHN, "A New Speech Enhancement Algorithm for Car Environment Noise Cancellation with MBD and Kalman Filtering" in IEICE TRANSACTIONS on Fundamentals,
vol. E88-A, no. 3, pp. 685-689, March 2005, doi: 10.1093/ietfec/e88-a.3.685.
Abstract: We present a new speech enhancement algorithm in a car environment with two microphones. The car audio signals and other background noises are the target noises to be suppressed. Our algorithm is composed of two main parts, i.e., the spatial and the temporal processes. The multi-channel blind deconvolution (MBD) is applied to the spatial process while the Kalman filter with a second-order high pass filter, for the temporal one. For the fast convergence, the MBD is newly expressed in frequency-domain with a normalization matrix. The final performance evaluated with the severely car noise corrupted speech shows that our algorithm produces noticeably enhanced speech.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e88-a.3.685/_p
Copy
@ARTICLE{e88-a_3_685,
author={Seungkwon BEACK, Seung H. NAM, Minsoo HAHN, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A New Speech Enhancement Algorithm for Car Environment Noise Cancellation with MBD and Kalman Filtering},
year={2005},
volume={E88-A},
number={3},
pages={685-689},
abstract={We present a new speech enhancement algorithm in a car environment with two microphones. The car audio signals and other background noises are the target noises to be suppressed. Our algorithm is composed of two main parts, i.e., the spatial and the temporal processes. The multi-channel blind deconvolution (MBD) is applied to the spatial process while the Kalman filter with a second-order high pass filter, for the temporal one. For the fast convergence, the MBD is newly expressed in frequency-domain with a normalization matrix. The final performance evaluated with the severely car noise corrupted speech shows that our algorithm produces noticeably enhanced speech.},
keywords={},
doi={10.1093/ietfec/e88-a.3.685},
ISSN={},
month={March},}
Copy
TY - JOUR
TI - A New Speech Enhancement Algorithm for Car Environment Noise Cancellation with MBD and Kalman Filtering
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 685
EP - 689
AU - Seungkwon BEACK
AU - Seung H. NAM
AU - Minsoo HAHN
PY - 2005
DO - 10.1093/ietfec/e88-a.3.685
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E88-A
IS - 3
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - March 2005
AB - We present a new speech enhancement algorithm in a car environment with two microphones. The car audio signals and other background noises are the target noises to be suppressed. Our algorithm is composed of two main parts, i.e., the spatial and the temporal processes. The multi-channel blind deconvolution (MBD) is applied to the spatial process while the Kalman filter with a second-order high pass filter, for the temporal one. For the fast convergence, the MBD is newly expressed in frequency-domain with a normalization matrix. The final performance evaluated with the severely car noise corrupted speech shows that our algorithm produces noticeably enhanced speech.
ER -
English
