A fast discrete-time learning algorithm for speech enhancement using noise constrained parameter estimation

Youshen Xia; Guiliang Lin; Wei Xing Zheng

doi:10.1109/IJCNN.2014.6889451

A fast discrete-time learning algorithm for speech enhancement using noise constrained parameter estimation

Youshen Xia, Guiliang Lin, Wei Xing Zheng

School of Computer, Data & Mathematical Sciences

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

1 Citation (Scopus)

Abstract

This paper proposes a fast discrete-time learning algorithm for speech enhancement of single-channel noisy speech signal, based on a noise constrained least squares estimate. Unlike existing learning algorithms for the noise constrained estimate, the proposed discrete-time learning algorithm has a low complexity and fast speed. Simulation results show that the proposed discrete-time learning algorithm has a faster speed than the existing learning algorithms for speech enhancement. Moreover, the proposed discrete-time learning algorithm has a good performance in having a significant gain in SNR at colored noise.

Original language	English
Title of host publication	Proceedings of the 2014 International Joint Conference on Neural Networks, July 6-11, 2014, Beijing, China
Publisher	IEEE
Pages	3149-3154
Number of pages	6
ISBN (Print)	9781479914845
DOIs	https://doi.org/10.1109/IJCNN.2014.6889451
Publication status	Published - 2014
Event	International Joint Conference on Neural Networks - Duration: 6 Jul 2014 → …

Conference

Conference	International Joint Conference on Neural Networks
Period	6/07/14 → …

Keywords

discrete-time systems
signal processing
speech processing systems

Access to Document

10.1109/IJCNN.2014.6889451

Cite this

@inproceedings{51682003b70048fb8be262b2d35927d5,

title = "A fast discrete-time learning algorithm for speech enhancement using noise constrained parameter estimation",

abstract = "This paper proposes a fast discrete-time learning algorithm for speech enhancement of single-channel noisy speech signal, based on a noise constrained least squares estimate. Unlike existing learning algorithms for the noise constrained estimate, the proposed discrete-time learning algorithm has a low complexity and fast speed. Simulation results show that the proposed discrete-time learning algorithm has a faster speed than the existing learning algorithms for speech enhancement. Moreover, the proposed discrete-time learning algorithm has a good performance in having a significant gain in SNR at colored noise.",

keywords = "discrete-time systems, signal processing, speech processing systems",

author = "Youshen Xia and Guiliang Lin and Zheng, {Wei Xing}",

year = "2014",

doi = "10.1109/IJCNN.2014.6889451",

language = "English",

isbn = "9781479914845",

pages = "3149--3154",

booktitle = "Proceedings of the 2014 International Joint Conference on Neural Networks, July 6-11, 2014, Beijing, China",

publisher = "IEEE",

note = "International Joint Conference on Neural Networks ; Conference date: 06-07-2014",

}

Xia, Y, Lin, G & Zheng, WX 2014, A fast discrete-time learning algorithm for speech enhancement using noise constrained parameter estimation. in Proceedings of the 2014 International Joint Conference on Neural Networks, July 6-11, 2014, Beijing, China. IEEE, pp. 3149-3154, International Joint Conference on Neural Networks, 6/07/14. https://doi.org/10.1109/IJCNN.2014.6889451

A fast discrete-time learning algorithm for speech enhancement using noise constrained parameter estimation. / Xia, Youshen; Lin, Guiliang; Zheng, Wei Xing.
Proceedings of the 2014 International Joint Conference on Neural Networks, July 6-11, 2014, Beijing, China. IEEE, 2014. p. 3149-3154.

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - A fast discrete-time learning algorithm for speech enhancement using noise constrained parameter estimation

AU - Xia, Youshen

AU - Lin, Guiliang

AU - Zheng, Wei Xing

PY - 2014

Y1 - 2014

N2 - This paper proposes a fast discrete-time learning algorithm for speech enhancement of single-channel noisy speech signal, based on a noise constrained least squares estimate. Unlike existing learning algorithms for the noise constrained estimate, the proposed discrete-time learning algorithm has a low complexity and fast speed. Simulation results show that the proposed discrete-time learning algorithm has a faster speed than the existing learning algorithms for speech enhancement. Moreover, the proposed discrete-time learning algorithm has a good performance in having a significant gain in SNR at colored noise.

AB - This paper proposes a fast discrete-time learning algorithm for speech enhancement of single-channel noisy speech signal, based on a noise constrained least squares estimate. Unlike existing learning algorithms for the noise constrained estimate, the proposed discrete-time learning algorithm has a low complexity and fast speed. Simulation results show that the proposed discrete-time learning algorithm has a faster speed than the existing learning algorithms for speech enhancement. Moreover, the proposed discrete-time learning algorithm has a good performance in having a significant gain in SNR at colored noise.

KW - discrete-time systems

KW - signal processing

KW - speech processing systems

UR - http://handle.uws.edu.au:8081/1959.7/uws:29267

U2 - 10.1109/IJCNN.2014.6889451

DO - 10.1109/IJCNN.2014.6889451

M3 - Conference Paper

SN - 9781479914845

SP - 3149

EP - 3154

BT - Proceedings of the 2014 International Joint Conference on Neural Networks, July 6-11, 2014, Beijing, China

PB - IEEE

T2 - International Joint Conference on Neural Networks

Y2 - 6 July 2014

ER -

A fast discrete-time learning algorithm for speech enhancement using noise constrained parameter estimation

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this