Total views : 325486

Mean-Median based Noise Estimation Method using Spectral Subtraction for Speech Enhancement Technique

Affiliations

  • Department of Electronics Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad - 826004, Jharkhand, India

Abstract


Background/Objectives: This article proposes a new noise estimation method which is based on mean and median statistical tools. In this article, the proposed method i.e., Mean-Median based noise estimation method have applied in the spectral subtraction method for speech enhancement technique. Methods/Statistical Analysis: The MATLAB/SIMULINK platform is used for simulating the simulation model of proposed technique. For performance evaluation of proposed noise estimation, Perceptual Evaluation of Speech Quality (PESQ) Score and Simulation time are chosen. Different noisy speech signal and clean speech signal have taken as input signal for proposed model and for finding PESQ score, respectively. Findings: The advantage of our proposed noise estimation method, it does not require signal to noise ratio, Voice Activity Detector, or histograms. This paper is carried comparison results with Modified Cascaded Median (MCM) based noise estimation method and also simulation time for different corrupted speech files. Application/Improvements: As per expected, proposed technique is given better speech quality signal (in PESQ scores). As compare to MCM based technique, it takes less simulation time and also no memory storage requirement.

Keywords

Mean-Median based Noise Estimation Method, Modified Cascaded Median based Noise Estimation, Spectral Subtraction, Speech Enhancement.

Full Text:

 |  (PDF views: 783)

References


  • Boll SF. Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans Acoust, Speech, Signal Process. 1979; 27(2):113–20.
  • Loizou PC. Speech enhancement: Theory and practice. New York: CRC; 2007.
  • Ephraim Y, Malah D. Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator. IEEE Trans Acoust, Speech, Signal Processing, 1984 Dec; ASSP-32:1109–21.
  • Hsu C-C, Lin T-E, Chen J-H, Chi T-S. Spectro-temporal subband wiener filter for speech enhancement. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); Kyoto. 2012.
  • Martin R. Spectral subtraction based on minimum statistics. Proc Eur Signal Process Conf; 1994. p. 1182–5.
  • Stahl V, Fisher A, Bipus R. Quantile based noise estimation for spectral subtraction and Wiener filtering. Proc IEEE ICASSP; Istanbul, Turkey. 2000. p. 1875–8.
  • Waddi SK, Pandey PC, Tiwari N. Speech enhancement using spectral subtraction and cascaded-median based noise estimation for hearing impaired listeners. Proc 19th Nat Conf Commun (NCC 2013); Delhi, India. 2013.
  • Pandey PC, Tiwari N. Speech enhancement using noise estimation based on dynamic quantile tracking for hearing impaired listeners. IEEE Proc 21th National Conference on Communications (NCC 2015); Mumbai: IIT; 2015.
  • Kumar B. Spectral subtraction using modified cascaded median based noise estimation for speech enhancement. ACM, 6th International Conference on Computer and Communication (ICCCT-15); Allahabad, India: MNNIT. 2015 Sep 25-27.
  • Kim S, Jang B. Development of bellows design software using MATLAB. Indian Journal of Science and Technology. 2015 Apr; 8(S8). DOI: 10.17485/ijst/2015/v8iS8/70619.
  • Koochaki A. Teaching calculation of transformer equivalent circuit parameters using MATLAB/Simulink for undergraduate electric machinery courses. Indian Journal of Science and Technology. 2015 Aug; 8(17). DOI: 10.17485/ijst/2015/v8i17/59182.
  • Sivakumar P, Vinod B, Devi RSS, Rajkumar ERJ. Real-time task scheduling for distributed embedded system using MATLAB toolboxes. Indian Journal of Science and Technology. 2015 Jul; 8(15). DOI: 10.17485/ijst/2015/v8i15/55680.
  • Pradeep M, Kumar MS, Sathiskumar S, Raja SH. Interleave isolated boost converter as a front end converter for solar/fuel cell application to attain maximum voltage in MATLAB. Indian Journal of Science and Technology. 2016 Apr; 9(16). DOI: 10.17485/ijst/2016/v9i16/92234.
  • Ahmed SF, Memon AR, Azim ChF, Desa H. Global optimal solution for active noise control problem. Indian Journal of Science and Technology. 2011; 4(9):1015–20.
  • Ganesan, Vignesh, Manoharan S. Surround noise cancellation and speech enhancement using sub band filtering and spectral subtraction. Indian Journal of Science and Technology. 2015; 8(33).
  • Kumar KR, Bhavani L, Spandana P, Rishitha K, Ashitha G. Removal of real world noise in speech: comparision of various parameters using kalman and h-infinity filter algorithms. Indian Journal of Science and Technology. 2016; 9(30).
  • Speech Enhancement Assessment Resource (SpEAR) database. CSLU; Oregon, USA. Available from: www.cslu.ogi.edu/nsel/data/SpEAR_database.html
  • ITU. Perceptual evaluation of speech quality (PESQ): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs. ITU-T Rec; 2001. p. 862.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.