The Experts below are selected from a list of 46206 Experts worldwide ranked by ideXlab platform

Michael Mason - One of the best experts on this subject based on the ideXlab platform.

  • small footprint implementation of dual microphone delay and sum Beamforming for in car speech enhancement
    International Conference on Acoustics Speech and Signal Processing, 2010
    Co-Authors: J Whittington, John Devlin, Michael Mason
    Abstract:

    For effective speech processing in an automotive environment, speech enhancement is necessary due to significant levels of background noise. In this paper, we present a cost effective small footprint implementation of one particular speech enhancement technique: dual microphone Delay-and-Sum Beamforming. In order to save resources, the implementation utilizes the overlapping frame property used in speech processing systems. The implementation also exhibits a simple interconnection structure leading to even greater resource saving. Experiment results show that the proposed design can produce enhanced output very close to that generated by a theoretical (floating-point) model while only requiring a modest hardware resource usage.

  • ICASSP - Small footprint implementation of dual-microphone Delay-and-Sum Beamforming for in-car speech enhancement
    2010 IEEE International Conference on Acoustics Speech and Signal Processing, 2010
    Co-Authors: J Whittington, John Devlin, Michael Mason
    Abstract:

    For effective speech processing in an automotive environment, speech enhancement is necessary due to significant levels of background noise. In this paper, we present a cost effective small footprint implementation of one particular speech enhancement technique: dual microphone Delay-and-Sum Beamforming. In order to save resources, the implementation utilizes the overlapping frame property used in speech processing systems. The implementation also exhibits a simple interconnection structure leading to even greater resource saving. Experiment results show that the proposed design can produce enhanced output very close to that generated by a theoretical (floating-point) model while only requiring a modest hardware resource usage.

  • FPGA implementation of dual-microphone Delay-and-Sum Beamforming for in-car speech enhancement and recognition
    2009
    Co-Authors: J Whittington, Ivan Himawan, Tristan Kleinschmidt, Michael Mason
    Abstract:

    In an automotive environment, the performance of a speech recognition system is affected by environmental noise if the speech signal is acquired directly from a microphone. Speech enhancement techniques are therefore necessary to improve the speech recognition performance. In this paper, a field-programmable gate array (FPGA) implementation of dual-microphone Delay-and-Sum Beamforming (DASB) for speech enhancement is presented. As the first step towards a cost-effective solution, the implementation described in this paper uses a relatively high-end FPGA device to facilitate the verification of various design strategies and parameters. Experimental results show that the proposed design can produce output waveforms close to those generated by a theoretical (floating-point) model with modest usage of FPGA resources. Speech recognition experiments are also conducted on enhanced in-car speech waveforms produced by the FPGA in order to compare recognition performance with the floating-point representation running on a PC.

Moeness G Amin - One of the best experts on this subject based on the ideXlab platform.

  • CAMSAP - A Beamforming approach to imaging of stationary indoor scenes under known building layout
    2013 5th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2013
    Co-Authors: Fauzia Ahmad, Moeness G Amin, Traian Dogaru
    Abstract:

    In this paper, we exploit a priori knowledge of building layout for imaging of stationary scenes associated with through-the-wall radar imaging and urban sensing. More specifically, the support of the part of the image corresponding to the exterior and interior walls is assumed known. This information may be available either through building blueprints or from prior surveillance operations. The contributions of the exterior and interior walls are removed from the data through use of projection matrices, which are determined from wall specific dictionaries. The wall-free data is then processed by Delay-and-Sum Beamforming to obtain the image of the stationary indoor scene. Numerical electromagnetic data is used to demonstrate the effectiveness of the proposed approach.

  • An SVD-based approach for mitigating wall reflections in through-the-wall radar imaging
    2011 IEEE RadarCon (RADAR), 2011
    Co-Authors: Fok Hing Chi Tivive, Abdesselam Bouzerdoum, Moeness G Amin
    Abstract:

    In this paper, we mitigate wall EM returns in through-the-wall radar imaging (TWRI) using singular value decomposition (SVD). To suppress wall reflections, the SVD is applied to the B-scan matrix of the received signals. The signal space is decomposed into three subspaces: the clutter subspace, the target subspace, and the noise subspace. Then, a set of normalized and smoothed eigen-components are combined to produce the target signal. Finally, Delay-and-Sum Beamforming is applied to the reconstructed B-scan matrix to form the image. Experimental results demonstrate that the proposed method is effective in removing background, reducing clutter, and high-lighting the targets.

