A New Residual Convolutional Neural Network-Based Speech Improvement

M. Balasubrahmanyam

doi:10.55524/ijircst.2022.10.6.7

Abstract

Among the most crucial methods for denoising a noisy voice signal and enhancing its quality is speech enhancement. This study makes use of Adaptive Residual Neural Network technique to reduces maximum off background noise. This method continuously monitors the background noise depends upon the environmental changes using SNR parameter. It has two functions first one is non linear functions followed by convolutional neural networks and second one is linearity followed due to Residual neural networks. By using these factors remove background noise even SNR is low conditions. Compared to other techniques this technique is new,fastest, requires less training and also reduces size.

Keywords

Convolutional Neural Networks, Liver, Segmentation, Tumor, ResNet, Deep Learning.

References

H. Levitt, "Noise reduct ion in hearing aids: A review," Journal of rehabilitation research and development.
D. Wang, "Deep learning reinvents the hearing aid," IEEE Spectrum.
J. Li, M. Akagi, S. Sakamoto, S. Hongo, & Y. Suzuki, "Two-stage binaural speech enhancement with Wiener filter for high-quality speech communication," Speech Communication, 2011.
Y. Hu, F. Chen, & M. Yuan, "Evaluat ion of noise reduct ion methods for sentence recognit ion by mandarinspeaking cochlear implant listeners," Ear & hearing, 2015.
Y.-H. Lai, F. Chen, X. Lu, Y. Tsao, S.-S. Wang , & C.-H. Lee, "A Deep Denoising Autoencoder approach to improving the intelligibility of vocoded speech in cochlear implant simulation," IEEE Trans on Biomedical Engineering, 2016.
L. Deng, J. Li, Y. Gong, and R. Haeb- Umbach, "An overview of noise robust automat ic speech recognition," IEEE/ACM Trans on Audio, Speech, and Language Processing, 2014.
P. Scalart , "Speech enhancement based on a priori signal to noise estimation," in International Conf. on Acoustics, Speech and Signal Processing (ICASSP), 1996.
S. F. Boll, "Suppression of acoustic noise in speech using spectral subtract ion," IEEE Trans on Acoustics, Speech and Signal Processing, 1979.
K. W. Wilson, P. Smaragdis, B. Raj & A. Divakaran, "Speech denoising using nonnegat ive matrix factorizat ion with priors," in Internat ional Conf. on Acoust ics, Speech and Signal Processing (ICASSP), 2008
Szu-Wei Fu, Yu Tsao, Xugang Lu & Hisashi Kawai, “Raw Waveformbased Speech Enhancement by Fully Convolut ional Networks”, P roc. of APSIPA Annual Summit and Conference 2017.
C. Valent ini-Bot inhao, X. Wang, S. akaki and J. Yamagishi, "Speech Enhancement for a Noise-Robust Text -to-Speech Synthesis System using Deep Recurrent Neural Networks", In Proceedings, Interspeech 2016.
Wang, DeLiang, and Jitong Chen. supervised speech separat ion based on deep learning: An overview." IEEE/ACM Trans. on Audio, Speech, and Language Processing (2018).
S. Patibandla, M. Archana, and R. C. Tanguturi, “Object Tracking using Multi Adaptive Feature Extraction Technique,” International Journal of Engineering Trends and Technology, vol. 70, no. 6, pp. 279–286, Jun. 2022, doi: 10.14445/22315381/ijett-v70i6p229.
G. Sadineni, A. M, and R. C. Tanguturi, “Optimized Detector Generation Procedure for Wireless Sensor Networks based Intrusion Detection System,” International Journal of Engineering Trends and Technology, vol. 70, no. 6, pp. 63–72, Jun. 2022, doi: 10.14445/22315381/ijett-v70i6p208.
S. Patibandla, Dr. M. Archana, and Dr. R. C. Tanguturi, “DATA AGGREGATION BASED HYBRID DEEP LEARNING TECHNIQUE FOR IDENTIFYING THE UNCERTAINTIES AND ACCURATE OBJECT DETECTION,” Indian Journal of Computer Science and Engineering, vol. 13, no. 3, pp. 697–708, Jun. 2022, doi: 10.21817/indjcse/2022/v13i3/221303049.
Dr. S. R. Anand, Dr. R. C. Tanguturi, and S. D S, “Blockchain Based Packet Delivery Mechanism for WSN,” International Journal of Recent Technology and Engineering (IJRTE), vol. 8, no. 2, pp. 1112–1117, Jul. 2019, doi: 10.35940/ijrte.b1627.078219.
M. V. Bharathi, R. C. Tanguturi, C. Jayakumar, and K. Selvamani, “Node capture attack in Wireless Sensor Network: A survey,” 2012 IEEE International Conference on Computational Intelligence and Computing Research, Dec. 2012, doi: 10.1109/iccic.2012.6510237.

Cites this article as

[M. Balasubrahmanyam, B. Haribabu, P. Uday Kumar (2022), A New Residual Convolutional Neural Network-Based Speech Improvement, International Journal of Innovative Research in Computer Science & Technology (IJIRCST), Vol-10, Issue-6, Page No-39-42], (ISSN 2347 - 5552). www.ijircst.org

Corresponding Author

M. Balasubrahmanyam

Assistant Professor, Department of Electronics and Communication Engineering, PACE Institute of Technology and Sciences, Ongole, India

Download Full Paper

Download PDF

No. of Downloads: 11 | No. of Views: 300

Image enhancement in wavelet domain using histogram equalization and median filters

Er. Eyenan Showkat, Dr. Gurinder Kaur Sodhi.

January 2023 - Vol 11, Issue 1
pH Sensor Based on Dual Gate Organic Field Effect Transistor

Safura Hameed Bhat, Ravinder Pal Singh, Monika Mehra.

January 2023 - Vol 11, Issue 1
Design of Tri Band and Dual Band Antenna Using Meta Cell

V. Mutyala Naidu, Dr S Suryanarayana Raju, Mr. C Ramana Babu, Dr. Ch. Manohar Kumar.

November 2022 - Vol 10, Issue 6

IJIRCST

A New Residual Convolutional Neural Network-Based Speech Improvement

Citations

Download Full Paper PDF

Total View 300

Total Download 11