American Institute of Mathematical Sciences

Advanced
July  2009, 5(3): 671-682. doi: 10.3934/jimo.2009.5.671

A multi-filter system for speech enhancement under low signal-to-noise ratios

K. F. C. Yiu 1, , K. Y. Chan 2, , S. Y. Low 3, and  S. Nordholm 3,

1. 

Department of Applied Mathematics, The Hong Kong Polytechnic University, Hunghom, Hong Kong, China
2. 

Department of Applied Mathematics, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China
3. 

Western Australian Telecommunications Research Institute, A joint venture between The University of Western Australia, and Curtin University of Technology, Perth, Australia, Australia

Received  March 2008 Revised  March 2009 Published  June 2009

In this paper, the problem of deteriorating performance of speech recognition under very low signal-to-noise ratios (SNR) is considered. In particular, for a given pre-trained speech recognizer and for a finite set of speech commands, we show that popular noise reduction methods have a mixed performance in speech recognition accuracy under very low SNR. Although most noise reduction methods are attempting to reduce speech distortion or to increase noise suppression, it does not necessarily improve speech recognition accuracy very much due to the complexity of the recognizer. We propose a new hybrid algorithm to optimize on the speech recognition accuracy directly by mixing different noise reduction methods together. We show that this method can indeed improve the accuracy significantly.
Keywords: Noise reduction, Optimization., Speech recognition, Speech enhancement.
Mathematics Subject Classification: 90C90, 68T1.
Citation: K. F. C. Yiu, K. Y. Chan, S. Y. Low, S. Nordholm. A multi-filter system for speech enhancement under low signal-to-noise ratios. Journal of Industrial and Management Optimization, 2009, 5 (3) : 671-682. doi: 10.3934/jimo.2009.5.671
[1]

Hai Huyen Dam, Siow Yong Low, Sven Nordholm. Two-level optimization approach with accelerated proximal gradient for objective measures in sparse speech reconstruction. Journal of Industrial and Management Optimization, 2022, 18 (5) : 3701-3717. doi: 10.3934/jimo.2021131
[2]

Meng Yu, Jack Xin. Stochastic approximation and a nonlocally weighted soft-constrained recursive algorithm for blind separation of reverberant speech mixtures. Discrete and Continuous Dynamical Systems, 2010, 28 (4) : 1753-1767. doi: 10.3934/dcds.2010.28.1753
[3]

Rentsen Enkhbat, Evgeniya A. Finkelstein, Anton S. Anikin, Alexandr Yu. Gornov. Global optimization reduction of generalized Malfatti's problem. Numerical Algebra, Control and Optimization, 2017, 7 (2) : 211-221. doi: 10.3934/naco.2017015
[4]

Valerii Maltsev, Michael Pokojovy. On a parabolic-hyperbolic filter for multicolor image noise reduction. Evolution Equations and Control Theory, 2016, 5 (2) : 251-272. doi: 10.3934/eect.2016004
[5]

Martin Redmann, Peter Benner. Approximation and model order reduction for second order systems with Levy-noise. Conference Publications, 2015, 2015 (special) : 945-953. doi: 10.3934/proc.2015.0945
[6]

Martin Redmann, Melina A. Freitag. Balanced model order reduction for linear random dynamical systems driven by Lévy noise. Journal of Computational Dynamics, 2018, 5 (1&2) : 33-59. doi: 10.3934/jcd.2018002
[7]

Amine Laghrib, Lekbir Afraites, Aissam Hadri, Mourad Nachaoui. A non-convex PDE-constrained denoising model for impulse and Gaussian noise mixture reduction. Inverse Problems and Imaging, , () : -. doi: 10.3934/ipi.2022031
[8]

Jian Lu, Lixin Shen, Chen Xu, Yuesheng Xu. Multiplicative noise removal with a sparsity-aware optimization model. Inverse Problems and Imaging, 2017, 11 (6) : 949-974. doi: 10.3934/ipi.2017044
[9]

Ziyuan Zhang, Liying Yu. Joint emission reduction dynamic optimization and coordination in the supply chain considering fairness concern and reference low-carbon effect. Journal of Industrial and Management Optimization, 2021  doi: 10.3934/jimo.2021155
[10]

Konovenko Nadiia, Lychagin Valentin. Möbius invariants in image recognition. Journal of Geometric Mechanics, 2017, 9 (2) : 191-206. doi: 10.3934/jgm.2017008
[11]

Juan Carlos De los Reyes, Carola-Bibiane Schönlieb. Image denoising: Learning the noise model via nonsmooth PDE-constrained optimization. Inverse Problems and Imaging, 2013, 7 (4) : 1183-1214. doi: 10.3934/ipi.2013.7.1183
[12]

Wei Wang, Na Sun, Michael K. Ng. A variational gamma correction model for image contrast enhancement. Inverse Problems and Imaging, 2019, 13 (3) : 461-478. doi: 10.3934/ipi.2019023
[13]

Anna Lisa Amadori. Contour enhancement via a singular free boundary problem. Conference Publications, 2007, 2007 (Special) : 44-53. doi: 10.3934/proc.2007.2007.44
[14]

Xiaoning Zhu, Zhongyi Li, Jian Sun. Expression recognition method combining convolutional features and Transformer. Mathematical Foundations of Computing, 2022  doi: 10.3934/mfc.2022018
[15]

Xuefeng Zhang, Hui Yan. Image enhancement algorithm using adaptive fractional differential mask technique. Mathematical Foundations of Computing, 2019, 2 (4) : 347-359. doi: 10.3934/mfc.2019022
[16]

Wenzhong Zhu, Huanlong Jiang, Erli Wang, Yani Hou, Lidong Xian, Joyati Debnath. X-ray image global enhancement algorithm in medical image classification. Discrete and Continuous Dynamical Systems - S, 2019, 12 (4&5) : 1297-1309. doi: 10.3934/dcdss.2019089
[17]

Joseph Malinzi, Rachid Ouifki, Amina Eladdadi, Delfim F. M. Torres, K. A. Jane White. Enhancement of chemotherapy using oncolytic virotherapy: Mathematical and optimal control analysis. Mathematical Biosciences & Engineering, 2018, 15 (6) : 1435-1463. doi: 10.3934/mbe.2018066
[18]

Josselin Garnier, George Papanicolaou. Resolution enhancement from scattering in passive sensor imaging with cross correlations. Inverse Problems and Imaging, 2014, 8 (3) : 645-683. doi: 10.3934/ipi.2014.8.645
[19]

Yifan Xu. Algorithms by layer-decomposition for the subgraph recognition problem with attributes. Journal of Industrial and Management Optimization, 2005, 1 (3) : 337-343. doi: 10.3934/jimo.2005.1.337
[20]

Marcello Delitala, Tommaso Lorenzi. Recognition and learning in a mathematical model for immune response against cancer. Discrete and Continuous Dynamical Systems - B, 2013, 18 (4) : 891-914. doi: 10.3934/dcdsb.2013.18.891

2021 Impact Factor: 1.411

Tools

Metrics

  • PDF downloads (73)
  • HTML views (0)
  • Cited by (6)

Other articles
by authors

[Back to Top]

Copyright © 2022 American Institute of Mathematical Sciences | Privacy Policy