  • target detection in single and multiple view through the wall radar imaging
    IEEE Transactions on Geoscience and Remote Sensing, 2009
    Co-Authors: Christian Debes, Moeness G Amin, Abdelhak M Zoubir
    Abstract:

    A detector of targets behind walls and in enclosed structures is presented. The detector is applied to through-the-wall radar images obtained by wideband delay and sum Beamforming. We consider the detection problem using single- and multiple-view imaging. The statistics of noise, clutter, and target images are examined and formulated using sample scenes. The effects of wall parameter errors on the image statistics are shown. An iterative detection scheme, which adapts itself to the image statistics, is presented. The proposed detection schemes are evaluated using real data.

  • three dimensional wideband Beamforming for imaging through a single wall
    IEEE Geoscience and Remote Sensing Letters, 2008
    Co-Authors: Fauzia Ahmad, Yimin D Zhang, Moeness G Amin
    Abstract:

    Through-the-wall imaging and urban sensing is an emerging area of research and development. The incorporation of the effects of signal propagation through wall material in producing an indoor image is important for reliable through-the-wall mission operations. We have previously analyzed wall effects, such as refraction and change in propagation speed, and designed a wideband beamformer for 2D imaging using line arrays. In this letter, we extend the analysis to 3D imaging via Delay-and-Sum Beamforming in the presence of a single uniform wall. The third dimension provides valuable information on target heights that can be used for enhancing target discrimination/identification. Supporting simulation results are provided.

J Whittington - One of the best experts on this subject based on the ideXlab platform.

  • small footprint implementation of dual microphone delay and sum Beamforming for in car speech enhancement
    International Conference on Acoustics Speech and Signal Processing, 2010
    Co-Authors: J Whittington, John Devlin, Michael Mason
    Abstract:

    For effective speech processing in an automotive environment, speech enhancement is necessary due to significant levels of background noise. In this paper, we present a cost effective small footprint implementation of one particular speech enhancement technique: dual microphone Delay-and-Sum Beamforming. In order to save resources, the implementation utilizes the overlapping frame property used in speech processing systems. The implementation also exhibits a simple interconnection structure leading to even greater resource saving. Experiment results show that the proposed design can produce enhanced output very close to that generated by a theoretical (floating-point) model while only requiring a modest hardware resource usage.

  • ICASSP - Small footprint implementation of dual-microphone Delay-and-Sum Beamforming for in-car speech enhancement
    2010 IEEE International Conference on Acoustics Speech and Signal Processing, 2010
    Co-Authors: J Whittington, John Devlin, Michael Mason
    Abstract:

    For effective speech processing in an automotive environment, speech enhancement is necessary due to significant levels of background noise. In this paper, we present a cost effective small footprint implementation of one particular speech enhancement technique: dual microphone Delay-and-Sum Beamforming. In order to save resources, the implementation utilizes the overlapping frame property used in speech processing systems. The implementation also exhibits a simple interconnection structure leading to even greater resource saving. Experiment results show that the proposed design can produce enhanced output very close to that generated by a theoretical (floating-point) model while only requiring a modest hardware resource usage.

  • FPGA implementation of dual-microphone Delay-and-Sum Beamforming for in-car speech enhancement and recognition
    2009
    Co-Authors: J Whittington, Ivan Himawan, Tristan Kleinschmidt, Michael Mason
    Abstract:

    In an automotive environment, the performance of a speech recognition system is affected by environmental noise if the speech signal is acquired directly from a microphone. Speech enhancement techniques are therefore necessary to improve the speech recognition performance. In this paper, a field-programmable gate array (FPGA) implementation of dual-microphone Delay-and-Sum Beamforming (DASB) for speech enhancement is presented. As the first step towards a cost-effective solution, the implementation described in this paper uses a relatively high-end FPGA device to facilitate the verification of various design strategies and parameters. Experimental results show that the proposed design can produce output waveforms close to those generated by a theoretical (floating-point) model with modest usage of FPGA resources. Speech recognition experiments are also conducted on enhanced in-car speech waveforms produced by the FPGA in order to compare recognition performance with the floating-point representation running on a PC.

