A variant of SWEMDH technique based on variational mode decomposition for speech enhancement

被引:0
作者
Selvaraj, Poovarasan [1 ]
Chandra, E. [1 ]
机构
[1] Bharathiar Univ, Dept Comp Sci, Coimbatore, Tamil Nadu, India
关键词
Speech enhancement; non-stationary noises; additive white gaussian noise; intrinsic mode functions; SWEMDH technique; variational mode decomposition; narrow-band components; NOISE;
D O I
10.3233/KES-210072
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In Speech Enhancement (SE) techniques, the major challenging task is to suppress non-stationary noises including white noise in real-time application scenarios. Many techniques have been developed for enhancing the vocal signals; however, those were not effective for suppressing non-stationary noises very well. Also, those have high time and resource consumption. As a result, Sliding Window Empirical Mode Decomposition and Hurst (SWEMDH)-based SE method where the speech signal was decomposed into Intrinsic Mode Functions (IMFs) based on the sliding window and the noise factor in each IMF was chosen based on the Hurst exponent data. Also, the least corrupted IMFs were utilized to restore the vocal signal. However, this technique was not suitable for white noise scenarios. Therefore in this paper, a Variant of Variational Mode Decomposition (VVMD) with SWEMDH technique is proposed to reduce the complexity in real-time applications. The key objective of this proposed SWEMD-VVMDH technique is to decide the IMFs based on Hurst exponent and then apply the VVMD technique to suppress both low- and high-frequency noisy factors from the vocal signals. Originally, the noisy vocal signal is decomposed into many IMFs using SWEMDH technique. Then, Hurst exponent is computed to decide the IMFs with low-frequency noisy factors and Narrow-Band Components (NBC) is computed to decide the IMFs with high-frequency noisy factors. Moreover, VVMD is applied on the addition of all chosen IMF to remove both low- and high-frequency noisy factors. Thus, the speech signal quality is improved under non-stationary noises including additive white Gaussian noise. Finally, the experimental outcomes demonstrate the significant speech signal improvement under both non-stationary and white noise surroundings.
引用
收藏
页码:299 / 308
页数:10
相关论文
共 20 条
  • [1] Sparse Representations for Single Channel Speech Enhancement Based on Voiced/Unvoiced Classification
    Ben Messaoud, Mohamed Anouar
    Bouzid, Aicha
    [J]. CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2017, 36 (05) : 1912 - 1933
  • [2] Enhancement of speech dynamics for voice activity detection using DNN
    Dwijayanti, Suci
    Yamamori, Kei
    Miyoshi, Masato
    [J]. EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2018,
  • [3] Garofolo J., 1993, DARPA TIMIT acousticphonetic continuous speech corpus, DOI [10.6028/nist.ir.4930, 10.6028/NIST.IR.4930, DOI 10.6028/NIST.IR.4930]
  • [4] Ghahabi O., 2018, P ESSV
  • [5] Robust noise power spectral density estimation for binaural speech enhancement in time-varying diffuse noise field
    Ji, Youna
    Baek, Yonghyun
    Park, Young-Cheol
    [J]. EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2017, : 1 - 16
  • [6] Decision-directed speech power spectral density matrix estimation for multichannel speech enhancement
    Jin, Yu Gwang
    Shin, Jong Won
    Kim, Nam Soo
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2017, 141 (03) : EL228 - EL233
  • [7] A unified approach to speech enhancement and voice activity detection
    Kasap, Ceyhan
    Arslan, Mustafa Levent
    [J]. TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2013, 21 (02) : 527 - 547
  • [8] Kulkarni D.S, 2016, INT J COMPUTER APPL, V139
  • [9] Robust Estimation of Non-Stationary Noise Power Spectrum for Speech Enhancement
    Mai, Van-Khanh
    Pastor, Dominique
    Aissa-El-Bey, Abdeldjalil
    Le-Bidan, Raphael
    [J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2015, 23 (04) : 670 - 682
  • [10] Empirical Mode Decomposition-Based Time-Frequency Analysis of Multivariate Signals
    Mandic, Danilo P.
    Rehman, Naveed Ur
    Wu, Zhaohua
    Huang, Norden E.
    [J]. IEEE SIGNAL PROCESSING MAGAZINE, 2013, 30 (06) : 74 - 86