CFP last date
20 January 2025
Call for Paper
February Edition
IJCA solicits high quality original research papers for the upcoming February edition of the journal. The last date of research paper submission is 20 January 2025

Submit your paper
Know more
The week's pick
Responsive image
SFLA-Based Line Balancing and Task Optimization in Master-Slave Controlled Hanger Transportation Systems for Garment Production

Duc Hoang Nguyen
Random Articles
Reseach Article

Highly Training Algorithm for Enhancement of Speech Signal Data (HTA-ESSD)

by Kumbhar Trupti Sambhaji, Veena C.S.
journal cover thumbnail

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 174 - Number 24
Year of Publication: 2021
Authors: Kumbhar Trupti Sambhaji, Veena C.S.
10.5120/ijca2021921137

Kumbhar Trupti Sambhaji, Veena C.S. . Highly Training Algorithm for Enhancement of Speech Signal Data (HTA-ESSD). International Journal of Computer Applications. 174, 24 ( Mar 2021), 1-5. DOI=10.5120/ijca2021921137

@article{ 10.5120/ijca2021921137,
author = { Kumbhar Trupti Sambhaji, Veena C.S. },
title = { Highly Training Algorithm for Enhancement of Speech Signal Data (HTA-ESSD) },
journal = { International Journal of Computer Applications },
issue_date = { Mar 2021 },
volume = { 174 },
number = { 24 },
month = { Mar },
year = { 2021 },
issn = { 0975-8887 },
pages = { 1-5 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume174/number24/31819-2021921137/ },
doi = { 10.5120/ijca2021921137 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:22:56.820131+05:30
%A Kumbhar Trupti Sambhaji
%A Veena C.S.
%T Highly Training Algorithm for Enhancement of Speech Signal Data (HTA-ESSD)
%J International Journal of Computer Applications
%@ 0975-8887
%V 174
%N 24
%P 1-5
%D 2021
%I Foundation of Computer Science (FCS), NY, USA
Abstract

The enhancement of speech aims to maximize the quality of speech by utilizing HTA (Highly Training Algorithm). The main aim of enhancement is to maximize the intelligibility or perceptual quality of the speech signal data. We represent HTA, aimed at fast removal and very effective of background noise from the signal-channel of speech signal data based on analytically determined output-weights and randomly selected-hidden units. The feature learning with HTA may not be effective for the natural signals, even with the larger number of the hidden nodes, C-HTA (Classified Highly Training Algorithm) are employed by leveraging the sparse auto-encoders. This work is mainly to apply C-HTA and HTA to enhance the speech-signal data. The proposed HTA is evaluated on Aurora database at three SNRs. We also compare our introduced algorithm with many state-art-methods.

References
  1. Mosayyebpour, S.; Esmaeili, M.; Gulliver, T.A. Single-microphone early and late reverberation suppression in noisy speech. IEEE Trans. Audio Speech Lang. Process. 2012, 21, 322–335.
  2. Shishir Banchhor, Jimish Dodia, and Darshana Gowda. Gui based performance analysis of speech enhancement techniques. International Journal of Scientific and Research Publications, 3(9):1, 2013.
  3. Hardik Panchmatia, Karan Gaikar, and Dharmesh Patel. Comparison of different speech enhancement techniques. Imperial Journal of Interdisciplinary Research, 2(5), 2016.
  4. P. C. Loizou, Speech Enhancement: Theory and Practice. NewYork: CRC, 2007.
  5. H. Chung. R. Badeau, E. Plourde and B. Champagne, “Training and compensation of class-conditioned NMF bases for speech enhancement,” Neurocomputing, vol. 284, pp. 107-118, Apr. 2018.
  6. Xu, Yong, et al. "An Experimental Study on Speech Enhancement Based on Deep Neural Networks." Signal Processing Letters IEEE 21.1(2014):65-68.
  7. X. Lu, Y. Tsao, S. Matsuda and C. Hori, “Speech enhancement based on deep denoising autoencoder,” in Proc. Interspeech, pp. 436-440, Aug. 2013.
  8. S. -W. Fu, Y. Tsao and X. Lu, “SNR-aware convolutional neural network modeling for speech enhancement,” in Proc. Interspeech, pp. 3768-3772, Sep. 2016.
  9. M. Kolbaek, D. Yu, Z. -H. Tan and J. Jensen, “Joint separation and denoising of noisy multi-talker speech using recurrent neural networks and permutation invariant training,” in Proc. MLSP, six pages, Sep. 2017.
  10. S. Nie, S. Liang, H. Li, X. Zhang, Z. Zhang,W. J. Liu and L. K. Dong, “Exploiting spectro-temporal structures using NMF for DNN-based supervised speech separation,” in Proc. ICASSP, pp. 469-473, Mar. 2016.
  11. W. Han, X. Zhang, M. Sun, W. Shi, X. Chen and Y. Hu, “Perceptual improvement of deep neural networks for monaural speech enhancement,” in Proc. Int. Workshop on Acoustic Signal Enhancement, five pages, Sep. 2016.
  12. R. Ram, M. N.Mohanty, Deep Neural Network based Speech Enhancement. Int. Conf. On Cognitive Informatics & Soft Computing, 2017. (Accepted).
  13. H. Hirsch, and D. Pearce (2000). “The Aurora Experimental Framework for the Performance Evaluation of Speech Recognition Systems under Noisy Conditions.” ISCA ITRW ASR2000, Paris, France, September 18-20.
  14. Adda Saadoune, Abderrahmane Amrouche, and Sid-Ahmed Selouani. Perceptual subspace speech enhancement using variance of the reconstruction error. Digital Signal Processing, 24:187 – 196, 2014.
  15. Sudeep Surendran and T. Kishore Kumar. Variance normalized perceptual subspace speech enhancement. AEU - International Journal of Electronics and Communications, 74(Supplement C):44 – 54, 2017.
  16. Y. H. Goh, P. Raveendran, and Y. L. Goh. Robust speech recognition system using bidirectional kalman filter. IET Signal Processing, 9(6):491–497, 2015.
  17. S. Surendran and T. K. Kumar, "Oblique Projection and Cepstral Subtraction in Signal Subspace Speech Enhancement for Colored Noise Reduction," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 26, no. 12, pp. 2328-2340, Dec. 2018.
Index Terms

Computer Science
Information Sciences

Keywords

Enhancement of speech HTA C-HTA

Powered by PhDFocusTM