Parham Aarabi - One of the best experts on this subject based on the ideXlab platform.

  • Structural analysis of multisensor arrays for speech separation applications
    Multisensor Multisource Information Fusion: Architectures Algorithms and Applications 2003, 2003
    Co-Authors: Maryam M. Shanechi, Parham Aarabi
    Abstract:

    This paper analyzes the Beamforming separation effectiveness of several different microphone array configurations. These configurations consist of 4, 8, and 16 microphones placed in a plane for two-dimensional speech separation, with inter-microphone distances varying from 10cm to 160cm in logarithmic step sizes. It is discovered that the linear and bi-linear arrays result in the largest signal-to-noise ratio (SNR) gain after Delay-and-Sum Beamforming in the case of speech signal and speech noise. Also, simulations show that larger inter-microphone distances result in a higher SNR gain, although the practicality of the higher inter-microphone distances is limited for certain applications where the array size is constrained.

  • ICASSP (1) - Multiple-microphone time-varying filters for robust speech recognition
    2004 IEEE International Conference on Acoustics Speech and Signal Processing, 1
    Co-Authors: Calvin Yiu-kit Lai, Parham Aarabi
    Abstract:

    A multiple microphone time varying filter that is an extension of the dual-microphone speech enhancement technique of P. Aarabi et al. (see Proceedings of the IEEE Conference on Multimedia and Expo, Baltimore, Maryland, July 2003) is proposed and experimentally analyzed. The technique utilizes information regarding the locations of the speech source of interest and the microphones to compute a time varying filter that results in substantial noise reduction over other speech enhancement techniques such as Delay-and-Sum Beamforming and superdirective Beamforming. For example, digit recognition results in an environment with two speakers and a reverberation time of 0.1s show a recognition accuracy rate increase of 25.2% over Delay-and-Sum Beamforming and an increase of 26.5% over superdirective Beamforming using six microphones.

  • ICASSP (1) - Robust digit recognition using phase-dependent time-frequency masking
    2003 IEEE International Conference on Acoustics Speech and Signal Processing 2003. Proceedings. (ICASSP '03)., 1
    Co-Authors: G. Shi, Parham Aarabi
    Abstract:

    A technique using the time-frequency phase information of two microphones is proposed to estimate an ideal time-frequency mask using time-delay-of-arrival (TDOA) of the signal of interest. At a signal-to-noise ratio (SNR) of 0 dB, the proposed technique using two microphones achieves a digit recognition rate (average over 5 speakers, each speaking 20-30 digits) of 71%. In contrast, Delay-and-Sum Beamforming only achieves a 40% recognition rate with two microphones and 60% with four microphones. Superdirective Beamforming achieves a 44% recognition rate with two microphones and 65% with four microphones.

Abdelhak M Zoubir - One of the best experts on this subject based on the ideXlab platform.

  • EUSIPCO - Fast wideband near-field imaging using the non-equispaced FFT with application to through-wall radar
    2011
    Co-Authors: Michael Leigsnering, Abdelhak M Zoubir
    Abstract:

    High resolution wideband near-field imaging requires wideband signals and large array apertures. Hence, a large amount of data needs to be processed in the image formation step. The standard delay and sum beamformer scales linearly with both output size and number of measurements resulting in high computational load. We propose a novel approach for image formation reducing the numerical complexity based on the non-equispaced fast Fourier transform (NFFT). The conventional delay and sum Beamforming algorithm is reformulated such that the computational efficiency of the NFFT is exploited. Experimental results from a through-the-wall radar imaging system show a good improvement of the speed whereas the introduced error is kept very low.

  • target detection in single and multiple view through the wall radar imaging
    IEEE Transactions on Geoscience and Remote Sensing, 2009
    Co-Authors: Christian Debes, Moeness G Amin, Abdelhak M Zoubir
    Abstract:

    A detector of targets behind walls and in enclosed structures is presented. The detector is applied to through-the-wall radar images obtained by wideband delay and sum Beamforming. We consider the detection problem using single- and multiple-view imaging. The statistics of noise, clutter, and target images are examined and formulated using sample scenes. The effects of wall parameter errors on the image statistics are shown. An iterative detection scheme, which adapts itself to the image statistics, is presented. The proposed detection schemes are evaluated using real data.