Improving quality and intelligibility of speech using single microphone for the broadband fMRI noise at low SNR

Functional Magnetic Resonance Imaging (fMRI) is used in many diagnostic procedures for neurological related disorders. Strong broadband acoustic noise generated during fMRI scan interferes with the speech communication between the physician and the patient. In this paper, we propose a single microphone Speech Enhancement (SE) technique which is based on the supervised machine learning technique and a statistical model based SE technique. The proposed algorithm is robust and computationally efficient and has capability to run in real-time. Objective and Subjective evaluations show that the proposed SE method outperforms the existing state-of-the-art algorithms in terms of quality and intelligibility of the recovered speech at low Signal to Noise Ratios (SNRs).

[1]  V. R. Ramachandran,et al.  Objective and subjective evaluation of adaptive speech enhancement methods for functional MRI , 2010, Journal of magnetic resonance imaging : JMRI.

[2]  I. Panahi,et al.  Two-channel multi-stage speech enhancement for noisy fMRI environment , 2013, Canadian Journal of Electrical and Computer Engineering.

[3]  Nishank Pathak.  Real-time speech enhancement for MRI noise environment , 2009 .

[4]  Issa M. S. Panahi,et al.  Two-stage data-driven single channel speech enhancement with cepstral analysis pre-processing , 2015, 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[5]  Yang Lu,et al.  An algorithm that improves speech intelligibility in noise for normal-hearing listeners. , 2009, The Journal of the Acoustical Society of America.

[6]  David Malah,et al.  Speech enhancement using a minimum mean-square error log-spectral amplitude estimator , 1984, IEEE Trans. Acoust. Speech Signal Process..

[7]  Tzi-Dar Chiueh,et al.  Active cancellation system of acoustic noise in MR imaging , 1999, IEEE Transactions on Biomedical Engineering.

[8]  R. Bowtell,et al.  “sparse” temporal sampling in auditory fMRI , 1999, Human brain mapping.

[9]  M McJury,et al.  The use of active noise control (ANC) to reduce acoustic noise generated during MRI scanning: some initial results. , 1997, Magnetic resonance imaging.

[10]  Manuel Rosa-Zurera,et al.  A computationally-efficient single-channel speech enhancement algorithm for monaural hearing aids , 2014, 2014 22nd European Signal Processing Conference (EUSIPCO).

[11]  Birger Kollmeier,et al.  SNR estimation based on amplitude modulation analysis with applications to noise suppression , 2003, IEEE Trans. Speech Audio Process..

[12]  Philipos C. Loizou,et al.  Improving Speech Intelligibility in Noise Using a Binary Mask That Is Based on Magnitude Spectrum Constraints , 2010, IEEE Signal Processing Letters.

[13]  R. Weisskoff,et al.  Improved auditory cortex imaging using clustered volume acquisitions , 1999, Human brain mapping.

[14]  Yi Hu,et al.  Multi-Band Speech Enhancement for Functional MRI , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[15]  Philipos C. Loizou,et al.  Speech Enhancement: Theory and Practice , 2007 .

[16]  M. Mintun,et al.  Brain work and brain imaging. , 2006, Annual review of neuroscience.

[17]  Issa M. S. Panahi,et al.  A multichannel speech enhancement method for functional MRI systems using a distributed microphone array , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[18]  Issa M. S. Panahi,et al.  Speech Enhancement in Functional MRI Environment using Adaptive Sub-Band Algorithms , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[19]  Issa M. S. Panahi,et al.  Single channel speech enhancement technique for low SNR quasi-periodic noise based on reduced order linear prediction , 2015, 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP).