Speech Processing Using FD Independent Component Analysis Algorithm

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    Speech is most mighty and usual medium to alternate the information amongst individuals. The speech method additionally goes underneath the system of some application tools to reward the know-how in effective approach. Audio supply separation is the crisis of computerized separation of audio sources gift in a room, making use of a set of differently placed microphones, shooting the auditory scene. On this paper, proposed a novel quick Frequency domain ICA algorithm using two viable implementations. Additionally, a effective possibility Ratio soar approach to the permutation difficulty of ordering sources along the frequency axis is provided. The suggestion of exploiting the additional geometrical expertise, such because the microphone spacing, so as to participate in permutation alignment using beam forming is then examined and ultimately discussed accuracy, sensitivity and Throughput ration values are evaluate with current and proposed ways.

     

     

     


  • Keywords


    frequency domain, speech processing, independent component analysis.

  • References


      [1] Yi Hu and Philipos C. Loizou, “Subjective comparison and evaluation of speech enhancement algorithms” IEEE Trans.Speech Audio Proc.2007:49(7): 588–601.

      [2] Yariv Ephraim, Hanoch Lev-Ari and William J.J. Roberts “A Brief Survey of Speech Enhancement” IEEE Sig. Proc. Let., vol. 10,pp. 104-106, April 2003 s.

      [3] Yoon. B-Y.; Tashev, I. & Acero, A. (2007) Robust Adaptive Beamforming Algorithm Using Instantaneous Direction Of Arrival With Enhanced Noise Suppression Capability. IEEE International Conference on Acoustics, Speech and Signal Processing 1:I-133–I136.

      [4] Reddy, D.R, “Speech recognition by machine: A review”, Proceedings of IEEE (Volume: 64, Issue: 4) ISSN: 0018-9219.

      [5] Young, S.J, “Robust continuous speech recognition using parallel model”, IEEE Transactions on Speech and Audio Processing (Volume: 4, Issue: 5).

      [6] Bassam A. Q. Al-Qatab , Raja N. Ainon, “Arabic Speech Recognition Using Hidden Markov Model Toolkit(HTK)”, 978-1-4244-6716-711 0/$26.00 ©2010 IEEE.

      [7] Chibelushi, C.C. “A review of speech-based bimodal recognition”, 2002 IEEE Transactions on Multimedia, (Volume: 4, Issue: 1).

      [8] Iosif Mporas,”Dynamic Selection of A Speech Enhancement Method For Robust Speech Recognition In Moving Motorcycle Environment”, ICASSP 2011 978-1-4577-0539- 7/11©2011 IEEE.

      [9] Ciira wa Maina,”Joint Speech Enhancement and Speaker Identification Using Approximate Bayesian Inference”, IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING 1558-7916© 2010 IEEE.

      [10] Fuming Chen, Sheng Li, Chuantao Li, Miao Liu, Zhao Li, Huijun Xue, Xijing Jing and Jianqi Wang, “A Novel Method for Speech Acquisition and Enhancement by 94 GHz Millimeter-Wave Sensor”, Published: 31 December 2015 Academic Editor: Vittorio M. N. Passaro.

      [11] Pejman Mowlaee and Rahim Saeidi, “Iterative Closed-Loop Phase-Aware Single-Channel Speech Enhancement”, IEEE SIGNAL PROCESSING LETTERS, VOL. 20, NO. 12, DECEMBER 2013.

      [12] Ruiyu Liang, Ruxue Guo, Ji Xi, Yue Xie and Li Zhao, “Self-Fitting Algorithm for Digital Hearing Aid Based on Interactive Evolutionary Computation and Expert System”, Published: 9 March 2017.

      [13] Thijs van de Laar and Bert de Vries, “A Probabilistic Modeling Approach to Hearing Loss Compensation”, Copyright (c) 2016 IEEE.

      [14] Sunita Dixit, Dr. MD Yusuf Mulge, “Review on Speech Enhancement Techniques”, International Journal of Computer Science and Mobile Computing, Vol.3 Issue.8, August- 2014, pg. 285-290.

      [15] Stephan Liwicki Georgios Tzimiropoulos Stefanos Zafeiriou Maja Pantic Barkatullah Qureshi, “Euler Principal Component Analysis”, Received: 5 December 2011 / Accepted: 8 August 2.


 

View

Download

Article ID: 28680
 
DOI: 10.14419/ijet.v7i2.32.28680




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.