On a Real-Time Blind Signal Separation Noise Reduction System

Blind signal separation has been studied extensively in order to tackle the cocktail party problem. It explores spatial diversity of the received mixtures of sources by different sensors. By using the kurtosis measure, it is possible to select the source of interest out of a number of separated BSS outputs. Further noise cancellation can be achieved by adding an adaptive noise canceller (ANC) as postprocessing. However, the computation is rather intensive and an online implementation of the overall system is not straightforward. This paper intends to fill the gap by developing an FPGA hardware architecture to implement the system. Subband processing is explored and detailed functional operations are profiled carefully. The final proposed FPGA system is able to handle signals with sample rate over 20000 samples per second.

[1]  Yun Liang,et al.  Design Space exploration of FPGA-based accelerators with multi-level parallelism , 2017, Design, Automation & Test in Europe Conference & Exhibition (DATE), 2017.

[2]  Lucas C. Parra,et al.  Convolutive blind separation of non-stationary sources , 2000, IEEE Trans. Speech Audio Process..

[3]  Emmanuel Vincent,et al.  A Consolidated Perspective on Multimicrophone Speech Enhancement and Source Separation , 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[4]  Rainer Martin,et al.  Noise power spectral density estimation based on optimal smoothing and minimum statistics , 2001, IEEE Trans. Speech Audio Process..

[5]  Shrikanth S. Narayanan,et al.  Robust Voice Activity Detection Using Long-Term Signal Variability , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[6]  Kiyohiro Shikano,et al.  Musical-Noise-Free Speech Enhancement Based on Optimized Iterative Spectral Subtraction , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[7]  Bangyan Zhou,et al.  A permutation algorithm based on dynamic time warping in speech frequency-domain blind source separation , 2017, Speech Commun..

[8]  Sven Nordholm,et al.  Convolutive blind signal separation with post-processing , 2004, IEEE Transactions on Speech and Audio Processing.

[9]  André B. J. Kokkeler,et al.  Adaptive Beamforming Using the Reconfigurable MONTIUM TP , 2010, 2010 13th Euromicro Conference on Digital System Design: Architectures, Methods and Tools.

[10]  Georgi Gaydadjiev,et al.  A reconfigurable beamformer for audio applications , 2009, 2009 IEEE 7th Symposium on Application Specific Processors.

[11]  Shoko Araki,et al.  The fundamental limitation of frequency domain blind source separation for convolutive mixtures of speech , 2003, IEEE Trans. Speech Audio Process..

[12]  T. Ens,et al.  Blind signal separation : statistical principles , 1998 .

[13]  S. Nordholm,et al.  A spatial filtering approach to robust adaptive beaming , 1992 .

[14]  Chiu-Wing Sham,et al.  Low-power reconfigurable acceleration of robust frequency-domain echo cancellation on FPGA , 2010, The 2010 International Conference on Green Circuits and Systems.

[15]  Jae S. Lim,et al.  Speech enhancement , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[16]  Brent E. Nelson,et al.  FPGA-based sonar processing , 1998, FPGA '98.

[17]  Jørgen Arendt Jensen,et al.  A new architecture for a single-chip multi-channel beamformer based on a standard FPGA , 2001, 2001 IEEE Ultrasonics Symposium. Proceedings. An International Symposium (Cat. No.01CH37263).

[18]  Sven Nordholm,et al.  Robust microphone array using subband adaptive beamformer and spectral subtraction , 2002, The 8th International Conference on Communication Systems, 2002. ICCS 2002..

[19]  L. J. Griffiths,et al.  An alternative approach to linearly constrained adaptive beamforming , 1982 .

[20]  Sven Nordholm,et al.  A blind approach to joint noise and acoustic echo cancellation , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[21]  Hang Zhang,et al.  Non-stationary sources separation based on maximum likelihood criterion using source temporal-spatial model , 2018, Neurocomputing.

[22]  Rajesh Mehra,et al.  Blind Audio Source Separation in Time Domain using ICA Decomposition , 2015 .

[23]  Jie Yin,et al.  Blind Source Separation and Identification for Speech Signals , 2017, 2017 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC).

[24]  Sven Nordholm,et al.  FPGA multi-filter system for speech enhancement via multi-criteria optimization , 2014, Appl. Soft Comput..

[25]  Sven Nordholm,et al.  Adaptive microphone array with noise statistics updates , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).

[26]  Michael Hubner,et al.  Multi-level parallelism analysis and system-level simulation for many-core Vision processor design , 2016, 2016 5th Mediterranean Conference on Embedded Computing (MECO).